Machines are rapidly gaining the ability to perceive, interpret and interact with the visual world in ways that were once ...

Four of the 25 most-cited scientific papers of the 21st century were authored or co-authored by University of Toronto ...

Four of the 25 most-cited scientific papers of the 21st century were authored or co-authored by University of Toronto ...

ABSTRACT: Convolutional auto-encoders have shown their remarkable performance in stacking deep convolutional neural networks for classifying image data during the past several years. However, they are ...

Evolutionary paradigms have been successfully applied to neural network designs for two decades. Unfortunately, these methods cannot scale well to the modern deep neural networks due to the ...

Previously, researchers doubted that neural networks could solve complex visual tasks without hand-designed systems. However, this work demonstrated that with sufficient data and computational ...

Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017) Imagenet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90.

Deep learning shows promising results in extracting useful information from medical images. The proposed work applies a Convolutional Neural Network (CNN) on retinal images to extract features that ...

Shallow convolutional neural networks (CNNs) have successfully been used to classify polarimetric synthetic aperture radar (PolSAR) imagery. However, one drawback of the existing deep CNN-based ...