Loading...
Please wait, while we are loading the content...
Similar Documents
Hyperplanes and the acquisition of common sense reasoning (1993).
| Content Provider | CiteSeerX |
|---|---|
| Author | Bodén, Mikael Narayanan, Ajit |
| Abstract | The overall aim of the paper is to demonstrate that, from a machine learning point of view, connectionist networks are not black boxes. Trained networks contain rich and varied internal representations gleaned from training sets. Analysis of these representations can provide useful results concerning the generalizability of these networks to novel examples. More particularly in the case of common sense reasoning, hyperplane analysis can demonstrate the adaptive power of connectionist networks when presented with information concerning new entities and the ability of such networks to cope with exceptions to what has already been input in the training set. One important advantage of such analysis is that machine learning researchers need not be committed to any particular form of symbolic structure but can study the process of acquiring common sense reasoning as well as the impact of new information on existing internal representations purely from the viewpoint of learning. Another advan... |
| File Format | |
| Publisher Date | 1993-01-01 |
| Access Restriction | Open |
| Subject Keyword | Common Sense Common Sense Reasoning Connectionist Network Particular Form New Information Training Set Varied Internal Representation Symbolic Structure Black Box Useful Result Internal Representation Important Advantage Hyperplane Analysis New Entity Adaptive Power Overall Aim Novel Example |
| Content Type | Text |
