Content and cluster analysis: assessing representational similarity in neural systems

Authors: Laakso A.; Cottrell G.

Source: Philosophical Psychology, Volume 13, Number 1, 1 March 2000 , pp. 47-76(30)

Publisher: Routledge, part of the Taylor & Francis Group

Key:
Free Content - Free Content
New Content - New Content
Subscribed Content - Subscribed Content
Free Trial Content - Free Trial Content

Abstract:

If connectionism is to be an adequate theory of mind, we must have a theory of representation for neural networks that allows for individual differences in weighting and architecture while preserving sameness, or at least similarity, of content. In this paper we propose a procedure for measuring sameness of content of neural representations. We argue that the correct way to compare neural representations is through analysis of the distances between neural activations, and we present a method for doing so. We then use the technique to demonstrate empirically that different artificial neural networks trained by backpropagation on the same categorization task, even with different representational encodings of the input patterns and different numbers of hidden units, reach states in which representations at the hidden units are similar. We discuss how this work provides a rebuttal to Fodor and Lepore’s critique of Paul Churchland’s state space semantics.

Language: English

Document Type: Research article

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$29.87 plus tax

 

OR

Back to top

Key:
Free Content - Free Content
New Content - New Content
Subscribed Content - Subscribed Content
Free Trial Content - Free Trial Content
Page Help Click here for Page Help
Shopping cart
Tools
Sign in






Need to register?
Sign up here
Text size: A | A | A | A