Behaviour Suite for Reinforcement Learning, or ‘bsuite’
Osband et al. https://arxiv.org/abs/1908.03568v2
A collection of carefully-designed experiments that investigate core capabilities of RL agents
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
Osband et al. https://arxiv.org/abs/1908.03568v2
A collection of carefully-designed experiments that investigate core capabilities of RL agents
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
Deepfakes may be a useful tool for spies https://www.technologyreview.com/f/613778/deepfakes-spies-espionage/
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
https://arxiv.org/abs/2001.06937
https://arxiv.org/abs/2001.06937
PHYRE: A New Benchmark for Physical Reasoning
By: Anton Bakhtin, Laurens van der Maaten, Justin Johnson, Laura Gustafson and Ross Girshick.
Facebook AI Research : https://phyre.ai
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
By: Anton Bakhtin, Laurens van der Maaten, Justin Johnson, Laura Gustafson and Ross Girshick.
Facebook AI Research : https://phyre.ai
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
phyre.ai
PHYRE · A Benchmark For Physical Reasoning
GPT-2 and the Nature of Intelligence
Gary Marcus, The Gradient: https://thegradient.pub/gpt2-and-the-nature-of-intelligence/
#GPT2 #DeepLearning #GenerativeModels
Gary Marcus, The Gradient: https://thegradient.pub/gpt2-and-the-nature-of-intelligence/
#GPT2 #DeepLearning #GenerativeModels
The Gradient
GPT-2 and the Nature of Intelligence
Anything that looks like genuine understanding is just an illusion.
Geoffrey Hinton - On the Nature of Intelligence
https://www.youtube.com/watch?v=MhvfhKnEIqM
https://www.youtube.com/watch?v=MhvfhKnEIqM
YouTube
Geoffrey Hinton - On the Nature of Intelligence
This talk is from the Creative Destruction Lab's fourth annual conference, "Machine Learning and the Market for Intelligence", hosted at the University of Toronto's Rotman School of Management on October 23, 2018.
Improved Classification of Blood-Brain-Barrier Drugs Using Deep Learning
https://www.nature.com/articles/s41598-019-44773-4
https://www.nature.com/articles/s41598-019-44773-4
Nature
Improved Classification of Blood-Brain-Barrier Drugs Using Deep Learning
Scientific Reports - Improved Classification of Blood-Brain-Barrier Drugs Using Deep Learning
Multi Matrix Deep Learning with GPUs
https://www.artiba.org/blog/multi-matrix-deep-learning-with-gpus
https://www.artiba.org/blog/multi-matrix-deep-learning-with-gpus
Introduction to Reinforcement Learning
By DeepMind : https://youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
By DeepMind : https://youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
Optuna: A Next-generation Hyperparameter Optimization Framework"
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
Google brings cross-platform AI pipeline framework MediaPipe to the web
https://venturebeat.com/2020/01/28/google-brings-cross-platform-ai-pipeline-framework-mediapipe-to-the-web/
https://venturebeat.com/2020/01/28/google-brings-cross-platform-ai-pipeline-framework-mediapipe-to-the-web/
VentureBeat
Google brings cross-platform AI pipeline framework MediaPipe to the web
Google has adapted MediaPipe, its open source framework for creating cross-platform AI pipelines, for deployment to the web.
PolyGame: An open-source framework for training AI players through self-play. Deals with many games, board size variation, partial observability...
https://ai.facebook.com/blog/open-sourcing-polygames-a-new-framework-for-training-ai-bots-through-self-play/
https://ai.facebook.com/blog/open-sourcing-polygames-a-new-framework-for-training-ai-bots-through-self-play/
Facebook
Open-sourcing Polygames, a new framework for training AI bots through self-play
In a collaboration with universities in France and Taiwan, Facebook AI is releasing Polygames, a new open source framework that enables researchers to train AI systems through self-play in a wide range of strategy games.
DeNeRD: an AI-based method to process whole images of the brain
https://medicalxpress.com/news/2019-10-denerd-ai-based-method-images-brain.html
https://medicalxpress.com/news/2019-10-denerd-ai-based-method-images-brain.html