The Two-Pass Softmax Algorithm
Code: https://github.com/google/XNNPACK
Paper: https://arxiv.org/abs/2001.04438v1
Code: https://github.com/google/XNNPACK
Paper: https://arxiv.org/abs/2001.04438v1
GitHub
GitHub - google/XNNPACK: High-efficiency floating-point neural network inference operators for mobile, server, and Web
High-efficiency floating-point neural network inference operators for mobile, server, and Web - google/XNNPACK
Controlling Text Generation with Plug and Play Language Models
https://eng.uber.com/pplm/
Paper: https://arxiv.org/abs/1912.02164
Code: https://github.com/uber-research/PPLM
https://eng.uber.com/pplm/
Paper: https://arxiv.org/abs/1912.02164
Code: https://github.com/uber-research/PPLM
The Autonomous Learning Library: A PyTorch Library for Building Reinforcement Learning Agents
https://autonomous-learning-library.readthedocs.io.
Code: https://github.com/cpnota/autonomous-learning-library
https://autonomous-learning-library.readthedocs.io.
Code: https://github.com/cpnota/autonomous-learning-library
GitHub
GitHub - cpnota/autonomous-learning-library: A PyTorch library for building deep reinforcement learning agents.
A PyTorch library for building deep reinforcement learning agents. - cpnota/autonomous-learning-library
Creating a Custom TFX Component
https://blog.tensorflow.org/2020/01/creating-custom-tfx-component.html/
https://blog.tensorflow.org/2020/01/creating-custom-tfx-component.html/
blog.tensorflow.org
Creating a Custom TFX Component
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.
Building richer, real-world data sets to push conversational research forward
https://ai.facebook.com/blog/building-richer-real-world-data-sets-to-push-conversational-research-forward
https://ai.facebook.com/blog/building-richer-real-world-data-sets-to-push-conversational-research-forward
Meta
Building richer, real-world datasets to push conversational research forward
Beat the Bot, which is a game exclusively for researchers on Messenger, helps provide conversational AI researchers with high-signal data. We plan to open-source our dataset to help push dialogue research forward.
The Story of Heads
Code: https://github.com/lena-voita/the-story-of-heads
https://lena-voita.github.io/posts/acl19_heads.html
Paper: https://www.aclweb.org/anthology/P19-1580/
Code: https://github.com/lena-voita/the-story-of-heads
https://lena-voita.github.io/posts/acl19_heads.html
Paper: https://www.aclweb.org/anthology/P19-1580/
GitHub
GitHub - lena-voita/the-story-of-heads: This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention:…
This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 pa...
Towards a Conversational Agent that Can Chat About…Anything
https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html
https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html
research.google
Towards a Conversational Agent that Can Chat About…Anything
Posted by Daniel Adiwardana, Senior Research Engineer, and Thang Luong, Senior Research Scientist, Google Research, Brain Team Modern conversatio...
Deep Graph Matching Consensus
Code: https://github.com/rusty1s/deep-graph-matching-consensus
Paper: https://arxiv.org/abs/2001.09621v1
Code: https://github.com/rusty1s/deep-graph-matching-consensus
Paper: https://arxiv.org/abs/2001.09621v1
Spinning Up in Deep RL
https://spinningup.openai.com/en/latest/
Github: https://github.com/openai/spinningup
https://spinningup.openai.com/en/latest/
Github: https://github.com/openai/spinningup
GitHub
GitHub - openai/spinningup: An educational resource to help anyone learn deep reinforcement learning.
An educational resource to help anyone learn deep reinforcement learning. - openai/spinningup
Encode, Tag and Realize: A Controllable and Efficient Approach for Text Generation
https://ai.googleblog.com/2020/01/encode-tag-and-realize-controllable-and.html
Code: https://github.com/google-research/lasertagger
https://ai.googleblog.com/2020/01/encode-tag-and-realize-controllable-and.html
Code: https://github.com/google-research/lasertagger
Googleblog
Encode, Tag and Realize: A Controllable and Efficient Approach for Text Generation
How to Develop a Cost-Sensitive Neural Network for Imbalanced Classification
https://machinelearningmastery.com/cost-sensitive-neural-network-for-imbalanced-classification/
https://machinelearningmastery.com/cost-sensitive-neural-network-for-imbalanced-classification/
MachineLearningMastery.com
How to Develop a Cost-Sensitive Neural Network for Imbalanced Classification - MachineLearningMastery.com
Deep learning neural networks are a flexible class of machine learning algorithms that perform well on a wide range of problems. Neural networks are trained using the backpropagation of error algorithm that involves calculating errors made by the model on…
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
Code: https://github.com/cambridgeltl/parameter-factorization
Paper: https://arxiv.org/pdf/2001.11453.pdf
Code: https://github.com/cambridgeltl/parameter-factorization
Paper: https://arxiv.org/pdf/2001.11453.pdf
GitHub
GitHub - cambridgeltl/parameter-factorization: Factorization of the neural parameter space for zero-shot multi-lingual and multi…
Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transfer - GitHub - cambridgeltl/parameter-factorization: Factorization of the neural parameter space for zero...
End-to-end training of sparse deep neural networks with little-to-no performance loss.
Code: https://github.com/google-research/rigl
Paper: https://arxiv.org/abs/1911.11134v1
Code: https://github.com/google-research/rigl
Paper: https://arxiv.org/abs/1911.11134v1
Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network
Paper: https://arxiv.org/abs/2002.00544v1
Code: https://github.com/uwjunqi/Tensor-Train-Neural-Network
Paper: https://arxiv.org/abs/2002.00544v1
Code: https://github.com/uwjunqi/Tensor-Train-Neural-Network
GitHub
GitHub - uwjunqi/Pytorch-Tensor-Train-Network: Jun and Huck's PyTorch-Tensor-Train Network Toolbox
Jun and Huck's PyTorch-Tensor-Train Network Toolbox - GitHub - uwjunqi/Pytorch-Tensor-Train-Network: Jun and Huck's PyTorch-Tensor-Train Network Toolbox
ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems
https://ai.googleblog.com/2020/02/ml-fairness-gym-tool-for-exploring-long.html
Code: https://github.com/google/ml-fairness-gym/
Paper: https://github.com/google/ml-fairness-gym/blob/master/papers/acm_fat_2020_fairness_is_not_static.pdf
https://ai.googleblog.com/2020/02/ml-fairness-gym-tool-for-exploring-long.html
Code: https://github.com/google/ml-fairness-gym/
Paper: https://github.com/google/ml-fairness-gym/blob/master/papers/acm_fat_2020_fairness_is_not_static.pdf
Googleblog
ML-fairness-gym: A Tool for Exploring Long-Term Impacts of Machine Learning Systems
Introducing PyTorch3D: An open-source library for 3D deep learning
https://ai.facebook.com/blog/-introducing-pytorch3d-an-open-source-library-for-3d-deep-learning/
Code: https://github.com/facebookresearch/pytorch3d
https://ai.facebook.com/blog/-introducing-pytorch3d-an-open-source-library-for-3d-deep-learning/
Code: https://github.com/facebookresearch/pytorch3d
Facebook
Introducing PyTorch3D: An open-source library for 3D deep learning
We just released PyTorch3D, a new toolkit for researchers and engineers that’s fast and modular for 3D deep learning research.
PyRoboLearn: A Python Framework for Robot Learning Practitioners
Github: https://github.com/robotlearn/pyrobolearn
https://robotlearn.github.io/pyrobolearn/
Github: https://github.com/robotlearn/pyrobolearn
https://robotlearn.github.io/pyrobolearn/
GitHub
GitHub - robotlearn/pyrobolearn: PyRoboLearn: a Python framework for Robot Learning
PyRoboLearn: a Python framework for Robot Learning - robotlearn/pyrobolearn
TyDi QA: A Multilingual Question Answering Benchmark
https://ai.googleblog.com/2020/02/tydi-qa-multilingual-question-answering.html
https://ai.googleblog.com/2020/02/tydi-qa-multilingual-question-answering.html
blog.research.google
TyDi QA: A Multilingual Question Answering Benchmark