no code implementations • NeurIPS 2021 • Shahab Bakhtiari, Patrick Mineault, Timothy Lillicrap, Christopher Pack, Blake Richards
We show that when we train a deep neural network architecture with two parallel pathways using a self-supervised predictive loss function, we can outperform other models in fitting mouse visual cortex.
no code implementations • NeurIPS 2021 • Patrick Mineault, Shahab Bakhtiari, Blake Richards, Christopher Pack
To test this hypothesis, we trained a 3D ResNet to predict an agent's self-motion parameters from visual stimuli in a simulated environment.
no code implementations • 1 Jan 2021 • Luke Yuri Prince, Shahab Bakhtiari, Colleen J Gillon, Blake Aaron Richards
As such, the success of dynamic latent variable modelling in calcium imaging data rests on being able to disentangle the contribution of these two sources of variation.