We present a measure of representation in neural networks that we call ‘R’, which is based on information theory. We show how R relates to an analysis of distributed representation, viz. a principal components analysis of activation space. Finally, we argue that R is well suited to measure representation in neural networks.6 page(s
Neuronal population codes are increasingly being investigated with multivariate pattern-information ...
In this work we study the distributed representations learnt by generative neural network models. In...
The ability to make distinctions is one of the fundamental capacities underlying cognition, from per...
This report is a survey of information representations in both biological and artificial neural netw...
This report is a survey of information representations in both biological and artificial neural netw...
Connectionist representations are mappings between elements in the problem domain and vectors of act...
A growing toolbox is emerging for linking neuroimaging data to computations supporting human cogniti...
Representational models specify how activity patterns in populations of neurons (or, more generally,...
This chapter discusses the role of information theory for analysis of neural networks using differen...
The word representation (as in "neural representation"), and many of its related terms, such as to r...
Representation learning algorithms offer the opportunity to learn invariant representations of the i...
Finding useful representations of data in order to facilitate scientific knowledge generation is a u...
<div><p>Neuronal population codes are increasingly being investigated with multivariate pattern-info...
Any act of information processing can be decomposed into the component operations of transfer, stora...
Abstract. Information theory provides a powerful framework to analyse how neurons represent sensory ...
Neuronal population codes are increasingly being investigated with multivariate pattern-information ...
In this work we study the distributed representations learnt by generative neural network models. In...
The ability to make distinctions is one of the fundamental capacities underlying cognition, from per...
This report is a survey of information representations in both biological and artificial neural netw...
This report is a survey of information representations in both biological and artificial neural netw...
Connectionist representations are mappings between elements in the problem domain and vectors of act...
A growing toolbox is emerging for linking neuroimaging data to computations supporting human cogniti...
Representational models specify how activity patterns in populations of neurons (or, more generally,...
This chapter discusses the role of information theory for analysis of neural networks using differen...
The word representation (as in "neural representation"), and many of its related terms, such as to r...
Representation learning algorithms offer the opportunity to learn invariant representations of the i...
Finding useful representations of data in order to facilitate scientific knowledge generation is a u...
<div><p>Neuronal population codes are increasingly being investigated with multivariate pattern-info...
Any act of information processing can be decomposed into the component operations of transfer, stora...
Abstract. Information theory provides a powerful framework to analyse how neurons represent sensory ...
Neuronal population codes are increasingly being investigated with multivariate pattern-information ...
In this work we study the distributed representations learnt by generative neural network models. In...
The ability to make distinctions is one of the fundamental capacities underlying cognition, from per...
DOI
Add to ORKG