Deep Learning
Multi-Resolution Weak Supervision for Sequential Data
Paroma Varma, Frederic Sala, Shiori Sagawa, Jason Fries, Daniel Fu, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, Christopher Rรฉ
Neural Information Processing Systems http://nips.cc/
MarksmanBackdoor: BackdoorAttackswith ArbitraryTargetClass
In recent years, machine learning models have been shown to be vulnerable to backdoor attacks.
SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models
Linfeng Zhang, Zhanhong Tan, Jiebo Song, Jingwei Chen, Chenglong Bao, Kaisheng Ma
Neural Information Processing Systems http://nips.cc/
MetaReg: Towards Domain Generalization using Meta-Regularization
Yogesh Balaji, Swami Sankaranarayanan, Rama Chellappa
Neural Information Processing Systems http://nips.cc/
Sequencer: Deep LSTMfor Image Classification
The modernize result, our Second, the connects Ontheother77], theoutput BiLSTM. Weadopt AdamWoptimizer [wingthepreviousstudy [weadopt ratebatchsizesfor Sequencer2D-S, Sequencer2D-M, are 2048, 1536, and 1024, respectively.
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Tom Zahavy, Matan Haroush, Nadav Merlis, Daniel J. Mankowitz, Shie Mannor
Deep RL(DRL) tackles the curse of dimensionality due to large state spaces by utilizing a Deep Neural Network (DNN) to approximate the value function and/or the policy.
