What is Machine Learning Introduction Well-Posed Learning Problems Designing a Learning System Steps for Designing Learning System Are Perspectives and Issues in Machine Learning Concept Learning and the General to Specific Ordering Concept Learning Task Concept Learning as a Search Important Representation Inductive Bias

Decision Tree Learning Types of Decision Tree Strengths and Weakness of Decision Tree Approach Appropriate Problems in Decision Tree Learning Issues in Decision Tree Learning What is Hypothesis Types of Hypothesis ID3 Information Gain for Each Feature

Artificial Neural Networks I Biological Motivation Neural Network Representations Appropriate Problems for Neural Network Learning Perceptron Genetic Algorithms Application Areas What is Reinforcement Learning Terms Used in Reinforcement Learning Approaches to Implement Reinforcement Learning Temporal Difference Learning EM Algorithm GIBS Algorithm

Previous Page

Next Page

Neural Network Representations

A prototypical example of ANN learning is provided by system ALVINN.
It uses a learned ANN to steer an autonomous vehicle driving at normal speeds on public highways.
The input to the neural network is a 30 x 32 grid of pixel intensities obtained from a forward-pointed camera mounted on the vehicle.
The network output is the direction in which the vehicle is steered.
The ANN is trained to mimic the observed steering commands of a human driving the vehicle for approximately 5 minutes.
ALVINN has used its learned networks to successfully drive at speeds up to 70 miles per hour and for distances of 90 miles on public highways (driving in the left lane of a divided public highway, with other vehicles present).

The network structure of ALVINN is typical of many ANNs.
Here the individual units are interconnected in layers that form a directed acyclic graph.
In general, ANNs can be graphs with many types of structures-acyclic or cyclic, directed or undirected.
This chapter will focus on the most common and practical ANN approaches, which are based on the BACKPROPAGATION algorithm.
The BACKPROPAGATION algorithm assumes the network is a fixed structure that corresponds to a directed graph, possibly containing cycles.
Learning corresponds to choosing a weight value for each edge in the graph.
Although certain types of cycles are allowed, the vast majority of practical applications involve acyclic feed-forward networks, similar to the network structure used by ALVINN.

Previous Page

Next Page