Self-driving Research in Review: CVPR 2019 Digest
https://medium.com/lyftlevel5/cvpr-digest-9195adbd5d0c
https://medium.com/lyftlevel5/cvpr-digest-9195adbd5d0c
Medium
Self-driving Research in Review: CVPR 2019 Digest
Peter Ondruska, Director, Research
Building AI to inform people's fashion choices
https://ai.facebook.com/blog/building-ai-to-inform-peoples-fashion-choice/
paper: https://research.fb.com/publications/fashion-minimal-edits-for-outfit-improvement/
https://ai.facebook.com/blog/building-ai-to-inform-peoples-fashion-choice/
paper: https://research.fb.com/publications/fashion-minimal-edits-for-outfit-improvement/
Facebook
Building AI to inform people's fashion choices
Facebook researchers have created an AI tool that analyzes sample images and then recommends easy changes to a person's outfit to make it more stylish.
Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs
code: https://github.com/nianticlabs/depth-hints
paper: https://arxiv.org/abs/1909.09051
dataset : https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html
code: https://github.com/nianticlabs/depth-hints
paper: https://arxiv.org/abs/1909.09051
dataset : https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html
GitHub
GitHub - nianticlabs/depth-hints: [ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation…
[ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs - nianticlabs/depth-hints
100,000 FACES GENERATED BY AI FREE FOR ANY USE
https://generated.photos/
https://drive.google.com/drive/folders/1wSy4TVjSvtXeRQ6Zr8W98YbSuZXrZrgY
https://generated.photos/
https://drive.google.com/drive/folders/1wSy4TVjSvtXeRQ6Zr8W98YbSuZXrZrgY
generated.photos
Generated Photos | Unique, worry-free model photos
AI-generated images have never looked better. Explore and download our diverse, copyright-free headshot images from our production-ready database.
ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP
https://github.com/graykode/nlp-roadmap
https://github.com/graykode/nlp-roadmap
GitHub
GitHub - graykode/nlp-roadmap: ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP
ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP - graykode/nlp-roadmap
Computing and artificial intelligence: Humanistic perspectives from MIT
https://news.mit.edu/2019/computing-and-ai-humanistic-perspectives-0924
https://news.mit.edu/2019/computing-and-ai-humanistic-perspectives-0924
MIT News | Massachusetts Institute of Technology
Computing and artificial intelligence: Humanistic perspectives from MIT
Faculty in MIT’s School of Humanities, Arts, and Social Sciences envision how the humanistic fields can help shape the MIT Schwarzman College of Computing — and benefit from advanced computing technologies.
Using deep neural networks for accurate hand-tracking on Oculus Quest
https://ai.facebook.com/blog/hand-tracking-deep-neural-networks/
https://ai.facebook.com/blog/hand-tracking-deep-neural-networks/
Facebook
Using deep neural networks for accurate hand-tracking on Oculus Quest
We’ve used novel machine learning and tracking architectures to develop a new, fully articulated hand-tracking system for VR.
SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model.
https://github.com/slundberg/shap
https://github.com/slundberg/shap
GitHub
GitHub - shap/shap: A game theoretic approach to explain the output of any machine learning model.
A game theoretic approach to explain the output of any machine learning model. - shap/shap
Deep Reinforcement Learning
CS 285 at UC Berkeley Lectures will be streamed and recorded.
lectures: https://www.youtube.com/playlist?list=PLkFD6_40KJIwhWJpGazJ9VSj9CFMkb79A
https://rail.eecs.berkeley.edu/deeprlcourse/
CS 285 at UC Berkeley Lectures will be streamed and recorded.
lectures: https://www.youtube.com/playlist?list=PLkFD6_40KJIwhWJpGazJ9VSj9CFMkb79A
https://rail.eecs.berkeley.edu/deeprlcourse/
YouTube
CS285 Fall 2019
Share your videos with friends, family, and the world
OpenAI’s GPT-2 Text Generator: Wise As a Scholar
https://www.youtube.com/watch?v=0OtZ8dUFxXA
OpenAI's post: https://openai.com/blog/gpt-2-6-month-follow-up/
https://www.youtube.com/watch?v=0OtZ8dUFxXA
OpenAI's post: https://openai.com/blog/gpt-2-6-month-follow-up/
YouTube
OpenAI’s GPT-2 Is Now Available - It Is Wise as a Scholar! 🎓
❤️ Check out Weights & Biases here and sign up for a free demo: https://www.wandb.com/papers
Weights & Biases blog post (the notebook is available too!)
- https://www.wandb.com/articles/visualize-xgboost-in-one-line
- https://colab.research.google.com/d…
Weights & Biases blog post (the notebook is available too!)
- https://www.wandb.com/articles/visualize-xgboost-in-one-line
- https://colab.research.google.com/d…
Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch
https://huggingface.co/transformers
https://huggingface.co/transformers
Probability for Machine Learning ( FREE 7-Day Mini-Course)
https://machinelearningmastery.com/probability-for-machine-learning-7-day-mini-course/
https://machinelearningmastery.com/probability-for-machine-learning-7-day-mini-course/
MachineLearningMastery.com
Probability for Machine Learning (7-Day Mini-Course) - MachineLearningMastery.com
Probability for Machine Learning Crash Course. Get on top of the probability used in machine learning in 7 days. Probability is a field of mathematics that is universally agreed to be the bedrock for machine learning. Although probability is a large field…
Releasing a new benchmark and data set for evaluating neural code search models
https://ai.facebook.com/blog/neural-code-search-evaluation-dataset/
article: https://arxiv.org/abs/1908.09804
code: https://github.com/facebookresearch/Neural-Code-Search-Evaluation-Dataset
https://ai.facebook.com/blog/neural-code-search-evaluation-dataset/
article: https://arxiv.org/abs/1908.09804
code: https://github.com/facebookresearch/Neural-Code-Search-Evaluation-Dataset
Facebook
Releasing a new benchmark and dataset for evaluating neural code search models
We are releasing a new benchmark and dataset to evaluate performance across various neural code search techniques to make it easier to evaluate a new model on a common set of questions.
Causal Bayesian Networks: A flexible tool to enable fairer machine learning
https://deepmind.com/blog/article/Causal_Bayesian_Networks
https://deepmind.com/blog/article/Causal_Bayesian_Networks
Deepmind
Causal Bayesian Networks: A flexible tool to enable fairer machine learning
Decisions based on machine learning (ML) are potentially advantageous over human decisions, as they do not suffer from the same subjectivity, and can be more accurate and easier to analyse. At the same time, data used to train ML systems often contain human…
COMPSCI 282BR - Interpretability and Explainability in Machine Learning
https://interpretable-ml-class.github.io
https://interpretable-ml-class.github.io
interpretable-ml-class.github.io
Explainable AI Course
ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
https://ai.googleblog.com/2019/10/robel-robotics-benchmarks-for-learning.html
https://ai.googleblog.com/2019/10/robel-robotics-benchmarks-for-learning.html
Googleblog
ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
Detectron2: A PyTorch-based modular object detection library
https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/
Detectron2 is FAIR's next-generation research platform for object detection and segmentation
https://github.com/facebookresearch/detectron2
https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/
Detectron2 is FAIR's next-generation research platform for object detection and segmentation
https://github.com/facebookresearch/detectron2
Meta
Detectron2: A PyTorch-based modular object detection library
We are open-sourcing Detectron2, the second-generation of our widely used object-recognition platform. Detectron2 has been rewritten from the ground up in PyTorch to enable faster model iteration and deployment.
The Biggest Threat of Deepfakes Isn’t the Deepfakes Themselves
https://medium.com/mit-technology-review/the-biggest-threat-of-deepfakes-isnt-the-deepfakes-themselves-16de646f51c0
https://medium.com/mit-technology-review/the-biggest-threat-of-deepfakes-isnt-the-deepfakes-themselves-16de646f51c0
Medium
The Biggest Threat of Deepfakes Isn’t the Deepfakes Themselves
The mere idea of AI-synthesized media is already making people stop believing that real things are real
A Gentle Introduction to Bayesian Belief Networks
https://machinelearningmastery.com/introduction-to-bayesian-belief-networks
https://machinelearningmastery.com/introduction-to-bayesian-belief-networks