Journal ArticleDOI
Learning representations by back-propagating errors
Reads0
Chats0
TLDR
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.Abstract:
We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.read more
Citations
More filters
Journal ArticleDOI
Toward optimal fragment generations for ab initio protein structure assembly
Dong Xu,Yang Zhang +1 more
TL;DR: A gapless‐threading method to generate position‐specific structure fragments is developed and it is found that the optimal fragment length for structural assembly is around 10, and at least 100 fragments at each location are needed to achieve optimal structure assembly.
Journal ArticleDOI
Nonlinear prediction as a way of distinguishing chaos from random fractal sequences
TL;DR: In this article, the scaling properties of the prediction error as a function of time are used to distinguish between chaos and random fractal sequences, a particular class of coloured noise which represent stochastic (infinite-dimensional) systems with power-law spectra.
Proceedings ArticleDOI
DeepSim: deep learning code functional similarity
Gang Zhao,Jeff Huang +1 more
TL;DR: A novel approach is proposed that encodes code control flow and data flow into a semantic matrix in which each element is a high dimensional sparse binary feature vector, and a new deep learning model is designed that measures code functional similarity based on this representation.
Journal ArticleDOI
An empirical survey of data augmentation for time series classification with neural networks.
Brian Kenji Iwana,Seiichi Uchida +1 more
TL;DR: A taxonomy is proposed and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods, and their application to time series classification with neural networks.
Journal ArticleDOI
Deep Learning for Launching and Mitigating Wireless Jamming Attacks
TL;DR: An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented, where the transmitter systematically selects when to take wrong actions and adapts the level of defense to mislead the jammer into making prediction errors and consequently increase its throughput.