373 citations · 1.1k across the 25 of their papers we have counts for
7 papers · 1 filter
ReZero is All You Need: Fast Convergence at Large Depth
Thomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao +2
Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architec…
Deflecting Adversarial Attacks
Yao Qin, Nicholas Frosst, Colin Raffel +2
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towar…
Improving Neural Story Generation by Targeted Common Sense Grounding
Huanru Henry Mao, Bodhisattwa Prasad Majumder, Julian McAuley +1
Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasonin…
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Yao Qin, Nicholas Frosst, Sara Sabour +3
Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or…
Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework
Qianli Ma, Lifeng Shen, Garrison W. Cottrell
As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade. However,…
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Yao Qin, Dongjin Song, Haifeng Chen +3
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of mult…
Example Selection For Dictionary Learning
Tomoki Tsuchida, Garrison W. Cottrell
In unsupervised learning, an unbiased uniform sampling strategy is typically used, in order that the learned features faithfully encode the statistical structure of the training da…