AI Lecture 4 - Branches of AI PDF

ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL ARTIFICIAL INTELLIGENCE (AI) INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) Lecture 4 - Branches of Artificial Intelligence (AI) Dr. Sarah M. Ayyad ARTIFICIAL INTELLIGENCE (AI) October 2024  Majo...

ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL ARTIFICIAL INTELLIGENCE (AI) INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) Lecture 4 - Branches of Artificial Intelligence (AI) Dr. Sarah M. Ayyad ARTIFICIAL INTELLIGENCE (AI) October 2024  Major Branches of AI ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI)  01. Machine Learning It is the science of getting machines to interpret, process and analyze data in order to solve real-world problems. It describes how computer perform tasks on their own by previous experiences.  Traditional Programming Vs. Machine Learning ARTIFICIAL INTELLIGENCE (AI)  Types of Machine Learning ARTIFICIAL INTELLIGENCE (AI)  1- supervised learning ▪ A training set of examples with the correct responses (targets) is provided and, based on this training set, the algorithm generalizes to respond correctly to all possible inputs. ▪ Important notes Data: labeled instances , e.g., emails marked spam/not spam ❑ Training Set ❑ Testing Set Features: attribute-value pairs which characterize each x  There are two groups of problems of supervised learning Classification uses an algorithm to accurately Classification assign test data into specific categories. - Regression is a process of finding the correlations between dependent and independent variables. - It helps in predicting the continuous variables Regression such as prediction of Market Trends, prediction of ARTIFICIAL INTELLIGENCE (AI) House prices, etc.  2- Unsupervised learning - Unsupervised machine learning is the process of inferring underlying hidden patterns from historical data. - In real-world, we do not always have input data with the corresponding output so to solve such cases, we need unsupervised learning. - The main applications of unsupervised learning include clustering, visualization, and dimensionality reduction.  2- Unsupervised learning:Clustering - Clustering is the process of grouping the given data into different clusters or groups. - Elements in a group or cluster should be as similar as possible, and points in different groups should be as dissimilar as possible.  3- Reinforcement Learning ▪ It is a subfield of artificial intelligence that focuses on enabling machines to learn by interacting with an environment to achieve specific goals. ▪ Unlike traditional supervised and unsupervised learning, where models are trained on static datasets, RL agents learn from experience through a continuous process of trial and error.  Real Time Examples for ML ▪ Email Spam Filtering ▪ Digit Recognition ▪ Image-Based Disease Diagnosis ▪ Online Fraud Detection ▪ Predicting customer ad clicks ▪ Weather Forcasting ▪ Sports analysis: determine a team's or player's performance in a game.  /(AI) 02. Neural Networks Neural networks, also known as artificial neural networks (ANNs). A subset of machine learning and are at the heart of deep learning algorithms. Their name and structure are inspired by the human brain, mimicking the way that biological neurons signal to one another.  Neural NEtworks Artificial neural networks (ANNs) are comprised of a node layers, containing an input layer, one or more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and has an associated weight. A neural network that consists of more than three layers—which would be inclusive of the inputs and the output—can be considered a deep learning algorithm. It is typically hundreds or thousands of layers. Machine Learning Vs. Deep Learning Machine Learning Vs. Deep Learning  /(AI) 03. Robotics A physically-embodied, artificially intelligent device with sensing and actuation. It can sense. It can act.  Robotics ARTIFICIAL INTELLIGENCE (AI) ▪ The most widely and successfully used robots up until now are industrial robot ‘arms’, mounted on fixed bases and used for instance in manufacturing. ▪ Robotics integrates science and engineering, and overlaps with many disciplines: artificial intelligence, computer vision, machine learning, electronic, mechanical engineering ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) /(AI) Natural Language 04. Processing (NLP) It is a branch of AI that enables computers to comprehend, generate, and manipulate human language.  NLP is an interdisciplinary subfield of computer science, AI, and linguistics. It is concerned with giving computers the ability to understand ARTIFICIAL text and spoken words (voice) in much the same way human beings can. NLP is the core technology behind virtual assistants, such as the INTELLIGENCE Siri, Cortana, or Alexa. The best-known natural language processing tool is GPT-3, from OpenAI. Nine months since the launch of our first commercial product, the (AI) OpenAI API, more than 300 applications are now using GPT-3.  05. Fuzzy logic Fuzzy logic is a type of reasoning used in AI systems that mimics human thinking by allowing for intermediate degrees of truth between strictly binary cases of true or false.  Fuzzy Logic In the real world, sometimes we face a condition where it is difficult to recognize whether the condition is true or not, their fuzzy logic gives relevant flexibility for reasoning that leads to inaccuracies and uncertainties of any condition. ARTIFICIAL INTELLIGENCE (AI)  Fuzzy Logic It is simply the generalization of the standard logic where a concept exhibits a degree of truth between 0.0 to 1.0. If the concept is completely true, standard logic is 1.0 and 0.0 for the completely false concept ARTIFICIAL INTELLIGENCE (AI) /(AI) 06. Expert System An expert system is a computer system emulating the decision-making ability of a human expert  Expert Systems ▪ Expert systems are designed to solve problems in a specific field or industry. ARTIFICIAL ▪ They work by using a knowledge base, which is a collection of information and rules about the subject, and an inference engine, which is a program that uses the knowledge base to make decisions or solve problems. The and get answers to their questions. INTELLIGEN user interface is the part of the system that allows people to interact with it ▪ One popular example of an AI expert system that business people would CE (AI) recognize is IBM Watson. Watson is an AI-powered expert system that is designed to help businesses make better decisions by analyzing large amounts of data. It has been used in a variety of industries. Expert System ARTI CIAL INTE IGEN  ARTI THANKS CIAL Do you have any questions? [email protected] INTE CREDITS: This presentation template was created by Slidesgo Flaticon Slidesgo, including icons by Flaticon and infographics & images by Freepik Freepik IGEN