Above is an adversarial example: the slightly perturbed image of the cat fools an InceptionV3 classifier into classifying it as "guacamole". Such "fooling images" are easy to synthesize using gradient ...

In the Big Data era, data is not only becoming bigger and bigger; it is also becoming more and more complex. This translates into a spectacular increase of the dimensionality of the data. For example, ...

Abstract: We propose a new method for domain adaptation that uses a gradient reversal layer (GRL) with instance weighting. Domain adaptation methods that use GRL have the latent problem of learning ...

Abstract: Training neural networks with backpropagation (BP) requires a sequential passing of activations and gradients. This has been recognized as the lockings (i.e., the forward, backward, and ...