ib-gp model
283f1354f1de1c53a14afe0a6740e889-Paper-Conference.pdf
Intheearly visual system, high dimensional natural stimuli areencoded into the trains of neuronal spikes that transmit the information to the brain to produce perception. However, is all the visual scene information required to explain the neuronal responses?
Natural image synthesis for the retina with variational information bottleneck representation
In the early visual system, high dimensional natural stimuli are encoded into the trains of neuronal spikes that transmit the information to the brain to produce perception. However, is all the visual scene information required to explain the neuronal responses? In this work, we search for answers to this question by developing a joint model of the natural visual input and neuronal responses using the Information Bottleneck (IB) framework that can represent features of the input data into a few latent variables that play a role in the prediction of the outputs. The correlations between data samples acquired from published experiments on ex-vivo retinas are accounted for in the model by a Gaussian Process (GP) prior. The proposed IB-GP model performs competitively to the state-of-the-art feedforward convolutional networks in predicting spike responses to natural stimuli.
Natural image synthesis for the retina with variational information bottleneck representation
However, is all the visual scene information required to explain the neuronal responses?
- Information Technology > Artificial Intelligence > Vision (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Data Science (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Natural image synthesis for the retina with variational information bottleneck representation
In the early visual system, high dimensional natural stimuli are encoded into the trains of neuronal spikes that transmit the information to the brain to produce perception. However, is all the visual scene information required to explain the neuronal responses? In this work, we search for answers to this question by developing a joint model of the natural visual input and neuronal responses using the Information Bottleneck (IB) framework that can represent features of the input data into a few latent variables that play a role in the prediction of the outputs. The correlations between data samples acquired from published experiments on ex-vivo retinas are accounted for in the model by a Gaussian Process (GP) prior. The proposed IB-GP model performs competitively to the state-of-the-art feedforward convolutional networks in predicting spike responses to natural stimuli.