Information loss in an optimal maximum likelihood decoding

Authors:
Inés Samengo
Affiliations:
Centro Atómico Bariloche, (8400) San Carlos de Bariloche, Río Negro, Argentina
Venue:
Neural Computation
Year:
2002

Citing 4
Cited 3

Elements of information theory

Elements of information theory
The upward bias in measures of information derived from limited data samples

Neural Computation
How well can we estimate the information carried in neuronal responses from limited samples?

Neural Computation
On decoding the responses of a population of neurons from short time windows

Neural Computation

A Subjective Distance Between Stimuli: Quantifying the Metric Structure of Representations

Neural Computation
Information theory in neuroscience

Journal of Computational Neuroscience
A finite-sample, distribution-free, probabilistic lower bound on mutual information

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The mutual information between a set of stimuli and the elicited neural responses is compared to the corresponding decoded information. The decoding procedure is presented as an artificial distortion of the joint probabilities between stimuli and responses. The information loss is quantified. Whenever the probabilities are only slightly distorted, the information loss is shown to be quadratic in the distortion.