Machine Learning Frameworks in 2019
https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/
https://thegradient.pub/state-of-ml-frameworks-2019-pytorch-dominates-research-tensorflow-dominates-industry/
The Gradient
The State of Machine Learning Frameworks in 2019
Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early academic outputs Caffe and Theano to the massive industry-backed PyTorch…
Open-sourcing mvfst-rl, a research platform for managing network congestion with reinforcement learning
https://ai.facebook.com/blog/open-sourcing-mvfst-rl-a-research-platform-for-managing-network-congestion-with-reinforcement-learning/
code: https://github.com/facebookresearch/mvfst-rl
https://ai.facebook.com/blog/open-sourcing-mvfst-rl-a-research-platform-for-managing-network-congestion-with-reinforcement-learning/
code: https://github.com/facebookresearch/mvfst-rl
Meta
Open-sourcing mvfst-rl, a research platform for managing network congestion with reinforcement learning
We’re open-sourcing a new platform for experimenting with reinforcement learning to proactively adapt to changing traffic patterns.
Information Gain and Mutual Information for Machine Learning
https://machinelearningmastery.com/information-gain-and-mutual-information/
https://machinelearningmastery.com/information-gain-and-mutual-information/
AttoNets, A New AI That is Faster & Efficient For Edge Computing
https://www.marktechpost.com/2019/10/11/attonets-a-new-ai-that-is-faster-efficient-for-edge-computing/
Paper: https://arxiv.org/pdf/1903.07209.pdf
https://www.marktechpost.com/2019/10/11/attonets-a-new-ai-that-is-faster-efficient-for-edge-computing/
Paper: https://arxiv.org/pdf/1903.07209.pdf
MarkTechPost
AttoNets, A New AI That is Faster & Efficient For Edge Computing
An AI team at the University of Waterloo, Canada, developed a new type of compact family of deep neural networks (AttoNets), which can even run on smartphones, tablets, and other mobile devices. The main problem with available neural networks is they require…
Recent advances in low-resource machine translation
https://ai.facebook.com/blog/recent-advances-in-low-resource-machine-translation/
https://ai.facebook.com/blog/recent-advances-in-low-resource-machine-translation/
Facebook
Recent advances in low-resource machine translation
Recently, Facebook AI has advanced state-of-the-art results in key language understanding tasks and also launched a new benchmark to push AI systems further
Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller
article: https://arxiv.org/abs/1909.11236
video: https://youtu.be/wmVKbX7MOnU
code: https://github.com/harvard-edge/source-seeking
article: https://arxiv.org/abs/1909.11236
video: https://youtu.be/wmVKbX7MOnU
code: https://github.com/harvard-edge/source-seeking
AI Learns Human Movement From Unorganized Data 🏃♀️
https://www.youtube.com/watch?v=882O_7hsAms
📝 The paper "Learning Predict-and-Simulate Policies From Unorganized Human Motion Data»
https://mrl.snu.ac.kr/publications/ProjectICC/ICC.html
https://www.youtube.com/watch?v=882O_7hsAms
📝 The paper "Learning Predict-and-Simulate Policies From Unorganized Human Motion Data»
https://mrl.snu.ac.kr/publications/ProjectICC/ICC.html
YouTube
AI Learns Human Movement From Unorganized Data 🏃♀️
❤️ Check out Lambda here and sign up for their GPU Cloud: https://lambdalabs.com/papers
📝 The paper "Learning Predict-and-Simulate Policies From Unorganized Human Motion Data" is available here:
https://mrl.snu.ac.kr/publications/ProjectICC/ICC.html
🙏 We…
📝 The paper "Learning Predict-and-Simulate Policies From Unorganized Human Motion Data" is available here:
https://mrl.snu.ac.kr/publications/ProjectICC/ICC.html
🙏 We…
Open-Source Library for Real-Time Metric-Semantic Localization and Mapping
video: https://www.youtube.com/watch?v=-5XxXRABXJs&feature=youtu.be
code: https://github.com/MIT-SPARK/Kimera
article: https://arxiv.org/abs/1910.02490
video: https://www.youtube.com/watch?v=-5XxXRABXJs&feature=youtu.be
code: https://github.com/MIT-SPARK/Kimera
article: https://arxiv.org/abs/1910.02490
YouTube
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping
Code available: https://github.com/MIT-SPARK/Kimera
Paper: https://arxiv.org/abs/1910.02490
Kimera has also been used in:
- 3D Dynamic Scene Graphs:
Video: https://www.youtube.com/watch?v=SWbofjhyPzI&feature=youtu.be
Paper: https://arxiv.org/abs/2002.06289…
Paper: https://arxiv.org/abs/1910.02490
Kimera has also been used in:
- 3D Dynamic Scene Graphs:
Video: https://www.youtube.com/watch?v=SWbofjhyPzI&feature=youtu.be
Paper: https://arxiv.org/abs/2002.06289…
Feature Engineering
The most effective way to improve your models
https://www.kaggle.com/learn/feature-engineering
The most effective way to improve your models
https://www.kaggle.com/learn/feature-engineering
Kaggle
Learn Feature Engineering Tutorials
Better features make better models. Discover how to get the most out of your data.
DeepFake Detector AIs Are Good Too!
https://www.youtube.com/watch?v=RoGHVI-w9bE
article: https://www.niessnerlab.org/projects/roessler2019faceforensicspp.html
https://www.youtube.com/watch?v=RoGHVI-w9bE
article: https://www.niessnerlab.org/projects/roessler2019faceforensicspp.html
YouTube
DeepFake Detector AIs Are Good Too!
❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers
📝 The paper "FaceForensics++: Learning to Detect Manipulated Facial Images" is available here:
https://www.niessnerlab.org/projects/roessler2019faceforensicspp.html
❤️ Watch…
📝 The paper "FaceForensics++: Learning to Detect Manipulated Facial Images" is available here:
https://www.niessnerlab.org/projects/roessler2019faceforensicspp.html
❤️ Watch…
OpenAI Plays Hide and Seek…and Breaks The Game! 🤖
https://www.youtube.com/watch?v=Lu56xVlZ40M
article: https://openai.com/blog/emergent-tool-use/
https://www.youtube.com/watch?v=Lu56xVlZ40M
article: https://openai.com/blog/emergent-tool-use/
YouTube
OpenAI Plays Hide and Seek…and Breaks The Game! 🤖
❤️ Check out Weights & Biases here and sign up for a free demo: https://www.wandb.com/papers
❤️ Their blog post is available here: https://www.wandb.com/articles/better-paths-through-idea-space
📝 The paper "Emergent Tool Use from Multi-Agent Interaction"…
❤️ Their blog post is available here: https://www.wandb.com/articles/better-paths-through-idea-space
📝 The paper "Emergent Tool Use from Multi-Agent Interaction"…
Using videos to teach AI about objects
https://research.fb.com/publications/grounded-human-object-interaction-hotspots-from-video/
https://ai.facebook.com/blog/research-in-brief-grounded-human-object-interaction-hotspots/
article: https://research.fb.com/wp-content/uploads/2019/09/Grounded-Human-Object-Interaction-Hotspots-From-Video.pdf?
https://research.fb.com/publications/grounded-human-object-interaction-hotspots-from-video/
https://ai.facebook.com/blog/research-in-brief-grounded-human-object-interaction-hotspots/
article: https://research.fb.com/wp-content/uploads/2019/09/Grounded-Human-Object-Interaction-Hotspots-From-Video.pdf?
Facebook Research
Grounded Human-Object Interaction Hotspots From Video - Facebook Research
Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction “hotspots” directly from…
A Gentle Introduction to Maximum Likelihood Estimation for Machine Learning
https://machinelearningmastery.com/what-is-maximum-likelihood-estimation-in-machine-learning/
https://machinelearningmastery.com/what-is-maximum-likelihood-estimation-in-machine-learning/
GPyTorch
Gaussian processes for modern machine learning systems.
https://gpytorch.ai
code: https://github.com/cornellius-gp/gpytorch
Gaussian processes for modern machine learning systems.
https://gpytorch.ai
code: https://github.com/cornellius-gp/gpytorch
GitHub
GitHub - cornellius-gp/gpytorch: A highly efficient implementation of Gaussian Processes in PyTorch
A highly efficient implementation of Gaussian Processes in PyTorch - cornellius-gp/gpytorch
Stuart_Russell___Human_Compatibl.epub
9.7 MB
Human Compatible: Artificial Intelligence and the Problem of Control
Stuart Russell
Stuart Russell
A New Workflow for Collaborative Machine Learning Research in Biodiversity
https://ai.googleblog.com/2019/10/a-new-workflow-for-collaborative.html
https://ai.googleblog.com/2019/10/a-new-workflow-for-collaborative.html
Googleblog
A New Workflow for Collaborative Machine Learning Research in Biodiversity
Facebook research being presented at ICCV
https://ai.facebook.com/blog/facebook-research-at-iccv-2019/
https://ai.facebook.com/blog/facebook-research-at-iccv-2019/
Facebook
Facebook research being presented at ICCV
Facebook researchers will join computer vision experts from around the world to discuss the latest advances at the International Conference on Computer Vision (ICCV) in Seoul, Korea, from October 27 to November 2.
A Gentle Introduction to Logistic Regression With Maximum Likelihood Estimation
https://machinelearningmastery.com/logistic-regression-with-maximum-likelihood-estimation/
https://machinelearningmastery.com/logistic-regression-with-maximum-likelihood-estimation/
MachineLearningMastery.com
A Gentle Introduction to Logistic Regression With Maximum Likelihood Estimation - MachineLearningMastery.com
Logistic regression is a model for binary classification predictive modeling. The parameters of a logistic regression model can be estimated by the probabilistic framework called maximum likelihood estimation. Under this framework, a probability distribution…
A new dense, sliding-window technique for instance segmentation
https://ai.facebook.com/blog/a-new-dense-sliding-window-technique-for-instance-segmentation/
https://ai.facebook.com/blog/a-new-dense-sliding-window-technique-for-instance-segmentation/
Meta
A new dense, sliding-window technique for instance segmentation
We’re introducing a new method that uses dense, sliding-window technique — instead of standard bounding boxes — to perform instance segmentation. .