Book contents
- Frontmatter
- Contents
- Preface
- Dedication
- 1 Introduction
- 2 The Basic Attractor Neural Network
- 3 General Ideas Concerning Dynamics
- 4 Symmetric Neural Networks at Low Memory Loading
- 5 Storage and Retrieval of Temporal Sequences
- 6 Storage Capacity of ANN's
- 7 Robustness - Getting Closer to Biology
- 8 Memory Data Structures
- 9 Learning
- 10 Hardware Implementations of Neural Networks
- Glossary
- Index
- Frontmatter
- Contents
- Preface
- Dedication
- 1 Introduction
- 2 The Basic Attractor Neural Network
- 3 General Ideas Concerning Dynamics
- 4 Symmetric Neural Networks at Low Memory Loading
- 5 Storage and Retrieval of Temporal Sequences
- 6 Storage Capacity of ANN's
- 7 Robustness - Getting Closer to Biology
- 8 Memory Data Structures
- 9 Learning
- 10 Hardware Implementations of Neural Networks
- Glossary
- Index
Summary
The Context of Learning
General comments and a limited scope
It would have been wonderful if some distinguished thinker had written: ‘Thinking about learning is a real headache’ and we could have used this phrase as a quote. A glimpse at the type of difficulties that present themselves when a new experience should lead to learning is expressed by Minsky[1] as follows:
Which agents could be wise enough to guess what changes should then be made? The high level agents can't know such things; they scarcely know which lower-level processes exist. Nor can lower-level agents know which of their actions helped us to reach our high-level goals; they scarcely know that higher-level goals exist. The agencies that move our legs aren't concerned with whether we are walking toward home or toward work – nor do the agents involved with such destinations know anything of controlling individual muscle units…
[p.75]Hebb[2] adds that ‘the more we learn about the nature of learning, the farther we seem to get from being able to give firm answers.’
The scope is truly awesome and very soon it overlaps the deep controversy between innateness and behaviorism. There are several courses of action which avoid, at this stage, the full dimension of the issue:
To consider artificial devices which can serve as associative memories with increasingly complex performances and which are decreed by the designer, and to restrict the question of learning to that of training such machines to their final, known performing organization.
[…]
- Type
- Chapter
- Information
- Modeling Brain FunctionThe World of Attractor Neural Networks, pp. 428 - 460Publisher: Cambridge University PressPrint publication year: 1989
- 1
- Cited by