Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models https://arxiv.org/abs/1805.12114
arXiv.org
Deep Reinforcement Learning in a Handful of Trials using...
Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is...
Dark Machines is a research collective of physicists and data scientists. We are curious about the universe and want to answer cutting edge questions about Dark Matter with the most advanced techniques that data science provides us with. http://www.darkmachines.org/
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks https://ai.intel.com/nervana/wp-content/uploads/sites/53/2018/06/ELQ_CameraReady_CVPR2018.pdf
Auto-Meta: Automated Gradient Based Meta Learner Search https://arxiv.org/abs/1806.06927
arXiv.org
Auto-Meta: Automated Gradient Based Meta Learner Search
Fully automating machine learning pipelines is one of the key challenges of
current artificial intelligence research, since practical machine learning
often requires costly and time-consuming...
current artificial intelligence research, since practical machine learning
often requires costly and time-consuming...
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization https://arxiv.org/abs/1806.08054
Training a Network of Spiking Neurons with Equilibrium Propagation https://openreview.net/forum?id=HygpgV2-bX
openreview.net
Training a Network of Spiking Neurons with Equilibrium Propagation
Backpropagation is almost universally used to train artificial neural networks. However, there are several reasons that backpropagation could not be plausibly implemented by biological neurons....
DARTS: Differentiable Architecture Search https://arxiv.org/abs/1806.09055 https://github.com/quark0/darts
GitHub
GitHub - quark0/darts: Differentiable architecture search for convolutional and recurrent networks
Differentiable architecture search for convolutional and recurrent networks - quark0/darts
Gradient Adversarial Training of Neural Networks https://arxiv.org/abs/1806.08028
A Configurable Cloud-Scale DNN Processor for Real-Time AI https://www.microsoft.com/en-us/research/uploads/prod/2018/06/ISCA18-Brainwave-CameraReady.pdf
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces https://arxiv.org/abs/1803.09179
Constructing Deep Neural Networks by Bayesian Network Structure Learning https://arxiv.org/abs/1806.09141
Deducing the symmetry of the standard model from the automorphism and structure groups of the exceptional Jordan algebra https://arxiv.org/abs/1806.09450