An unsupervised trained neural network model to predict visual cortex measurements
Understanding how the visual cortex of the human brain really works is still an open problem for science today. A better understanding of natural intelligence could also benefit object-recognition algorithms based on convolutional neural networks. In this talk we demonstrate the asset of using a residual neural network of only 20 layers for this task. This will be compared with the approaches applied by the most successful competitors of this challenge.
Arnoud Visser’s research focuses on perception and cooperation inside robot teams. With perception one can build a joint world model which could be the basis of shared decision making. Arnoud Visser was the founder of the Intelligent Robotics Lab, a place where robotics research in Amsterdam is conducted and shared.