Many applications of deep learning use feedforward neural network architectures (Fig. 1), which learn to map a fixed-size input (for example, an image) to a fixed-size output (for example, a ...

Researchers have created a deep-learning algorithm that can, given a still image from a scene, create a short video that simulates the most likely future of that scene.

Deep learning, a subset of machine learning represents the next stage of development for AI. By using artificial neural networks that act very much like a human brain, machines can take data in ...

The Dice loss function is widely used to train deep learning algorithms in medical segmentation tasks. However, in multi-class segmentation tasks, the Dice loss function can result in imbalanced ...

The University of Toronto is creating three new tenure-stream faculty positions in deep learning, a sub-discipline of artificial intelligence (AI), in recognition of University Professor Emeritus ...

It is just the beginning for deep learning: We managed to make computers see as a three-year-old child, but, as Li said in a TED talk, “the real challenge is ahead: How can we help our computer ...