Category: Branches in AI

Cognitive Computing is a branch of AI that replicates human-like cognitive functions. The world today is looking for integration of artificial intelligence and Machine Learning in computers and other systems to solve complex problems. At present, many systems use Artificial Neural Network which mimic the working of human brain similar to neurons. Although it is efficient in doing so, it has a limiting point. This is where Cognitive Computing boomed.

Cognitive Computing refers to systems that mimic human through processes and simulate the way humans earn and interact with information.

What is Cognitive Computing?

Cognitive Computing aims to create systems capable of mimicking human-like cognitive functions. The word “cognitive” describes processes involved in perception, learning, reasoning, and problem-solving, i.e., functions related to human intelligence. Cognitive computing aims to create systems able to comprehend, interpret, and respond to complex information like the way humans do.

Features of Cognitive Computing

Some of the features of cognitive computing are −

• Adoptive: Mimic the ability of human brain to learn and adopt from the surroundings.
• Interactive: Interact with all elements in the system – processor, devices, cloud services, and user.
• Iterative and Stateful: Learn from past experiences, and return suitable information.
• Contextual: Identify contextual elements such as meaning, syntax, time, location, users profile, etc.

How Cognitive Computing Works?

The systems used in cognitive computing combine structured and unstructured data from various sources to solve the types of problems that humans are typically tasked to refine the way they identify patterns and process data. To achieve these capabilities, cognitive computing systems must have the following attributes −

• Adaptive: Systems must be flexible enough to learn as much as information possible. They must be flexible with dynamic data and adjust with the changing environment.
• Interactive: Human-computer interaction is a critical component in cognitive systems. Users should be able to interact with cognitive machines and define their needs.
• Interactive and Stateful: These technologies can ask questions and pull in additional data to identify or clarify a problem.
• Contextual: Cognitive computing should be able to understand, identify, and mine contextual data, such as syntax, time, location, domain, user requirements, user profiles, tasks and goals.

Benefits of Cognitive Computing

Some of the benefits of cognitive computing are −

• Enhanced Decision making: Working with large data and recognizing patterns helps decision-making with a data-driven edge.
• Improved Efficiency: Allows organizations to focus on higher-value tasks, saving time and resources while enhancing overall productivity by automating tasks that are repetitive, optimizing workflow with no human intervention.
• Natural Language Understanding: Facilities more interactive and natural conversation between humans and machines.

Disadvantages of Cognitive Computing

Some of the challenges of cognitive computing −

• Data Privacy: Cognitive computing relies heavily on data analysis, which raises concerns about the privacy and security of sensitive information.
• Complexity: Implementation of cognition solutions can be complex and may require integration with existing systems.
• Ethical and Bias: Biases present in the training data will lead to unfair or discriminatory outcomes.

Real-World Examples of Cognitive Computing

Cognitive computing is widely applied in various real-world scenarios which include −

• IBM Watson for Oncology is used for analyzing medical and clinical trial data, and patient records to recommend personalized treatment options especially for cancer patients.
• Cognitive computing systems analyze vast amounts of financial data in real-time to detect patters and anomalies, helping financial organizations to identify potential fraudulent activities.
• Most businesses and organizations are using cognitive computing to develop smart virtual assistants and chat-bots that can interpret natural language, respond to customer questions, and offer personalized support.
• Cognitive systems help automate the hiring process by scanning resumes, screening applicants, and even performing preliminary interviews, making the hiring process more efficient.

What is Swarm Intelligence?

Swarm Intelligence is the branch of AI that is a collection of behavior of various decentralized, self-organized systems. In a better way to explain, living organisms in nature like birds, fish, ants, and others make complex decisions in groups. Artificial intelligence applies similar principles for dynamic and effective decisions.

Aspects of Swarm Intelligence

Some of the key aspects of swarm intelligence are −

• Decentralized: No single entity dictates the swarm’s behavior, each individual makes decisions based on local information and learning’s from interactions with nearby members.
• Self-Organized: Complex collective behavior emerges form simple rules followed by individuals without any central coordination.
• Adaptable: When individual edge devices are able to recognize and share critical information with their peers, the entire network becomes smarter and more adaptable.
• Scalability: Swarm systems are able to work effectively with different sizes of individuals, scaling to different problem sizes.
• Emergent Behavior: The swarm’s group behavior is more than the sum of all individual behaviors, creating new and unexpected patterns.
• Collective Decision-Making: The swarm as a whole can make decisions through voting mechanisms, even without a leader.

How does Swarm intelligence Work?

Swarm Intelligence is a form of collective learning and decision-making based on decentralized, self-organized systems. As a form of artificial intelligence, swarm intelligence comprises a network of endpoint devices capable of generating and processing data at the source. Relevant information that fits certain predetermined conditions can be shared across the network, allowing individual agents to process and act on dynamic environment.

For example, self-driving vehicles able to gather and process traffic data could share it with other vehicles in the network to allow them to react to changing traffic conditions.

Examples of Swarm Intelligence Algorithms

Some of the common examples of swarm intelligence algorithms −

• Ant Colony Optimization: This algorithm is inspired by the behavior of ants, used for optimization problems like finding the shortest path.
• Particle Swarm Optimization: Mimics the movement of bird flocks, where individuals adjust their position based on their own experience and the best solution found in the group.
• Bacterial Foraging Optimization: This algorithm is developed based on the behavior of bacteria, used for optimization problems with dynamic environments.
• Firefly Algorithm: Inspired by the behavior of fireflies, used for optimization problems where individuals search for the best solutions by moving towards brighter “fireflies”.

Challenges in Swarm Intelligence

While the basic principles are simple, understanding, and controlling the emergent behavior of a swarm can be complex, especially while dealing with large-scale problems. Some of the challenges in swarm intelligence are −

• Predicting Collective Behavior: Difficult to predict the behavior from the individual rules.
• Interpretability Issues: The functions of colony could not be understood with knowledge of functioning of a agent.
• Premature Convergence: The swarm might settle on a sub optimal solution too quickly.
• Parameter Tuning: Achieving optimal results often requires careful adjustment of algorithm settings.
• Stochastic Nature: The randomness in swarm intelligence algorithms can lead to inconsistent results.
• Computational Resources & Scalability: These algorithms can be computationally intensive, especially with larger, more complex problems, and their performance might degrade as problem complexity increases.

What is Evolutionary Computation?

Evolutionary Computation is a branch of artificial intelligence that is inspired by biological evolution to solve complex problems. These algorithms are originated from biological concepts such as selection, mutation, and reproduction. Some of the most common algorithms include Genetic Algorithms, Evolution Strategies, and Differential Evolution.

Motivation for Evolutionary Computation

The major motivation for developing evolutionary computation includes −

• Nature has always been an inspiration for engineers and scientists.
• To develop new problem solving methods which is the key theme in mathematics and computer science.
• Increased complexity of problems to be solved.
• Increased requirement for robust problem solving technologies.
• Rise of problems that are too complex to be solved by the existing algorithms.

Implementation of Evolutionary Computation

Following are the steps required to implement evolutionary computation −

• Defining Problem: The initial step involves clearly defining the problems and identifying an optimized solution.
• Initialization: A population of potential solution, or individuals is initialized randomly.
• Selection: Individuals from the population are selected, based on their fitness to reproduction.
• Variation: Selected individuals undergo variations through genetic operators lie crossover and mutation.
• Evaluation and Iteration: These newly generated individuals are evaluated, and the cycle is often iterated until a termination is initiated.

Evolutionary Algorithms

Evolutionary algorithms are a class of algorithms that use natural section to solve problems. The basic algorithm of evolutionary computation is as follows −

INITIALIZE population w/ random Individuals
REPEAT until
EVALUATE population/individual fitness
SELECT parents with highest fitness
COMBINE parents to form offspring
MUTATE resulting offspring
NEXT POPULATION = offspring

The five key mechanism in evolutionary computation algorithms include recombination, mutation, evaluation and selection, and mimicking natural processes of evolution in their functioning.

Evolutionary Computation encompasses the following AI algorithms −

• Genetic Algorithms
• Evolution Strategies
• Evolutionary Programming
• Genetic Programming

Benefits of Evolutionary Computation

Some of the key benefits of evolutionary computation in businesses and organizations in a number of ways include −

• Fast Processing Time: Compared to other manual analysis and more complex AI techniques like neural networks, evolutionary systems have the capability to process large datasets and reach an optimal solution at a faster rate. When the iteration no longer produces better solutions, the process automatically terminates and yields the optimized solution.
• Enhancing other machine learning methods: Evolutionary AI algorithms can quickly complete tasks such as classification, and then this information can be fed into more complex machine learning algorithms for further analysis.
• Network Security: Evolutionary computation can detect the attacks on networks in real time. This enables companies to act rapidly to malfunctions and major damages.

Applications of Evolutionary Computation

The use cases of evolutionary computation is across various fields and domains −

• Engineering and Designing: Evolutionary computation has various applications in numerous engineering fields, from optimizing aerodynamic shapes to designing circuits.
• Machine Learning: In machine learning, evolutionary computation algorithms can be used to train large datasets especially in neural networks, tune hyper parameters, and evolve decision making.
• Game Development: Evolutionary computation algorithms assist in creating intelligent opponents in games, creative and engaging games, and game testing.
• Bio-informatics: Evolutionary computation can be used in bio-informatics in domains like gene expression data analysis, prediction of protein structure, and more.
• Financial Forecasting: Evolutionary computation can be used in finance sector in tasks like optimizing portfolio, prediction of stock market, and others.

Challenges in Evolutionary Computation

Despite the capabilities evolutionary computation provides, it has certain challenges too which include −

• Parameter Tuning: Finding the right parameters for evolutionary algorithms can be a difficult tasks, affecting their efficiency and effectiveness.
• Convergence Speed: Evolutionary computation algorithms can sometimes be time-taking to find an optimal solution, which can be a disadvantage while dealings with time-sensitive applications.
• Noisy and Dynamic Problem Spaces While evolutionary computation algorithms are effective, they still present complications in maintaining diversity and ensuring convergence.

What are Artificial Neural Networks (ANNs)?

Artificial Neural Networks (ANNs) Artificial Neural Networks are parallel computing devices, which are basically an attempt to make a computer model of the brain. The main objective is to develop a system to perform various computational tasks faster than the traditional systems.

The inventor of the first neuro-computer, Dr. Robert Hecht-Nielsen, defines a neural network as −

“A computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.”

Basic Structure of ANNs

The idea of ANNs is based on the belief that working of human brain by making the right connections, can be imitated using silicon and wires as living neurons and dendrites.

The human brain is composed of 86 billion nerve cells called neurons. They are connected to other thousand cells by Axons. Stimuli from external environment or inputs from sensory organs are accepted by dendrites. These inputs create electric impulses, which quickly travel through the neural network. A neuron can then send the message to other neuron to handle the issue or does not send it forward.

ANNs are composed of multiple nodes, which imitate biological neurons of human brain. The neurons are connected by links and they interact with each other. The nodes can take input data and perform simple operations on the data. The result of these operations is passed to other neurons. The output at each node is called its activation or node value.

Each link is associated with weight. ANNs are capable of learning, which takes place by altering weight values. The following illustration shows a simple ANN −

Artificial Neurons Vs Biological Neurons

Some of the differences between artificial neurons and biological neurons are tabulated below.

Feature	Biological Neurons	Artificial Neurons
Structure	Complex with cell body, dendrites, and axons.	Simplifies mathematical function.
Functionality	Signals interpreted through action potentials and neurotransmitters.	Computes weighted sums and applies an activation function.
Communication	Uses chemical and electrical signals for inter-neuron communication	Communicates through numerical data and mathematical models
Processing Speed	Slower transmission due to chemical processes.	Extremely fast computations based on electronic processing.
Energy Efficiency	Highly energy efficient and is capable of operating on small amounts of energy.	Generally less energy-efficient, varies by architecture and implementation.
Complexity	Highly complex, involves various types of neurons and glacial cells, and intricate chemical signaling.	Simpler in structure but can scale up to model complex behaviors through layers of neurons in neural networks.
Execution	Operates in real-time within biological systems.	Operates in digital environments, requiring hardware and software.
Learning	Learns through experience and can generalize in complex ways.	Learns through datasets and optimization techniques, often requiring large datasets.

Types of ANNs

Neural networks are classified into different categories based on factors like their depth, the number of hidden layers, and the I/O capabilities of each node. Types of neural networks include −

• Convolutional Neural Networks
• Deconvolutional Neural Networks
• Recurrent Neural Networks
• Feed-forward Neural Networks
• Modular Neural Networks
• Generative Adversarial Networks

Topologies of ANNs

There are two Artificial Neural Network topologies − FeedForward and Feedback.

FeedForward ANN

In this ANN, the information flow is unidirectional. A unit sends information to other unit from which it does not receive any information. There are no feedback loops. They are used in pattern generation/recognition/classification. They have fixed inputs and outputs.

FeedBack ANN

Feedback ANN have connections that loop back, which allows to fed back information into the structure. This structure enables to handle sequential data and temporal dependencies, making them suitable for tasks like time series prediction and language modeling.

Working of ANNs

In the topology diagrams shown, each arrow represents a connection between two neurons and indicates the pathway for the flow of information. Each connection has a weight, an integer number that controls the signal between the two neurons.

If the network generates a “good or desired” output, there is no need to adjust the weights. However, if the network generates a “poor or undesired” output or an error, then the system alters the weights in order to improve subsequent results.

Machine Learning in ANNs

ANNs are capable of learning and they need to be trained. There are several learning strategies −

• Supervised Learning: It involves a teacher that is scholar than the ANN itself. For example, the teacher feeds some example data about which the teacher already knows the answers.For example, pattern recognizing. The ANN comes up with guesses while recognizing. Then the teacher provides the ANN with the answers. The network then compares it guesses with the teacher’s “correct” answers and makes adjustments according to errors.
• Unsupervised Learning: It is required when there is no example data set with known answers. For example, searching for a hidden pattern. In this case, clustering i.e. dividing a set of elements into groups according to some unknown pattern is carried out based on the existing data sets present.
• Reinforcement Learning: This strategy built on observation. The ANN makes a decision by observing its environment. If the observation is negative, the network adjusts its weights to be able to make a different required decision the next time.

Applications of ANNs

They can perform tasks that are easy for a human but difficult for a machine −

• Aerospace: Autopilot aircrafts, aircraft fault detection.
• Automotive: Automobile guidance systems.
• Military: Weapon orientation and steering, target tracking, object discrimination, facial recognition, signal/image identification.
• Electronics: Code sequence prediction, IC chip layout, chip failure analysis, machine vision, voice synthesis.
• Financial: Real estate appraisal, loan advisor, mortgage screening, corporate bond rating, portfolio trading program, corporate financial analysis, currency value prediction, document readers, credit application evaluators.
• Industrial: Manufacturing process control, product design and analysis, quality inspection systems, welding quality analysis, paper quality prediction, chemical product design analysis, dynamic modeling of chemical process systems, machine maintenance analysis, project bidding, planning, and management.
• Medical: Cancer cell analysis, EEG and ECG analysis, prosthetic design, transplant time optimizer.
• Speech: Speech recognition, speech classification, text to speech conversion.
• Telecommunications: Image and data compression, automated information services, real-time spoken language translation.
• Transportation: Truck Brake system diagnosis, vehicle scheduling, routing systems.
• Software: Pattern Recognition in facial recognition, optical character recognition, etc.
• Time Series Prediction: ANNs are used to make predictions on stocks and natural calamities.
• Signal Processing: Neural networks can be trained to process an audio signal and filter it appropriately in the hearing aids.
• Control: ANNs are often used to make steering decisions of physical vehicles.
• Anomaly Detection: As ANNs are expert at recognizing patterns, they can also be trained to generate an output when something unusual occurs that misfits the pattern.

There are some situations where we cannot make a yes or no decision. This can be due to lack of information, unclear situation or dilemma. Similarly, there are conditions where computers face this kind of situation in decision-making. Fuzzy Logic is used to handle these uncertainties.

What is Fuzzy Logic?

Fuzzy Logic (FL) is a method of reasoning that resembles human reasoning. The approach of FL imitates the way of decision making in humans that involves all intermediate possibilities between digital values YES and NO.

The conventional logic block that a computer can understand takes precise input and produces a definite output as TRUE or FALSE, which is equivalent to human’s YES or NO.

The inventor of fuzzy logic, Lotfi Zadeh, observed that unlike computers, the human decision making includes a range of possibilities between YES and NO, such as −

Probabilities
CERTAINLY YES
POSSIBLY YES
CANNOT SAY
POSSIBLY NO
CERTAINLY NO

The fuzzy logic works on the levels of possibilities of input to achieve the definite output.

Characteristics of FLS’s

Following are the characteristics of fuzzy logic systems −

• Versatile and simple method for applying machine learning technology.
• Allows to replicate the logical process of human reasoning.
• Can easily be modified to enhance or raise system performance.
• Fuzzy logic can control nonlinear systems that might be challenging to handle mathematically.

Architecture of FLS’s

The fundamental architecture of fuzzy logic systems includes four components which include −

• Knowledge Base − It stores IF-THEN rules provided by experts.
• Inference Engine − It simulates the human reasoning process by making fuzzy inference on the inputs and IF-THEN rules.
• Defuzzification Module − It transforms the fuzzy set obtained by the inference engine into a crisp value.
• Fuzzification Module − It transforms the system inputs, which are crisp numbers, into fuzzy sets. It splits the input signal into five steps.

Following are the five steps of the Fuzzification Module −

Step	Description
LP	x is Large Positive
MP	x is Medium Positive
S	x is Small
MN	x is Medium Negative
LN	x is Large Negative

Membership Function

Membership functions allow you to quantify linguistic term and represent a fuzzy set graphically. A membership function for a fuzzy set A on the universe of discourse X is defined as μ_A:X → [0,1].

Here, each element of X is mapped to a value between 0 and 1. It is called membership value or degree of membership. It quantifies the degree of membership of the element in X to the fuzzy set A.

• x axis represents the universe of discourse.
• y axis represents the degrees of membership in the [0, 1] interval.

There can be multiple membership functions applicable to fuzzify a numerical value. Simple membership functions are used as use of complex functions does not add more precision in the output.

All membership functions for LP, MP, S, MN, and LN are shown as below −

The triangular membership function shapes are most common among various other membership function shapes such as trapezoidal, singleton, and Gaussian.

Here, the input to 5-level fuzzifier varies from -10 volts to +10 volts. Hence the corresponding output also changes.

Example for FLS’s

Let us consider an air conditioning system with 5-level fuzzy logic system. This system adjusts the temperature of air conditioner by comparing the room temperature and the target temperature value.

Algorithm of FLS’s

The algorithm of fuzzy logic system is mentioned below −

• Define linguistic Variables and terms (start)
• Construct membership functions for them. (start)
• Construct knowledge base of rules (start)
• Convert crisp data into fuzzy data sets using membership functions. (fuzzification)
• Evaluate rules in the rule base. (Inference Engine)
• Combine results from each rule. (Inference Engine)
• Convert output data into non-fuzzy values. (de-fuzzification)

Steps to Develop FLS’s

Following is the detailed step by step description to develop a fuzzy logic system −

Step 1: Define linguistic variables and terms

Linguistic variables are input and output variables in the form of simple words or sentences. For room temperature, cold, warm, hot, etc., are linguistic terms.

Temperature (t)={very-cold, cold, warm, very-warm, hot}

Every member of this set is a linguistic term and it can cover some portion of overall temperature values.

Step 2: Construct membership functions for them

The membership functions of temperature variable are as shown −

Step 3: Construct knowledge base rules

Create a matrix of room temperature values versus target temperature values that an air conditioning system is expected to provide.

RoomTemp. /Target	Very_Cold	Cold	Warm	Hot	Very_Hot
Very_Cold	No_Change	Heat	Heat	Heat	Heat
Cold	Cool	No_Change	Heat	Heat	Heat
Warm	Cool	Cool	No_Change	Heat	Heat
Hot	Cool	Cool	Cool	No_Change	Heat
Very_Hot	Cool	Cool	Cool	Cool	No_Change

Build a set of rules into the knowledge base in the form of IF-THEN-ELSE structures.

Sr. No.	Condition	Action
1	IF temperature=(Cold OR Very_Cold) AND target=Warm THEN	Heat
2	IF temperature=(Hot OR Very_Hot) AND target=Warm THEN	Cool
3	IF (temperature=Warm) AND (target=Warm) THEN	No_Change

Step 4: Obtain fuzzy value

Fuzzy set operations perform evaluation of rules. The operations used for OR and AND are Max and Min respectively. Combine all results of evaluation to form a final result. This result is a fuzzy value.

Step 5: Perform de-fuzzification

De-fuzzification is then performed according to membership function for output variable.

Application Areas of FLS’s

The key application areas of fuzzy logic are as given −

• Fuzzy logic has been used in Natural Language Processing and various artificial intelligence applications.
• It can be use in organization that handle large data to facilitate effective decision-making.
• It is been used for controlling fuel delivery and ignition depending on throttle position, cooling water temperature, RPM, and other factors.
• It can also be used for Pattern Recognition and Classification in handwriting detection. It also serves to search for blurry images.

Advantages of FLSs

The advantages of fuzzy logic are −

• Mathematical concepts within fuzzy reasoning are very simple.
• You can modify a FLS by just adding or deleting rules due to flexibility of fuzzy logic.
• Fuzzy logic Systems can take imprecise, distorted, noisy input information.
• FLSs are easy to construct and understand.
• Fuzzy logic is a solution to complex problems in all fields of life, including medicine, as it resembles human reasoning and decision making.

Disadvantages of FLSs

While there are many advantages of fuzzy logic systems, there are certain challenges too which include −

• There is no systematic approach to fuzzy system designing.
• They are understandable only when simple.
• They are suitable for the problems which do not need high accuracy.

Robotics is a domain in Artificial Intelligence that deals with the study of creating intelligent and efficient robots.

What are Robots?

Robots are programmed machines that perform tasks automatically, with little or no human intervention.

The main objective behind robots is to aim at manipulating the objects by perceiving, picking, moving, modifying the physical properties of object, destroying it, or to have an effect thereby freeing manpower from doing repetitive functions without getting bored, distracted, or exhausted.

What is Robotics?

Robotics is a branch of engineering and computer science that involves training and programming machines to replicate or substitute for human actions. These robots are designed to perform basic and repetitive tasks with greater efficiency and accuracy than humans.

Aspects of Robotics

Some of the key aspects of robotics are listed below −

• The robots have mechanical construction, form, or shape designed to accomplish a particular task.
• They have electrical components which power and control the machinery.
• They contain some level of computer program that determines what, when and how a robot does something.

Role of AI in Robotics

Robotics and Artificial Intelligence are closely related fields, which when integrated give rise to a machine that could think intelligently just like humans. Some of the key benefits of integration of AI include −

• AI makes robots human friendly, and enhances the overall productivity of an organization through improved efficiency and quality.
• This integration of AI with robotics allows machines to perform complex tasks with ease.
• Robots use AI to learn from past experiences, adapt to new situations and make data driven decisions.
• Additionally, the other branches of AI such as Machine learning allows in analyzing large datasets to recognize patterns and improve its performance in dynamic environment and Computer Vision helps the robot understand visual data to effectively perform tasks like navigation and object recognition.

Difference Between Robot System and Other AI Program

The differences between robot system and other AI program’s are tabulated below −

AI Programs	Robots
They usually operate in computer-stimulated worlds.	They operate in real physical world
The input to an AI program is in symbols and rules.	Inputs to robots is analog signal in the form of speech waveform or images
They need general purpose computers to operate on.	They need special hardware with sensors and effectors.

Components of a Robot

Robots have several components, which includes −

• Power Supply: The robots are powered by batteries, solar power, hydraulic, or pneumatic power sources.
• Actuators: They convert energy into movement.
• Electric motors (AC/DC): They are required for rotational movement.
• Pneumatic Air Muscles: They contract almost 40% when air is sucked in them.
• Muscle Wires: They contract by 5% when electric current is passed through them.
• Piezo Motors and Ultrasonic Motors: Best for industrial robots.
• Sensors: They provide knowledge of real time information on the task environment. Robots are equipped with vision sensors to be to compute the depth in the environment. A tactile sensor imitates the mechanical properties of touch receptors of human fingertips.

Robot Locomotion

Locomotion is the mechanism that makes a robot capable of moving in its environment. There are various types of locomotions −

• Legged
• Wheeled
• Combination of Legged and Wheeled Locomotion
• Tracked slip/skid

Legged Locomotion

This type of locomotion consumes more power while demonstrating walk, jump, trot, hop, climb up or down, etc. It requires more number of motors to accomplish a movement. It is suited for rough as well as smooth terrain where irregular or too smooth surface makes it consume more power for a wheeled locomotion. It is little difficult to implement because of stability issues.

It comes with the variety of one, two, four, and six legs. If a robot has multiple legs then leg coordination is necessary for locomotion. For example −

The total number of possible gaits (a periodic sequence of lift and release events for each of the total legs) a robot can travel depends upon the number of its legs.

If a robot has k legs, then the number of possible events N = (2k-1)!.

In case of a two-legged robot (k=2), the number of possible events is N = (2k-1)! = (2*2-1)! = 3! = 6.

Hence there are six possible different events −

• Lifting the Left leg
• Releasing the Left leg
• Lifting the Right leg
• Releasing the Right leg
• Lifting both the legs together
• Releasing both the legs together

In case of k=6 legs, there are 39916800 possible events. Hence the complexity of robots is directly proportional to the number of legs.

Wheeled Locomotion

It requires fewer number of motors to accomplish a movement. It is little easy to implement as there are less stability issues in case of more number of wheels. It is power efficient as compared to legged locomotion.

• Standard wheel: Rotates around the wheel axle and around the contact
• Castor wheel: Rotates around the wheel axle and the offset steering joint.
• Swedish 45^o and Swedish 90^o wheels: Omni-wheel, rotates around the contact point, around the wheel axle, and around the rollers.
• Ball or spherical wheel: Omni-directional wheel, technically difficult to implement.

Slip/Skid Locomotion

In this type, the vehicles use tracks as in a tank. The robot is steered by moving the tracks with different speeds in the same or opposite direction. It offers stability because of large contact area of track and ground.

Components of a Robot

Robots are constructed with the following −

• Power Supply: The robots are powered by batteries, solar power, hydraulic, or pneumatic power sources.
• Actuators: They convert energy into movement.
• Electric motors (AC/DC): They are required for rotational movement.
• Pneumatic Air Muscles: They contract almost 40% when air is sucked in them.
• Muscle Wires: They contract by 5% when electric current is passed through them.
• Piezo Motors and Ultrasonic Motors: Best for industrial robots.
• Sensors: They provide knowledge of real time information on the task environment. Robots are equipped with vision sensors to be to compute the depth in the environment. A tactile sensor imitates the mechanical properties of touch receptors of human fingertips.

Applications of Robotics

The robotics has been instrumental in the various domains such as −

• Industries: Robots are used for handling material, cutting, welding, color coating, drilling, polishing, etc.
• Military: Autonomous robots can reach inaccessible and hazardous zones during war. A robot named Daksh, developed by Defense Research and Development Organization (DRDO), is in function to destroy life-threatening objects safely.
• Medicine: The robots are capable of carrying out hundreds of clinical tests simultaneously, rehabilitating permanently disabled people, and performing complex surgeries such as brain tumors.
• Exploration: The robot rock climbers used for space exploration, underwater drones used for ocean exploration are to name a few.
• Entertainment: Disney’s engineers have created hundreds of robots for movie making.

What is Computer Vision?

Computer Vision is a field of artificial intelligence that uses Machine Learning and Neural Networks to teach computers and systems to interpret and extract information from images and videos. This extracted information can be used for identifying and making decisions.

Role of AI in Computer Vision

Computer Vision and Artificial Intelligence complement each other, enhancing their abilities to accomplish development. Although AI lays the foundation for data analysis and decision making, computer vision introduces the aspect of visual understanding to this combination.

Computer Vision is a technology that in combination with AI allows machines to comprehend and analyze visual information, resembling the mechanism of human sight.

How does Computer Vision Work?

Computer vision requires large amounts of data, where it runs analyses of data over and over until it experts in distinguishing and recognizing images. For example, to train a computer recognize a dog in an image, it needs to be fed with vast qualities of different dog breed images to effectively recognize.

The most essential technologies which are used to effectively develop computer visions are Deep Learning, Convolutional Neural Network, and Machine Learning.

Machine Learning uses algorithms and models to enable computers to learn by itself in the context of visual data. The computer has to be fed with enough large data, for it to teach itself and differentiate the images. Convolutional neural Networks (CNN) helps machine learning model by breaking them down to pixels that are given tags or labels. These labels are used to perform convolutions and make predictions. A recurrent Neural Network (RNN) is used in a similar way but for video applications to help computers visualize series of frames and relate to each other.

Hardware of Computer Vision System

Some of the most commonly used hardware components are listed below −

• Power supply
• Image acquisition device such as camera
• A processor
• A software
• A display device for monitoring the system
• Accessories such as camera stands, cables, and connectors

Tasks of Computer Vision

Following is the list of tasks that incorporate computer vision to improve efficiency and productivity −

• Optical Character Reader (OCR): In the domain of computers OCR is a software to convert scanned documents into editable text, which accompanies a scanner.
• Face Detection: Many state-of-the-art cameras come with this feature, which enables to read the face and take the picture of that perfect expression. It is used to let a user access the software on correct match.
• Object Recognition: They are installed in supermarkets, cameras, high-end cars such as BMW, GM, and Volvo.
• Estimating Position: It is estimating position of an object with respect to camera as in position of tumor in humans body.

Application Domains of Computer Vision

Computer Vision has wide range of applications across various fields. Some of them include −

• Agriculture: Companies are employing computer vision in agriculture for sowing and harvesting purposes. Additionally, these solutions are also useful for weeding, detecting plant health, and advanced weather analysis.
• Autonomous Vehicles: Computer vision allows the vehicle to make autonomous decisions. Some of the tasks that engage computer vision are advanced processes such as path planning, driving scene perception, and behavior arbitration.
• Face Recognition: Computer vision can be used in detecting and recognizing faces in public, which is already being implemented in certain jurisdiction.
• Interactive Entertainment: These solutions use computer vision to deliver truly immersive experiences. For example, smart eye wear demonstrates how users can receive information about what they see while looking at it.
• Human Pose Tracking: These use computer vision to process visual inputs and estimate human posture. This is applied in industries such as gaming, robotics, fitness apps, and physical therapy.
• Medical Imagery: Medical systems depend mostly on pattern detection and image classification for diagnoses. Computer vision is mostly deployed in departments of pathology, radiology, and ophthalmology for visual pattern recognition.
• Manufacturing: Computer vision is used in predictive maintenance in their inspection systems, additionally it is used to automate processes.
• Retail Management: Retail stores use computer vision to monitor shopping activity, making predictions to prevent loss, and to make customer friendly.
• Education: Teachers use computer vision solutions to evaluate the learning process, identify disengaged students, and personalize teaching to ensure that they are not left behind.
• Transport: Computer Visions is being increasingly applied to increase transportation efficiency especially to detect traffic signal violators, detect speeding, wrong-side driving violations, and to identify disruptive behaviors.

Challenges of Computer Vision

Despite the advancements in Computer Vision, it faces several other challenges that can affect accurate interpretation of image and video analysis −

• Variability in Images: Images can vary in quality, lighting, angle, and background, making it difficult to analyze.
• Perspective and Scale Variability: Objects can appear differently depending on their distance,angle, or size in relation to the camera. This variability in perspective and scale presents a significant challenge for computer vision systems.
• Contextual Understanding: Computer vision systems often require help with understanding context. They can identify individual objects in an image, but understanding the relationship between them and interpreting the scene can be quite challenging.

What is Natural Language Processing?

Natural Language Processing (NLP)refers to AI method of communicating with an intelligent systems using a natural language such as English. Processing of natural language is required when you want an intelligent system like robot to perform as per your instructions, when you want to hear decision from a dialogue based clinical expert system, etc.

The field of NLP involves making computers to perform useful tasks with the natural languages humans use. The input and output of an NLP system can be speech or a written text.

Key Terms in NLP

Some of the key terms and concepts in natural language processing are listed below −

• Phonology − It is study of organizing sound systematically.
• Morphology − It is a study of construction of words from primitive meaningful units.
• Morpheme − It is primitive unit of meaning in a language.
• Syntax − It refers to arranging words to make a sentence. It also involves determining the structural role of words in the sentence and in phrases.
• Semantics − It is concerned with the meaning of words and how to combine words into meaningful phrases and sentences.
• Pragmatics − It deals with using and understanding sentences in different situations and how the interpretation of the sentence is affected.
• Discourse − It deals with how the immediately preceding sentence can affect the interpretation of the next sentence.
• World Knowledge − It includes the general knowledge about the world.

Techniques in NLP

Techniques in NLP are methods and algorithms used to process, analyze, and understand human language and data. Some of the common NLP techniques are −

• Tokenization − It is a technique in NLP that involves splitting a sentence or phrase into smaller units known as tokens.
• Part-to-Speech Tagging − This technique in NLP involves the process of identifying and labeling works in a sentence based in their part of speech (noun, verb, adjective).
• Named Entity Recognition (NER) − This technique in NLP is used to identify named entities in the text, such as people, organizations, locations, dates, and more.
• Semantic Analysis − This technique in NLP determines the sentiment expressed in a piece of text.

Steps in NLP

For the better understanding, analysis of written and spoken language effectively the following 5 NLP steps are followed

• Lexical Analysis − It involves identifying and analyzing the structure of words. Lexicon of a language means the collection of words and phrases in a language. Lexical analysis is dividing the whole chunk of text into paragraphs, sentences, and words.
• Syntactic Analysis (Parsing) − It involves analysis of words in the sentence for grammar and arranging words in a manner that shows the relationship among the words. The sentence such as “The school goes to boy” is rejected by English syntactic analyzer.
• Semantic Analysis − It draws the exact meaning or the dictionary meaning from the text. The text is checked for meaningfulness. It is done by mapping syntactic structures and objects in the task domain. The semantic analyzer disregards sentence such as “hot ice-cream”.
• Discourse Integration − The meaning of any sentence depends upon the meaning of the sentence just before it. In addition, it also brings about the meaning of immediately succeeding sentence.
• Pragmatic Analysis − During this, what was said is re-interpreted on what it actually meant. It involves deriving those aspects of language which require real world knowledge.

Components of NLP

There are two components of NLP as given −

Natural Language Understanding (NLU)

NLU helps machine to understand and analyse human language by extracting metadata from content which includes concepts, entities, keywords, emotion, relations, and semantic roles. Understanding involves the following tasks −

• Mapping the given input in natural language into useful representations.
• Analyzing different aspects of the language.

Natural Language Generation (NLG)

It is the process of producing meaningful phrases and sentences in the form of natural language from some internal representation.

It involves −

• Text planning − It includes retrieving the relevant content from knowledge base.
• Sentence planning − It includes choosing required words, forming meaningful phrases, setting tone of the sentence.
• Text Realization − It is mapping sentence plan into sentence structure.

Challenges in NLP

Natural Language Processing often faces various challenges due to the complexity and diversity of human language. The most common challenge would be ambiguity, below the different levels of ambiguity −

• Lexical Ambiguity − It is at very primitive level such as word-level. For example, treating the word “board” as noun or verb?
• Syntax Level Ambiguity − A sentence can be parsed in different ways. For example, “He lifted the beetle with red cap.” − Did he use cap to lift the beetle or he lifted a beetle that had red cap?
• Referential ambiguity − Referring to something using pronouns. For example, Rima went to Gauri. She said, “I am tired.” − Exactly who is tired?

What is Artificial Intelligence?

Artificial Intelligence is the ability of machines to perform tasks like thinking, reasoning, and learning similar to humans. It is a broad field in science that includes various techniques like Machine learning, Natural Language Processing, Robotics, and more.

What is Machine Learning?

Machine learning (ML) is a subset of artificial intelligence that enables machines to learn from data without being explicitly programmed. It uses algorithms to analyze large amounts of data, learn from the insights, and gain patterns and make informed decisions.

In simple words, the machine “learns” from the data and uses this knowledge to make predictions and decisions.

Machine learning algorithms enhance their performance over time as they undergo continuous training and exposed to additional data. Machine learning models are the output or what the program learns by executing an algorithm on training data. The greater the amount of data used, the better the model will get.

There are three main types of machine learning −

• Supervised Learning: In this type of learning, the machine is given labeled data to train algorithms especially to classify data or predict outcomes. Some of the algorithms include Linear regression, Logistic regression, Random Forest, and other.
• Unsupervised Learning: In this type of learning, the machine is given unlabeled datasets to algorithms to find hidden patterns or data groupings. There are three types of unsupervised learning tasks which include clustering, association rule, and dimensionality reduction.
• Reinforcement Learning: In this type of learning, an agent is trained to interpret the environment and learns from the feedback which is can be a reward (positive feedback) or penalty (negative feedback).

Artificial Intelligence and Machine Learning are two term that are often used interchangeably. However, they are not the same thing but are closely connected.

Relationship Between AI and ML

Understanding the relationship between AI and ML is important for developing intelligent systems. The simplest way to understand this is −

• AI is the broader concept of enabling a system to think, act, and learn like humans.
• ML is an application of AI that allows machines to learn from data and gain knowledgeable insights.

Artificial Intelligence is the branch of computer science that covers a variety of approaches and algorithms, and machine learning being one of it.

Machine Learning Vs Artificial Intelligence

We are often confused between machine learning and artificial intelligence. The table below consists of the difference between both the terms −

Aspect	Artificial Intelligence (AI)	Machine Learning (ML)
Definition	AI refers to the enabling systems to think, act, and learn similar to humans.	ML is a subset of AI that focuses on algorithms that learn from data and gain insights.
Scope	AI is a broad field that consists of various other technologies like Natural Language Processing and Robotics.
Goals	To create systems that can perform tasks replicating humans.	To develop models that can improve their performance over time as they are exposed to more data.
Techniques Used	Includes reasoning, learning, planning, and understanding.	Primarily uses statistical methods, neural networks, and decision trees.
Complexity	Often involves multiple systems and layers of abstraction.	Generally focuses on specific tasks and can be less complex.

Benefits of using AI and ML Together

AI and ML together offer some key benefits to enhance organizations and businesses which include −

• Wider Data Ranges: Analyzing and understanding a wide range of structured and unstructured data sources.
• Better Decision-Making: Improving data integrity, accelerating data processing, and reducing human error for more better and relevant decision-making.
• Efficiency: Increasing operational efficiency and reducing costs.
• Analytic Integration: Integrating predictive analytics and insights into business help them grow.

Artificial Intelligence is technology than allows systems to mimic human behavior, intelligence, and characteristics. It is not the AI, but different concepts in AI help tackle real-world problems. This chapter discusses about the main branches of artificial intelligence and the basic components of AI.

Key Aspects of AI

Some of the key aspects of AI that allows the systems to process, interpret, synthesize, and understand information are −

• Learning: This aspect allows AI systems to analyze data and interpret patterns with human intervention. For example, voice assistants like Siri or Alexa improve their grasping ability through continuous learning.
• Decision Making: The AI systems employ logical rules, probabilistic models, and algorithms to make conclusions and decisions. These systems are often designed to apply reasoning to get accurate outcomes. For example, tools like Grammarly decided when to insert commas and other punctuation marks.
• Problem-Solving: This aspect in AI involves processing data, manipulating it, and applying it solve problems in various scenarios. For example, in a chess game the AI analyzes the opponent’s moves and strategies the next moves based on the game’s rules and future scenarios.
• Perception: This aspect related to how the technology utilizes actual or simulated sensory organs. AI systems analyses data to recognize objects and understand their spatial relationships to these entities. This is usually included in tasks like image identification, object recognition, image partitioning, and video examination.

Branches of AI

Artificial intelligence includes many specialized fields, each with a unique functionality and application. Below are the ten key branches of AI and their respective roles −

Machine Learning

Machine learning(ML)is one of the most crucial branch of AI that enables machines to learn autonomously from data without explicit programming. ML systems enhance their performance continuously based on analyzing patterns and applying algorithms.

This approach is widely used to enable businesses to forecast trends and recommendation systems. ML algorithms are used in various applications including image recognition, spam filtering, and natural language processing.

Natural Language Processing

Natural Language Processing (NLP) allows computers to understand, interpret, and generate human language. By using these algorithms and linguistic rules, NLP systems analyze text and speech, to bridge the gap between humans and computers. Applications like chatbots, voice assistants, and google translator. use NLP.

Computer Vision

Computer Vision is the technology that allows machines to interpret the world visually i.e., it allows to identify objects in images and videos. Algorithmic models help computers teach themselves to differentiate one image from another. Some of the major applications of computer vision are object tracking, image classification, and facial recognition across various industries

Robotics

Robotics uses AI to develop and design programmed robots or machines that perform tasks automatically. AI is applied to make intelligent robots which can perform the tasks similar to humans. Some of the major areas of applications include manufacturing automation, medical robots, service robots, and space exploration.

Expert Systems

Expert Systems is a branch of AI which rely on obtaining the knowledge of human experts and program that knowledge into a system. This makes these systems have the ability of decision making and problem-solving. Some of the common areas of application are medical diagnosis, financial forecasting, and troubleshooting systems.

Neural Networks

Neural Networks are systems which are developed inspired by the biological neurons in human brain. This technology is applied in self-driving cars, speech recognition, image recognition, automatic machine translation, and more. The main challenges while implementing neural networks is it requires lots of data to get trained with lots of computational power.

Fuzzy Logic

Fuzzy Logic is a branch of AI that helps solve issues or statements and recognize if they are true or false. It is a mathematical method for identifying uncertainty in decision-making, and it is used in wide range of applications like control systems, decision-making systems, and pattern recognition.

Evolutionary Computation

Evolutionary Computation is a branch of AI that mimics biological evolution processes using algorithms like genetic algorithm, evolutionary programming, evolution strategies, and genetic programming. It involves creating a initial solution, evaluating its property, selecting solutions based on evaluation results, conducting evolutionary operations, and obtaining the next solution until the requirement is fulfilled.

Cognitive Computing

Cognitive Computing is a branch of AI that simulates human thought processes in a computerized model. The key features of the technology include contextual understanding, adaptive learning, and interactive capabilities. The key areas of application include healthcare diagnostics, financial analysis, and customer service.

Swarm Intelligence

Swarm Intelligence is a branch of AI which refers to the collective behavior of decentralized, self-organized systems observed in nature. This is used to explain how simple agents can work together to achieve complex tasks, without a centralized control or a leader.