Deep neural networks (DNNs) are becoming increasingly popular as a model of the human visual system. However, they show behaviours that are uncharacteristic of humans …
C Ivan - CVPR Workshops, 2019 - openaccess.thecvf.com
Abstract Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally …
G Friedland, M Krell - arXiv preprint arXiv:1708.06019, 2017 - arxiv.org
We derive the calculation of two critical numbers predicting the behavior of perceptron networks. First, we derive the calculation of what we call the lossless memory (LM) …
NO Hodas, P Stinis - Frontiers in psychology, 2018 - frontiersin.org
As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A …
A wide variety of deep learning techniques from style transfer to multitask learning rely on training affine transformations of features. Most prominent among these is the popular …
H JANG, F TONG - Journal of Vision, 2018 - jov.arvojournals.org
Convolutional neural networks (CNNs) have attracted considerable attention for their remarkable performance at a variety of cognitive tasks, including visual object recognition …
For many initialization schemes, parameters of two randomly initialized deep neural networks (DNNs) can be quite different, but feature distributions of the hidden nodes are …
Standard training techniques for neural networks involve multiple sources of randomness, eg, initialization, mini-batch ordering and in some cases data augmentation. Given that …
Abstract Neural Networks (NNs) are increasingly used across scientific domains to extract knowledge from experimental or computational data. An NN is composed of natural or …