Our paper on system identification with deep neural networks in monkey V1 has finally been published in PLoS Computational Biology. In the paper we show that multi-layer convolutional neural networks outperform other existing predictive models of V1 at predicting spiking responses to natural images. As usual, data and code are available.
Recently, two approaches based on deep learning have emerged for modeling nonlinear computations in the visual system: transfer learning from artificial neural networks trained on object recognition and data-driven convolutional neural network models trained end-to-end on large populations of neurons. We tested both approaches in V1 of awake monkeys and found that the transfer learning approach performed similarly well to the data-driven approach. Both outperformed classical linear-nonlinear and wavelet-based feature representations that build on existing theories of V1.
Notably, transfer learning using a pre-trained feature space required substantially less experimental time to achieve the same performance, suggesting that the computations of V1 can be reasonably well explained by high-level functional goals such as object recognition.