Technical Program

Paper Detail

Paper: PS-1A.65
Session: Poster Session 1A
Location: H Lichthof
Session Time: Saturday, September 14, 16:30 - 19:30
Presentation Time:Saturday, September 14, 16:30 - 19:30
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Adversarial Training of Neural Encoding Models on Population Spike Trains
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Authors: Poornima Ramesh, Mohamad Atayi, Jakob H Macke, Technical University of Munich, Germany
Abstract: Neural population responses to sensory stimuli can exhibit both nonlinear stimulus-dependence and richly structured shared variability. Here, we show how adversarial training can be used to optimize neural encoding models to capture both the deterministic and stochastic components of neural population data. To account for the discrete nature of neural spike trains, we use the REBAR method to estimate unbiased gradients for adversarial optimization of neural encoding models. We illustrate our approach on population recordings from primary visual cortex. We show that adding latent noise-sources to a convolutional neural network yields a model which captures both the stimulus-dependence and noise correlations of the population activity.