https://www.wired.com/story/googles-ai-guru-computers-think-more-like-brains/ Google AI #GeoffreyHinton
WIRED
Google’s AI Guru Wants Computers to Think More Like Brains
Google's top AI researcher, Geoff Hinton, discusses a controversial Pentagon contract, a shortage of radical ideas, and fears of an "AI winter."
Applied Machine Learning course of Columbia University Spring 2018
https://www.cs.columbia.edu/~amueller/comsw4995s18/schedule/
https://www.cs.columbia.edu/~amueller/comsw4995s18/schedule/
Andreas C. Müller - Associate Research Scientist
COMS W4995 Applied Machine Learning Spring 2018 - Schedule
Website of Associate Research Scientist Andreas C. Mueller - Columbia University
Bloomberg talks about FAIR's robotics research effort.
https://www.google.com/amp/s/www.bloomberg.com/amp/news/articles/2019-05-20/facebook-s-robotic-arms-and-legs-are-learning-faster-than-ever
https://www.google.com/amp/s/www.bloomberg.com/amp/news/articles/2019-05-20/facebook-s-robotic-arms-and-legs-are-learning-faster-than-ever
Troubleshooting Deep Neural Networks
A Field Guide to Fixing Your Model
https://josh-tobin.com/troubleshooting-deep-neural-networks
#ArtificialIntelligence #DeepLearning #NeuralNetworks
A Field Guide to Fixing Your Model
https://josh-tobin.com/troubleshooting-deep-neural-networks
#ArtificialIntelligence #DeepLearning #NeuralNetworks
Josh-Tobin
Troubleshooting Deep Neural Networks
A Field Guide to Fixing Your Model
TensorWatch: A debugging and visualization tool designed for deep learning
https://github.com/microsoft/tensorwatch
https://github.com/microsoft/tensorwatch
GitHub
GitHub - microsoft/tensorwatch: Debugging, monitoring and visualization for Python Machine Learning and Data Science
Debugging, monitoring and visualization for Python Machine Learning and Data Science - microsoft/tensorwatch
The Best and Most Current of Modern Natural Language Processing
Blog by Victor Sanh: https://medium.com/huggingface/the-best-and-most-current-of-modern-natural-language-processing-5055f409a1d1
#NaturalLanguageProcessing #MachineLearning #NLP #DeepLearning #Research
Blog by Victor Sanh: https://medium.com/huggingface/the-best-and-most-current-of-modern-natural-language-processing-5055f409a1d1
#NaturalLanguageProcessing #MachineLearning #NLP #DeepLearning #Research
Medium
🌻 The Best and Most Current of Modern Natural Language Processing
Which papers can I read to catch up with the latest trends in modern Natural Language Processing?
Human Visual Understanding for Cognition and Manipulation -- A primer for the roboticist
Hjelm et al.: https://arxiv.org/abs/1905.05272
#Robotics #Neurons #Cognition
Hjelm et al.: https://arxiv.org/abs/1905.05272
#Robotics #Neurons #Cognition
arXiv.org
Human Visual Understanding for Cognition and Manipulation -- A...
Robotic research is often built on approaches that are motivated by insights
from self-examination of how we interface with the world. However, given
current theories about human cognition and...
from self-examination of how we interface with the world. However, given
current theories about human cognition and...
25 Excellent Machine Learning Open Datasets
https://opendatascience.com/25-excellent-machine-learning-open-datasets/
https://opendatascience.com/25-excellent-machine-learning-open-datasets/
Open Data Science - Your News Source for AI, Machine Learning & more
25 Excellent Machine Learning Open Datasets
Looking to work on some data, but can't collect your own? Here are 25 helpful machine learning open datasets to use today!
A machine-learning model from MIT researchers computationally breaks down how segments of amino acid chains determine a protein’s function, which could help researchers design and test new proteins for drug development or biological research.
https://news.mit.edu/2019/machine-learning-amino-acids-protein-function-0322
https://news.mit.edu/2019/machine-learning-amino-acids-protein-function-0322
MIT News | Massachusetts Institute of Technology
Model learns how individual amino acids determine protein function
A model from MIT researchers “learns” vector embeddings of each amino acid position in a 3-D protein structure, which can be used as input features for machine-learning models to predict amino acid segment functions for drug development and biological research.
Using RAPIDS with PyTorch
Blog by Even Oldridge: https://medium.com/rapids-ai/using-rapids-with-pytorch-e602da018285
#MachineLearning #DeepLearning #Pytorch #OpenSource #DataScience
Blog by Even Oldridge: https://medium.com/rapids-ai/using-rapids-with-pytorch-e602da018285
#MachineLearning #DeepLearning #Pytorch #OpenSource #DataScience
Evolving Rewards to Automate Reinforcement Learning"
Faust et al.: https://arxiv.org/abs/1905.07628
#AutoRL #MachineLearning #ReinforcementLearning
Faust et al.: https://arxiv.org/abs/1905.07628
#AutoRL #MachineLearning #ReinforcementLearning
A year ago, Christine finished the Deep Learning Specialization. Now she’s a full-time
OpenAI research scientist building neural networks that create original music. Watch Christine M. Payne and Andrew Ng 's chat: https://www.youtube.com/watch?v=U1bIc6pFdw4
OpenAI research scientist building neural networks that create original music. Watch Christine M. Payne and Andrew Ng 's chat: https://www.youtube.com/watch?v=U1bIc6pFdw4
YouTube
Ones To Watch: Christine Payne
Christine finished the Deep Learning Specialization a year ago. Now she's a full-time OpenAI research scientist building neural networks that create original music. Christine and Andrew chat about the tech behind her latest project, MuseNet, and her advice…
What are the OECD Principles on AI?
The OECD AI Principles: https://www.oecd.org/going-digital/ai/principles/
#ArtificialIntelligence #AIGovernance #DeepLearning #Ethics #Governance
The OECD AI Principles: https://www.oecd.org/going-digital/ai/principles/
#ArtificialIntelligence #AIGovernance #DeepLearning #Ethics #Governance
OECD
Artificial intelligence
Artificial intelligence (AI) is a transformative technology capable of tasks that typically require human-like intelligence, such as understanding language, recognising patterns, and making decisions. AI holds the potential to address complex challenges…
Best Paper Award #ICLR18: 'On the Convergence of Adam and Beyond'
OpenReview: https://openreview.net/pdf?id=ryQu7f-RZ
#artificialintelligence #deeplearning #machinelearning
OpenReview: https://openreview.net/pdf?id=ryQu7f-RZ
#artificialintelligence #deeplearning #machinelearning
#ICLR2019 Best Paper
"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"
Jonathan Frankle, Michael Carbin: https://arxiv.org/abs/1803.03635
#DeepLearning #MachineLearning #NeuralNetworks
"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"
Jonathan Frankle, Michael Carbin: https://arxiv.org/abs/1803.03635
#DeepLearning #MachineLearning #NeuralNetworks
arXiv.org
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without...
Data-Efficient Image Recognition with Contrastive Predictive Coding
Hénaff et al.: https://arxiv.org/abs/1905.09272
#ArtificialIntelligence #ComputerVision #MachineLearning
Hénaff et al.: https://arxiv.org/abs/1905.09272
#ArtificialIntelligence #ComputerVision #MachineLearning
arXiv.org
Data-Efficient Image Recognition with Contrastive Predictive Coding
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient...
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Zakharov et al.: https://arxiv.org/abs/1905.08233
#ComputerVision #GenerativeAdversarialNetworks #MachineLearning
Zakharov et al.: https://arxiv.org/abs/1905.08233
#ComputerVision #GenerativeAdversarialNetworks #MachineLearning
arXiv.org
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head...
A public debate about AGI as part of the World of Science Festival in NYC on May 31, in which I'll share the stage with Gary Kasparov, Shannon Vallor and Hod Lipson. Moderated by Daniel Sieberg.
https://www.worldsciencefestival.com/programs/making-room-for-machines-getting-ready-for-agi/
https://www.worldsciencefestival.com/programs/making-room-for-machines-getting-ready-for-agi/
World Science Festival
Making Room for Machines: Getting Ready For AGI | World Science Festival
Join this year’s Turing Prize winner Yann LeCun and other pioneers in artificial intelligence for a no-nonsense discussion of whether a truly intelligent machine can be created—and, if so, how and when. The “thinking machines” that Alan Turing postulated…