ImageNet Classification with Deep Convolutional Neural ...
The learning rates for each net-work were chosen independently to make train-ing as fast as possible. No regularization of any kind was employed. The magnitude of the ... Linear Units (ReLUs). Deep convolutional neural net-works with ReLUs train several times faster than their equivalents with tanh units. This is demonstrated in Figure 1, which ...
Download ImageNet Classification with Deep Convolutional Neural ...
Information
Domain:
Source:
Link to this page:
Documents from same domain
On Discriminative vs. Generative Classifiers: A …
papers.nips.ccOn Discriminative vs. Generative classifiers: A comparison of logistic regression and naive Bayes Andrew Y. Ng Computer Science Division University of California, Berkeley
SAGA: A Fast Incremental Gradient Method With Support for ...
papers.nips.ccSAGA is preferred over SVRG both theoretically and in practice. For neural networks, where no theory is available for either method, the storage of gradients is generally more expensive than the
Thinking Fast and Slow with Deep Learning and Tree Search
papers.nips.ccSystem 1 is a fast, unconscious and automatic mode of thought, also known as intuition or heuristic process. System 2, an evolutionarily recent process unique to humans, is a slow, conscious, explicit
A Growing Neural Gas Network Learns Topologies
papers.nips.ccA Growing Neural Gas Network Learns Topologies 627 a) Delaunay triangulation b) induced Delaunay triangulation Figure 1: Two ways of defining closeness among a set of points.
Attention is All you Need - Neural Information Processing ...
papers.nips.ccAttention Is All You Need Ashish Vaswani Google Brain avaswani@google.com Noam Shazeer Google Brain noam@google.com Niki Parmar Google Research nikip@google.com
Generative Adversarial Nets - NIPS
papers.nips.ccGenerative adversarial networks has been sometimes confused with the related concept of “adversar-ial examples” [28]. Adversarial examples are examples found by using gradient-based optimization directly on the input to a classification network, in order to find examples that are similar to the data yet misclassified.
Time-series Generative Adversarial Networks
papers.nips.ccA good generative model for time-series data should preserve temporal dynamics, in the sense that new sequences respect the original relationships between variables across time. Existing methods that bring generative adversarial networks (GANs) into the sequential setting do not adequately attend to the temporal correlations unique to time ...
Hidden Technical Debt in Machine Learning Systems
papers.nips.ccaccount for in system design. These include boundary erosion, entanglement, hidden feedback loops, undeclared consumers, data dependencies, configuration issues, changes in the external world, and a variety of system-level anti-patterns. 1 Introduction As the machine learning (ML) community continues to accumulate years of experience with live
Character-level Convolutional Networks for Text Classification
papers.nips.ccApplying convolutional networks to text classification or natural language processing at large was explored in literature. It has been shown that ConvNets can be directly applied to distributed [6] [16] or discrete [13] embedding of words, without any knowledge on the syntactic or semantic structures of a language.
InfoGAN: Interpretable Representation Learning by ...
papers.nips.cc30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain. ... a higher-order extension of the spike-and-slab restricted Boltzmann machine that can disentangle emotion from identity on the Toronto Face Dataset ... we want PG(cjx) to have a small entropy. In other words, the information in the latent code cshould not ...
Related documents
Sequence to Sequence Learning with Neural Networks
arxiv.orgsearch decoder. This is by far the best result achieved by direct translation with large neural net-works. For comparison,the BLEU score of an SMT baseline on this dataset is 33.30 [29]. The 34.81 BLEU score was achieved by an LSTM with a vocabulary of …
Generating Sequences With Recurrent Neural Networks
arxiv.orgRecurrent Neural Networks Alex Graves Department of Computer Science University of Toronto graves@cs.toronto.edu Abstract This paper shows how Long Short-term Memory recurrent neural net-works can be used to generate complex sequences with long-range struc-ture, simply by predicting one data point at a time. The approach is
High-Frequency Component Helps Explain the Generalization ...
openaccess.thecvf.comtion behaviors of neural networks, such as the capacity in memorizing label shuffled data [65] and the vulnerability towards adversarial examples [54, 21] To explain the generalization behaviors of neural net-works, many theoretical breakthroughs have been made progressively, including studying the properties of stochas-
Exploiting Edge Features for Graph Neural Networks
openaccess.thecvf.commodels to graph node classification on several citation net-works, whole graph classification, and regression on sev-eral molecular datasets. Compared with the current state-of-the-art methods, i.e., GCNs and GAT, our models obtain better performance, which testify to the importance of ex-ploiting edge features in graph neural networks. 1.