Wilma Bainbridge Tencia Lee Kendra Leigh Machine Learning Wilma Bainbridge Tencia Lee Kendra Leigh

What is Machine Learning? Machine learning is the process in which a machine changes its structure, program, or data in response to external information in such a way that its expected future performance improves. Learning by machines can overlap with simpler processes, such as the addition of records to a database, but other cases are clear examples of what is called “learning,” such as a speech recognition program improving after hearing samples of a person’s speech.

Components of a Learning Agent Curiosity Element – problem generator; knows what the agent wants to achieve, takes risks (makes problems) to learn from Learning Element – changes the future actions (the performance element) in accordance with the results from the performance analyzer Performance Element – choosing actions based on percepts Performance Analyzer – judges the effectiveness of the action, passes info to the learning element

Why is machine learning important? Or, why not just program a computer to know everything it needs to know already? Many programs or computer-controlled robots must be prepared to deal with things that the creator would not know about, such as game-playing programs, speech programs, electronic “learning” pets, and robotic explorers. Here, they would have access to a range of unpredictable knowledge and thus would benefit from being able to draw conclusions independently.

Relevance to AI Helps programs handle new situations based on the input and output from old ones Programs designed to adapt to humans will learn how to better interact Could potentially save bulky programming and attempts to make a program “foolproof” Makes nearly all programs more dynamic and more powerful while improving the efficiency of programming.

Approaches to Machine Learning Boolean logic and resolution Evolutionary machine learning – many algorithms / neural networks are generated to solve a problem, the best ones survive Statistical learning Unsupervised learning – algorithm that models outputs from the input, knows nothing about the expected results Supervised learning – algorithm that models outputs from the input and expected output Reinforcement learning – algorithm that models outputs from observations

Current Machine Learning Research Almost all types of AI are developing machine learning, since it makes programs dynamic. Examples: Facial recognition – machines learn through many trials what objects are and aren’t faces Language processing – machines learn the rules of English through example; some AI chatterbots start with little linguistic knowledge but can be taught almost any language through extensive conversation with humans

Future of Machine Learning Gaming – opponents will be able to learn from the player’s strategies and adapt to combat them Personalized gadgets – devices that adapt to their owner as he changes (gets older, gets different tastes, changes his modes) Exploration – machines will be able to explore environments unsuitable for humans and quickly adapt to strange properties

Problems in Machine Learning Learning by Example: Noise in example classification Correct knowledge representation Heuristic Learning Incomplete knowledge base Continuous situations in which there is no absolute answer Case-based Reasoning Human knowledge to computer representation

Problems in Machine Learning Grammar – meaning pairs new rules must be relearned a number of times to gain “strength” Conceptual Clustering Definitions can be very complicated Not much predictive power

Successes in Research ARCH by P.H. Winston in which positive and negative examples are used to explain the concept D. B. Lenat’s pioneering work in heuristics with incomplete knowledge base: RLL language and EURISKO system LAS by Anderson (1977) & AMBER by Langley (1982) simulate aspects of grammar learning

Successes continued… Aspects of daily life using machine learning Optical character recognition Handwriting recognition Speech recognition Automated steering Assess credit card risk Filter news articles Refine information retrieval Data mining

Bibliography http://robotics.stanford.edu/people/nilsson/mlbook.html http://www.mlnet.org/ http://ai-depot.com/GameAI/Learning.html http://web.engr.oregonstate.edu/~tgd/experimental-research/ http://encyclopedia.thefreedictionary.com/machine%20learning Shapiro, Stuart C. and David Eckroth (ed.) “Machine Learning” Encyclopedia of Artificial Intelligence. New York: John Wiley & Sons. © 1987.

Any Questions?