Skip to content

Paper overview | Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

The article presents the comparison of the complexity of the representation of visual features in the deep convolutional neural network and in our brain. DNN activity layer-by-layer is used to predict voxel activations and it is shown that lower layers of DNN are better at predicting V1,V2 and that higher layers of DNN are better in predicting activity in LO and higher areas of ventral stream. The result effectively demonstrates that layer-by-layer complexity of visual features we see in DNN is also present in the visual cortex.

Download PDF


I have worked on various projects in machine learning and computer science, neuroscience and brain-computer interfaces, reinforcement learning and robotics. Currently I am focusing on two things: leading machine learning team at OffWorld Inc. to train robots for space exploration, and continuing the research done as part of my PhD on neuroscience and artificial intelligence.

No comments yet.

Leave a Reply

Your email address will not be published.

Comments (0)