Artificial Intelligence Lecture PDF
Document Details
Uploaded by CourteousTulsa
Nile University of Nigeria
2024
Emmanuel Ali(PhD)
Tags
Summary
This document is a lecture on artificial intelligence, covering the introduction, history, subfields, and ethics of AI. The lecture was delivered on October 7, 2024.
Full Transcript
Artificial Intelligence Emmanuel Ali(PhD) October 7, 2024 Emmanuel Ali(PhD) 1st Semester October 7, 2024 1 / 10 Outline 1 Introduction to AI 2 Search Algorithms 3 Evolutionary Algorithms 4 Knowledge representation and inf...
Artificial Intelligence Emmanuel Ali(PhD) October 7, 2024 Emmanuel Ali(PhD) 1st Semester October 7, 2024 1 / 10 Outline 1 Introduction to AI 2 Search Algorithms 3 Evolutionary Algorithms 4 Knowledge representation and inference 5 Machine Learning Fundamentals Emmanuel Ali(PhD) 1st Semester October 7, 2024 2 / 10 Introduction Artificial Intelligence is a concept that machines can achieve a living being intelligence, which enables them to handle complex and simple tasks. It involves creating algorithms and computer programs that enable machines to perform tasks that typically require human intelligence, such as problem-solving, learning, reasoning, understanding natural language, and recognizing patterns. AI systems aim to mimic human cognitive functions and improve their performance over time through learning and adaptation. Emmanuel Ali(PhD) 1st Semester October 7, 2024 3 / 10 History of artificial intelligence Period Key Events 1950 Alan Turing made the Turing test as a sign of intelligence. 1955 Allen Newell and Herbert A. Simon created the Logic Theorist. 1956 Artificial Intelligence is coined as a term at Dartmouth Conference organized by John McCarthy, Claude Shannon, Marvin Minsky, and Nathan Rochester. 1958 An early neural network, perceptron, was introduced by Frank Rosenblatt. 1966 ELIZA: The first chatbot was created by Joseph Weizenbaum. 1972 Prolog, a logic programming language, was created by Alain Colmerauer and Philippe Roussel. 1980 XCON, a type of expert system, was created by Carnegie Mellon University for the Digital Equipment Corporation. 1982 John Hopfield proved a neural network (called a Hopfield net) could learn and process information in a completely new way. Also, Geoffrey Hinton and David Rumelhart popularized a method for training neural networks called backprop- agation. 1989 Yann LeCun, Yoshua Bengio, and Patrick Haffner showed convolutional neural networks (CNNs) used to recognize handwritten characters. 1997 Deep Blue became the first computer chess-playing system to beat a reigning world chess champion, Garry Kasparov. Sepp Hochreiter and Jürgen Schmidhu- ber proposed the Long Short-Term Memory recurrent neural network. 2005 Stanford team won the DARPA Grand Challenge by driving autonomously for 131 miles along an unrehearsed desert trail. 2012 AlexNet won the ImageNet challenge, kickstarting the deep learning revolution in computer vision. 2017 ”Attention is All You Need” paper was published by Google, introducing the transformer model. AlphaGo was able to defeat Go champion, Ke Jie. 2019 Generative Pre-trained Transformer (GPT) language models began to generate coherent text. Table 1: Some key events in the history of artificial intelligence Emmanuel Ali(PhD) 1st Semester October 7, 2024 4 / 10 Subfields of artificial intelligence AI now consists many sub-fields, using a variety of techniques, such as: Cognitive science and brain understanding – e.g. brain modelling Evolutionary Computation – e.g. genetic algorithms, genetic programming Perception and Vision – e.g. object recognition, image understanding Robotics – e.g. intelligent control, autonomous exploration Expert Systems – e.g. decision support systems, teaching systems Speech Processing– e.g. speech recognition and production Natural Language Processing – e.g. machine translation Planning and decision making – e.g. scheduling, game playing Machine Learning – e.g. decision tree learning, version space learning, time series prediction, classification Emmanuel Ali(PhD) 1st Semester October 7, 2024 5 / 10 Ethics in AI Ethics are guiding principles to discern right and wrong. AI ethics is a field that studies on how to reduce risks and avoid adverse outcomes while getting the optimal outcome of its applications. Issues in AI ethics include: data responsibility and privacy, moral agency and value alignment, fairness, explainability, robustness, transparency, environmental sustainability, inclusion, accountability, trust, and technology misuse Emmanuel Ali(PhD) 1st Semester October 7, 2024 6 / 10 Frame Title Emmanuel Ali(PhD) 1st Semester October 7, 2024 7 / 10 Frame Title Emmanuel Ali(PhD) 1st Semester October 7, 2024 8 / 10 Frame Title Emmanuel Ali(PhD) 1st Semester October 7, 2024 9 / 10 Frame Title Emmanuel Ali(PhD) 1st Semester October 7, 2024 10 / 10