A concise overview of machine learning--computer programs that learn from data--the basis of such applications as voice recognition and driverless cars.
Today, machine learning underlies a range of applications we use every day, from product recommendations to voice recognition--as well as some we don't yet use everyday, including driverless cars. It is the basis for a new approach to artificial intelligence that aims to program computers to use example data or past experience to solve a given problem. In this volume in the MIT Press Essential Knowledge series, Ethem Alpaydin offers a concise and accessible overview of "the new AI." This expanded edition offers new material on such challenges facing machine learning as privacy, security, accountability, and bias.
Alpaydin, author of a popular textbook on machine learning, explains that as "Big Data" has gotten bigger, the theory of machine learning--the foundation of efforts to process that data into knowledge--has also advanced. He describes the evolution of the field, explains important learning algorithms, and presents example applications. He discusses the use of machine learning algorithms for pattern recognition; artificial neural networks inspired by the human brain; algorithms that learn associations between instances; and reinforcement learning, when an autonomous agent learns to take actions to maximize reward. In a new chapter, he considers transparency, explainability, and fairness, and the ethical and legal implications of making decisions based on data.
Author(s): Ethem Alpaydin
Edition: Revised, Updated
Publisher: The MIT Press
Year: 2021
Language: English
Pages: 280
Contents
Series Foreword
Preface
1: Why We Are Interested in Machine Learning
The Power of the Digital
Computers Store Data
Computers Exchange Data
Mobile Computing
Social Data
All That Data: The Dataquake
Learning versus Programming
Artificial Intelligence
Understanding the Brain
Pattern Recognition
What We Talk about When We Talk about Learning
History
2: Machine Learning, Statistics, and Data Analytics
Learning to Estimate the Price of a Used Car
Randomness and Probability
Learning a General Model
Model Selection
Supervised Learning
Learning a Sequence
Credit Scoring
Expert Systems
Expected Values
3: Pattern Recognition
Learning to Read
Matching Model Granularity
Generative Models
Face Recognition
Speech Recognition
Natural Language Processing and Translation
Combining Multiple Models
Outlier Detection
Dimensionality Reduction
Decision Trees
Active Learning
Learning to Rank
Bayesian Methods
4: Neural Networks and Deep Learning
Artificial Neural Networks
Neural Network Learning Algorithms
What a Perceptron Can and Cannot Do
Recurrent Networks for Learning Time
Connectionist Models in Cognitive Science
Neural Networks as a Paradigm for Parallel Processing
Hierarchical Representations in Multiple Layers
Deep Learning
Learning Hidden Representations
End-to-End Learning
Generative Adversarial Networks
5: Learning Clusters and Recommendations
Finding Groups in Data
Recommendation Systems
6: Learning to Take Action
Reinforcement Learning
K-Armed Bandit
Temporal Difference Learning
Learning to Play Games
Reinforcement Learning in Real Life
7: Challenges and Risks
The Other Side of Machine Learning
Data Privacy and Security
Biased Data
Model Interpretability
Ethical, Legal, and Other Social Aspects
8: Where Do We Go from Here?
Make Them Smart, Make Them Learn
High-Performance Computation
How Green Is My AI?
Data Mining
Data Science
Machine Learning, Artificial Intelligence, and the Future
Closing Remarks
Glossary
Notes
Preface
Chapter 1
Chapter 2
Chapter 3
Chapter 4
Chapter 7
Chapter 8
References
Further Reading
Index
