Asia
A Unified Approach to Count-Based Weakly-Supervised Learning
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally.
f7ae58c7f1a1cc4abe9273a0f971ba2a-Paper.pdf
Variational Bayes (VB) is a scalable alternative to Markov chain Monte Carlo (MCMC)forBayesian posterior inference.
Parsimonious Bayesian deep networks
Neural Information Processing Systems http://nips.cc/
Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks
Anirvan Sengupta, Cengiz Pehlevan, Mariano Tepper, Alexander Genkin, Dmitri Chklovskii
Neural Information Processing Systems http://nips.cc/
Adaptive Influence Maximization with Myopic Feedback
Neural Information Processing Systems http://nips.cc/
Video Prediction via Selective Sampling
Jingwei Xu, Bingbing Ni, Xiaokang Yang
This module is trained in an adversarial learning manner [5]. The Selectionmodule selects high possibility candidates from proposals and combines to produce the final prediction, according to the criteria of better position matching.
Reduced Policy Optimization for Continuous Control with Hard Constraints Shutong Ding 1 Jingya Wang 1 Yali Du2Y e Shi 1 1
Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees.