WHAT IS AI ?

• In today’s rapidly advancing technological landscape, AI has become a household term. From chatbots and virtual assistants to self-driving cars and recommendation algorithms, the impact of AI is ubiquitous. 
• Rather than being explicitly programmed for specific tasks, AI systems use algorithms and vast amounts of data to recognize patterns, make decisions, and improve their performance over time.
• Artificial Intelligence encompasses a wide range of technologies, including machine learning, natural language processing, computer vision, and robotics. These technologies enable AI systems to perform complex tasks, such as speech recognition and face detection, with remarkable accuracy.

HISTORY

• The concept of Artificial Intelligence (AI) has been around for centuries, with the earliest recorded ideas dating back to ancient Greek mythology. However, the modern field of AI emerged in the 1950s, when computer scientists and researchers began exploring the possibility of creating machines that could think, learn, and solve problems like humans.
• One of the pioneering figures in the field of AI was Alan Turing, a British mathematician and computer scientist, who in 1950 proposed the Turing test, a method for determining whether a machine can exhibit intelligent behavior indistinguishable from a human.
• Over the decades, the field of AI has evolved significantly, with the development of various techniques and technologies, such as machine learning, deep learning, and natural language processing. 
• The 1980s and 1990s saw a surge in the popularity of expert systems, which were designed to mimic the decision-making process of human experts.
• In the 2000s, the rise of big data and powerful computing resources paved the way for the development of more advanced AI systems, leading to breakthroughs in areas like computer vision, speech recognition, and autonomous vehicles.

HOW DOES AI WORK ?

• Artificial intelligence (AI) enables machines to learn from data and recognize patterns in it, to perform tasks more efficiently and effectively. AI works in five steps:

  • Input: Data is collected from various sources. This data is then sorted into categories.
  • Processing: The AI sorts and deciphers the data using patterns it has been programmed to learn until it recognizes similar patterns in the data.
  • Outcomes: The AI can then use those patterns to predict outcomes.
  • Adjustments: If the data sets are considered a “fail,” AI learns from that mistake, and the process is repeated again under different conditions.
  • Assessments: In this way, AI is constantly learning and improving.

APPLICATIONS OF AI:

• Artificial Intelligence has many practical applications across various industries and domains, including:

  1. Healthcare – AI is used for medical diagnosis by analyzing medical images like X-rays and MRIs to identify diseases. For instance, AI systems are being developed to detect skin cancer from images with high accuracy.
  2. Finance – AI helps in credit scoring by analyzing a borrower’s financial history and other data to predict their creditworthiness. This helps banks decide whether to approve a loan and at what interest rate.
  3. Retail – AI is used for product recommendations by analyzing your past purchases and browsing behavior to suggest products you might be interested in. For example, Amazon uses AI to recommend products to customers on their website.
  4. Manufacturing – AI helps in quality control by inspecting products for defects. AI systems can be trained to identify even very small defects that human inspectors might miss.
  5. Transportation – AI is used for autonomous vehicles by developing self-driving cars that can navigate roads without human input. Companies like Waymo and Tesla are developing self-driving car technology.
  6. Customer service – AI-powered chatbots are used to answer customer questions and provide support. For instance, many banks use chatbots to answer customer questions about their accounts and transactions.
  7. Security – AI is used for facial recognition by identifying people from images or videos. This technology is used for security purposes, such as identifying criminals or unauthorized individuals.
  8. Marketing – AI is used for targeted advertising by showing ads to people who are most likely to be interested in the product or service being advertised. For example, social media companies use AI to target ads to users based on their interests and demographics.
  9. Education – AI is used for personalized learning by tailoring educational content to the individual needs of each student. For example, AI-powered tutoring systems can provide students with personalized instruction and feedback.

WHY IS AI IMPORTANT ?

• The widespread adoption of Artificial Intelligence (AI) has brought about numerous benefits and advantages across various industries and aspects of our lives. Here are some of the key benefits of AI:

  1. Improved Efficiency and Productivity: AI-powered systems can perform tasks with greater speed, accuracy, and consistency than humans, leading to improved efficiency and productivity in various industries. This can result in cost savings, reduced errors, and increased output.
  2. Enhanced Decision-Making: AI algorithms can analyze large amounts of data, identify patterns, and make informed decisions faster than humans. This can be particularly useful in fields such as finance, healthcare, and logistics, where timely and accurate decision-making is critical.
  3. Personalization and Customization: AI-powered systems can learn from user behavior and preferences to provide personalized recommendations, content, and experiences. This can lead to increased customer satisfaction and loyalty, as well as improved targeting and marketing strategies.
  4. Automation of Repetitive Tasks: AI can be used to automate repetitive, time-consuming tasks, freeing up human resources to focus on more strategic and creative work. This can lead to cost savings, reduced errors, and improved work-life balance for employees.
  5. Improved Safety and Risk Mitigation: AI-powered systems can be used to enhance safety in various applications, such as autonomous vehicles, industrial automation, and medical diagnostics. AI algorithms can also be used to detect and mitigate risks, such as fraud, cybersecurity threats, and environmental hazards.
  6. Advancements in Scientific Research: AI can assist in scientific research by analyzing large datasets, generating hypotheses, and accelerating the discovery of new insights and breakthroughs. This can lead to advancements in fields such as medicine, climate science, and materials science.
  7. Enhanced Human Capabilities: AI can be used to augment and enhance human capabilities, such as improving memory, cognitive abilities, and decision-making. This can lead to improved productivity, creativity, and problem-solving skills.

TYPES OF ARTIFICIAL INTELLIGENCE

• Artificial Intelligence (AI) has transformed industries, leading to significant advancements in technology, science, and everyday life. To understand AI better, we must first recognize that AI can be categorized into different types based on capabilities and functionalities.

• Type 1: Based on capabilities of AI

  • Narrow AI
  • General AI
  • Super AI

• Type 2: Based on functionality of AI

  • Reactive Machines
  • Limited Memory AI
  • Theory of Mind
  • Self-Aware AI

NARROW AI (WEAK AI):

• Narrow AI is designed and trained on a specific task or a narrow range tasks. These Narrow AI systems are designed and trained for a purpose. These Narrow systems performs their designated tasks but mainly lack in the ability to generalize tasks.

• Examples:

  • Voice assistants like Siri or Alexa that understand specific commands.
  • Facial recognition software used in security systems.
  • Recommendation engines used by platforms like Netflix or Amazon.

GENERAL AI (STRONG AI):

• General AI refers to AI systems that have human intelligence and abilities to perform various tasks. Systems have capability to understand, learn and apply across a wide range of tasks that are similar to how a human can adapt to various tasks.

• Potential Applications:

  • Robots that can learn new skills and adapt to unforeseen challenges in real-time.
  • AI systems that could autonomously diagnose and solve complex medical issues across various specializations.

SUPER AI:

• Super AI surpasses intelligence of human in solving-problem, creativity, and overall abilities. Super AI develops emotions, desires, need and beliefs of their own. They are able to make decisions of their own and solve problem of its own. Such AI would not only be able to complete tasks better than humans but also understand and interpret emotions and respond in a human-like manner.
• While Super AI remains speculative, it could revolutionize industries, scientific research, and problem-solving, possibly leading to unprecedented advancements. However, it also raises ethical concerns regarding control and regulation.

REACTIVE MACHINES:

• Reactive machines are the most basic form of AI. They operate purely based on the present data and do not store any previous experiences or learn from past actions. These systems respond to specific inputs with fixed outputs and are unable to adapt.

• Examples:

  • IBM’s Deep Blue, which defeated the world chess champion Garry Kasparov in 1997. It could identify the pieces on the board and make predictions but could not store any memories or learn from past games.
  • Google’s AlphaGo, which played the board game Go using a similar approach of pattern recognition without learning from previous games.

LIMITED MEMORY AI:

• Limited Memory AI can learn from past data to improve future responses. Most modern AI applications fall under this category. These systems use historical data to make decisions and predictions but do not have long-term memory. Machine learning models, particularly in autonomous systems and robotics, often rely on limited memory to perform better.

• Examples:

  • Self-driving cars: They observe the road, traffic signs, and movement of nearby cars, and make decisions based on past experiences and current conditions.
  • Chatbots that can remember recent conversations to improve the flow and relevance of replies.

THOERY OF MIND:

• Theory of Mind AI aims to understand human emotions, beliefs, intentions, and desires. While this type of AI remains in development, it would allow machines to engage in more sophisticated interactions by perceiving emotions and adjusting behavior accordingly.

• Potential Applications:

  • Human-robot interaction where AI could detect emotions and adjust its responses to empathize with humans.
  • Collaborative robots that work alongside humans in fields like healthcare, adapting their tasks based on the needs of the patients.

SELF-AWARENESS AI:

• Self-Aware AI is an advanced stage of AI that possesses self-consciousness and awareness. This type of AI would have the ability to not only understand and react to emotions but also have its own consciousness, similar to human awareness.

• Potential Applications:

  • Fully autonomous systems that can make moral and ethical decisions.
  • AI systems that can independently pursue goals based on their understanding of the world around them.

AGENTS IN ARTIFICIAL INTELLIGENCE

• In artificial intelligence, an agent is a computer program or system that is designed to perceive its environment, make decisions and take actions to achieve a specific goal or set of goals. The agent operates autonomously, meaning it is not directly controlled by a human operator.

• Agents can be classified into different types based on their characteristics, such as whether they are reactive or proactive, whether they have a fixed or dynamic environment, and whether they are single or multi-agent systems.

  • Reactive agents are those that respond to immediate stimuli from their environment and take actions based on those stimuli. Proactive agents, on the other hand, take initiative and plan ahead to achieve their goals. The environment in which an agent operates can also be fixed or dynamic. Fixed environments have a static set of rules that do not change, while dynamic environments are constantly changing and require agents to adapt to new situations.
  • Multi-agent systems involve multiple agents working together to achieve a common goal. These agents may have to coordinate their actions and communicate with each other to achieve their objectives. Agents are used in a variety of applications, including robotics, gaming, and intelligent systems. They can be implemented using different programming languages and techniques, including machine learning and natural language processing.

• An agent is anything that can be viewed as:

  • Perceiving its environment through sensors and
  • Acting upon that environment through actuators

STRUCTURE OF AI AGENT:

• To understand the structure of Intelligent Agents, we should be familiar with Architecture and Agent programs. 

• Architecture is the machinery that the agent executes on. It is a device with sensors and actuators, for example, a robotic car, a camera, and a PC. An agent program is an implementation of an agent function. An agent function is a map from the percept sequence(history of all that an agent has perceived to date) to an action. 
   

                             Agent = Architecture + Agent Program

TYPES OF AGENTS:

• Agents can be grouped into five classes based on their degree of perceived intelligence and capability :

  • Simple Reflex Agents
  • Model-Based Reflex Agents
  • Goal-Based Agents
  • Utility-Based Agents
  • Learning Agent
  • Multi-agent systems
  • Hierarchical agents

SIMPLE REFLEX AGENTS:

• Simple reflex agents ignore the rest of the percept history and act only on the basis of the current percept.
• Percept history is the history of all that an agent has perceived to date. The agent function is based on the condition-action rule. A condition-action rule is a rule that maps a state i.e., a condition to an action. If the condition is true, then the action is taken, else not.
• This agent function only succeeds when the environment is fully observable. For simple reflex agents operating in partially observable environments, infinite loops are often unavoidable.

• Problems with Simple reflex agents are : 

  • Very limited intelligence.
  • No knowledge of non-perceptual parts of the state.
  • Usually too big to generate and store.
  • If there occurs any change in the environment, then the collection of rules needs to be updated.

MODEL BASED REFLEX AGENTS:

• It works by finding a rule whose condition matches the current situation. A model-based agent can handle partially observable environments by the use of a model about the world.

• The agent has to keep track of the internal state which is adjusted by each percept and that depends on the percept history. The current state is stored inside the agent which maintains some kind of structure describing the part of the world which cannot be seen. 

GOAL BASED AGENTS:

• These kinds of agents take decisions based on how far they are currently from their goal(description of desirable situations). Their every action is intended to reduce their distance from the goal.

• This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state. The knowledge that supports its decisions is represented explicitly and can be modified, which makes these agents more flexible. They usually require search and planning. The goal-based agent’s behavior can easily be changed. 

UTILITY BASED AGENTS:

• The agents which are developed having their end uses as building blocks are called utility-based agents. When there are multiple possible alternatives, then to decide which one is best, utility-based agents are used.
• They choose actions based on a preference (utility) for each state. Sometimes achieving the desired goal is not enough. We may look for a quicker, safer, cheaper trip to reach a destination. Agent happiness should be taken into consideration.

• Utility describes how “happy” the agent is. Because of the uncertainty in the world, a utility agent chooses the action that maximizes the expected utility. A utility function maps a state onto a real number which describes the associated degree of happiness. 

MULTI AGENT SYSTEMS:

• These agents interact with other agents to achieve a common goal. They may have to coordinate their actions and communicate with each other to achieve their objective.

• A multi-agent system (MAS) is a system composed of multiple interacting agents that are designed to work together to achieve a common goal. These agents may be autonomous or semi-autonomous and are capable of perceiving their environment, making decisions, and taking action to achieve the common objective.

• MAS can be used in a variety of applications, including transportation systems, robotics, and social networks. They can help improve efficiency, reduce costs, and increase flexibility in complex systems.

• MAS can be classified into different types based on their characteristics, such as whether the agents have the same or different goals, whether the agents are cooperative or competitive, and whether the agents are homogeneous or heterogeneous.

  • In a homogeneous MAS, all the agents have the same capabilities, goals, and behaviors. 
  • In contrast, in a heterogeneous MAS, the agents have different capabilities, goals, and behaviors. 

HIERARCHICAL AGENTS:

• These agents are organized into a hierarchy, with high-level agents overseeing the behavior of lower-level agents. The high-level agents provide goals and constraints, while the low-level agents carry out specific tasks. 
• Hierarchical agents can be implemented in a variety of applications, including robotics, manufacturing, and transportation systems. They are particularly useful in environments where there are many tasks and sub-tasks that need to be coordinated and prioritized.
• In a hierarchical agent system, the high-level agents are responsible for setting goals and constraints for the lower-level agents. These goals and constraints are typically based on the overall objective of the system. For example, in a manufacturing system, the high-level agents might set production targets for the lower-level agents based on customer demand.
• One advantage of hierarchical agents is that they allow for more efficient use of resources. By organizing agents into a hierarchy, it is possible to allocate tasks to the agents that are best suited to carry them out, while avoiding duplication of effort. This can lead to faster, more efficient decision-making and better overall performance of the system.

SEARCH ALGORITHMS IN AI

• Artificial Intelligence is the study of building agents that act rationally. Most of the time, these agents perform some kind of search algorithm in the background in order to achieve their tasks. 
• A search problem consists of: 
  
  • A State Space. Set of all possible states where you can be.
  • A Start State. The state from where the search begins.
  • A Goal State. A function that looks at the current state returns whether or not it is the goal state.
• The Solution to a search problem is a sequence of actions, called the plan that transforms the start state to the goal state.

TYPES OF SEARCH ALGORITHM:

• There are far too many powerful search algorithms out there to fit in a single article. Instead, this article will discuss six of the fundamental search algorithms, divided into two categories, as shown below. 

UNINFORMED SEARCH

• The search algorithms in this section have no additional information on the goal node other than the one provided in the problem definition. The plans to reach the goal state from the start state differ only by the order and/or length of actions. Uninformed search is also called Blind search. These algorithms can only generate the successors and differentiate between the goal state and non goal state. 

• The following uninformed search algorithms are discussed:

  1. Depth First Search
  2. Breadth First Search
  3. Uniform Cost Search

• Each of these algorithms will have: 

  • A problem graph, containing the start node S and the goal node G.
  • A strategy, describing the manner in which the graph will be traversed to get to G.
  • A fringe, which is a data structure used to store all the possible states (nodes) that you can go from the current states.
  • A tree, that results while traversing to the goal node.
  • A solution plan, which the sequence of nodes from S to G.

DEPTH FIRST SEARCH:

• Depth-first search (DFS) is an algorithm for traversing or searching tree or graph data structures. The algorithm starts at the root node (selecting some arbitrary node as the root node in the case of a graph) and explores as far as possible along each branch before backtracking. It uses last in- first-out strategy and hence it is implemented using a stack.
• DFS requires very less memory as it only needs to store a stack of the nodes on the path from root node to the current node.
• It takes less time to reach to the goal node than BFS algorithm (if it traverses in the right path).

BREADTH FIRST SEARCH:

• Breadth-first search (BFS) is an algorithm for traversing or searching tree or graph data structures. It starts at the tree root (or some arbitrary node of a graph, sometimes referred to as a ‘search key’), and explores all of the neighbor nodes at the present depth prior to moving on to the nodes at the next depth level. It is implemented using a queue.
• BFS will provide a solution if any solution exists. If there are more than one solutions for a given problem, then BFS will
  provide the minimal solution which requires the least number of steps.

UNIFORM COST SEARCH:

• Uniform Cost Search (UCS) is different from BFS and DFS because here the costs come into play. In other words, traversing via different edges might not have the same cost. The goal is to find a path where the cumulative sum of costs is the least. 
• The primary goal of the uniform-cost search is to find a path to the goal node which has the lowest cumulative cost. Uniform-cost search expands nodes according to their path costs form the root node. It can be used to solve any graph/tree where the optimal cost is in demand.
• A uniform-cost search algorithm is implemented by the priority queue. It gives maximum priority to the lowest cumulative cost. Uniform cost search is equivalent to BFS algorithm if the path cost of all edges is the same.

INFORMED SEARCH ALGORITHM

• In this type, algorithms have information on the goal state, which helps in more efficient searching. This information is obtained by something called a heuristic. 
• In an informed search, a Search Heuristic is a function that estimates how close a state is to the goal state. For example – Manhattan distance, Euclidean distance, etc. (Lesser the distance, closer the goal.)
•  It takes the current state of the agent as its input and produces the estimation of how close agent is from the goal.
•  Heuristic function estimates how close a state is to the goal. It is represented by h(n), and it calculates the cost of an optimal path between the pair of states. The value of the heuristic function is always positive.

GREEDY SEARCH:

• Greedy best-first search algorithm always selects the path which appears best at that moment. It is the combination of depth-first search and breadth-first search algorithms. It uses the heuristic function and search.
• In greedy search, we expand the node closest to the goal node. The “closeness” is estimated by a heuristic h(x).
• A heuristic h is defined as- 
  h(x) = Estimate of distance of node x from the goal node. 
  Lower the value of h(x), closer is the node from the goal. 
• Expand the node closest to the goal state, i.e. expand the node with a lower h value. 

A* TREE SEARCH:

• A* Tree Search, or simply known as A* Search, combines the strengths of uniform-cost search and greedy search. In this search, the heuristic is the summation of the cost in UCS, denoted by g(x), and the cost in the greedy search, denoted by h(x). The summed cost is denoted by f(x).

• The following points should be noted wrt heuristics in A* search. 

  • Here, h(x) is called the forward cost and is an estimate of the distance of the current node from the goal node.
  • And, g(x) is called the backward cost and is the cumulative cost of a node from the root node.
  • A* search is optimal only when for all nodes, the forward cost for a node h(x) underestimates the actual cost h*(x) to reach the goal. This property of A* heuristic is called admissibility.

GRAPH SEARCH:

• A* tree search works well, except that it takes time re-exploring the branches it has already explored. In other words, if the same node has expanded twice in different branches of the search tree, A* search might explore both of those branches, thus wasting time.
• A* Graph Search, or simply Graph Search, removes this limitation by adding this rule: do not expand the same node more than once. 
• Graph search is optimal only when the forward cost between two successive nodes A and B, given by h(A) – h (B), is less than or equal to the backward cost between those two nodes g(A -> B). This property of the graph search heuristic is called consistency. 

HILL CLIMBING ALGORITHM  IN AI

• Hill climbing is a widely used optimization algorithm in Artificial Intelligence (AI) that helps find the best possible solution to a given problem. As part of the local search algorithms family, it is often applied to optimization problems where the goal is to identify the optimal solution from a set of potential candidates.
• Hill Climbing is a heuristic search algorithm used primarily for mathematical optimization problems in artificial intelligence (AI). It is a form of local search, which means it focuses on finding the optimal solution by making incremental changes to an existing solution and then evaluating whether the new solution is better than the current one.
• ill climbing is a fundamental concept in AI because of its simplicity, efficiency, and effectiveness in certain scenarios, especially when dealing with optimization problems or finding solutions in large search spaces.
• In the Hill Climbing algorithm, the process begins with an initial solution, which is then iteratively improved by making small, incremental changes. These changes are evaluated by a heuristic function to determine the quality of the solution. The algorithm continues to make these adjustments until it reaches a local maximum—a point where no further improvement can be made with the current set of moves.

• Hill climbing follows these steps:

  1. Initial State: Start with an arbitrary or random solution (initial state).
  2. Neighboring States: Identify neighboring states of the current solution by making small adjustments (mutations or tweaks).
  3. Move to Neighbor: If one of the neighboring states offers a better solution (according to some evaluation function), move to this new state.
  4. Termination: Repeat this process until no neighboring state is better than the current one. At this point, you’ve reached a local maximum or minimum (depending on whether you’re maximizing or minimizing).

TYPES OF HILL CLIMBING:

1. SIMPLE HILL CLIMBING:

• Simple Hill Climbing is a straightforward variant of hill climbing where the algorithm evaluates each neighboring node one by one and selects the first node that offers an improvement over the current one.

   2. STEEPEST-ASCENT HILL CLIMBING:

• Steepest-Ascent Hill Climbing is an enhanced version of simple hill climbing. Instead of moving to the first neighboring node that improves the state, it evaluates all neighbors and moves to the one offering the highest improvement (steepest ascent).

   3. STOCHASTIC HILL CLIMBING:

• Stochastic Hill Climbing introduces randomness into the search process. Instead of evaluating all neighbors or selecting the first improvement, it selects a random neighboring node and decides whether to move based on its improvement over the current state.

STATE-SPACE GRAPH IN HILL CLIMBING:

• In the Hill Climbing algorithm, the state-space diagram is a visual representation of all possible states the search algorithm can reach, plotted against the values of the objective function (the function we aim to maximize).

• In the state-space diagram:

  • X-axis: Represents the state space, which includes all the possible states or configurations that the algorithm can reach.
  • Y-axis: Represents the values of the objective function corresponding to each state.
• The optimal solution in the state-space diagram is represented by the state where the objective function reaches its maximum value, also known as the global maximum.

• Key Regions in the State-Space Diagram:

  1. Local Maximum: A local maximum is a state better than its neighbors but not the best overall. While its objective function value is higher than nearby states, a global maximum may still exist.
  2. Global Maximum: The global maximum is the best state in the state-space diagram, where the objective function achieves its highest value. This is the optimal solution the algorithm seeks.
  3. Plateau/Flat Local Maximum: A plateau is a flat region where neighboring states have the same objective function value, making it difficult for the algorithm to decide on the best direction to move.
  4. Ridge: A ridge is a higher region with a slope, which can look like a peak. This may cause the algorithm to stop prematurely, missing better solutions nearby.
  5. Current State: The current state refers to the algorithm’s position in the state-space diagram during its search for the optimal solution.
  6. Shoulder: A shoulder is a plateau with an uphill edge, allowing the algorithm to move toward better solutions if it continues searching beyond the plateau.