Researchers at Google deepmind work on some of the most complex and interesting challenges in AI. Their world-class research has resulted in hundreds of peer-reviewed papers, including in Nature and Science. It's a great resource to follow AI research!!

https://deepmind.com/

Now you can train an AI to swipe Tinder for you (Auto-Tinder)

https://www.marktechpost.com/2019/10/27/now-you-can-train-an-ai-to-swipe-tinder-for-you-auto-tinder/

Neuroscientists at University College London started with a simple question: Does the visual cortex represent stimuli with many different response patterns, or does it use similar patterns over and over again? The answer revealed a surprising mathematical rule at work. A power law that governs how the brain encodes sensory inputs as neural activity is tuned to keep our perceptions in balance. If the drop-off in neural responses was faster, important details would be lost. If it were slower, trivia would overwhelm us.
https://www.quantamagazine.org/a-power-law-keeps-the-brains-perceptions-balanced-20191022/

Few-Shot Unsupervised Image-to-Image Translation
paper https://arxiv.org/pdf/1905.01723.pdf
code https://github.com/NVlabs/FUNIT

From NeurIPS 2019: Particularly helpful for fighting wild forest fires: real-time segmentation of fire perimeter from aerial full-motion infrared video
https://www.profillic.com/paper/arxiv:1910.06407
FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video

Pytorch-Struct
Fast, general, and tested differentiable structured prediction in PyTorch. By Harvard NLP : https://github.com/harvardnlp/pytorch-struct
#PyTorch #DeepLearning #ArtificialIntelligence

Capacity, Bandwidth, and Compositionality in Emergent Language Learning
Resnick et al.: https://arxiv.org/abs/1910.11424
#ArtificialIntelligence #MachineLearning #MultiagentSystems

Credit Risk Analysis Using Machine Learning and Deep Learning Models By Peter Martey Dominique Guegan and Bertrand Hassani.

Github: https://github.com/brainy749/CreditRiskPaper
Paper/Article: https://www.mdpi.com/2227-9091/6/2/38/htm

https://t.iss.one/ArtificialIntelligenceArticles

Kaggle:
"Competition Launch: TensorFlow 2.0 Question Answering"
More: https://www.kaggle.com/c/tensorflow2-question-answering

A deep learning framework for neuroscience - Blake A. Richards et al.

@ArtificialIntelligenceArticles
https://www.nature.com/articles/s41593-019-0520-2
@ArtificialIntelligenceArticles

Deep Learning Drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
GitHub by Marimuthu Kalimuthu: https://github.com/kmario23/deep-learning-drizzle
Webpage: https://deep-learning-drizzle.github.io
#artificialintelligence #deeplearning #machinelearning #reinforcementlearning

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
Gupta et al.: https://arxiv.org/abs/1910.11956
Website : https://relay-policy-learning.github.io
#ReinforcementLearning #MachineLearning #Robotics

Deep learning is good at finding patterns in reams of data, but can't explain how they're connected. Turing Award winner Yoshua Bengio wants to change that.
https://www.wired.com/story/ai-pioneer-algorithms-understand-why/
#DeepLearning #AI

Deep causal representation learning for unsupervised domain adaptation
Moraffah et al.: https://arxiv.org/abs/1910.12417
#DeepLearning #MachineLearning #UnsupervisedLearning

Neural Network Distiller: A Python Package For DNN Compression Research
Zmora et al.: https://arxiv.org/abs/1910.12232
#DeepLearning #MachineLearning #Python

Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
Greg Yang : https://arxiv.org/abs/1910.12478
#ArtificialIntelligence #DeepLearning #MachineLearning