wednesday, 24 may 2017—12:15
Deep learning models of perception and cognition
Marc Zorzi, University of Padova, Italy
Deep learning in stochastic recurrent neural networks with many layers of neurons (“deep networks”) is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex representations of the sensory data through unsupervised learning. Using examples from research in my laboratory, spanning diverse domains such as numerosity perception, written language processing and space coding, I will show that deep learning models represent a major step forward for connectionist modeling in psychology and cognitive neuroscience.