Here is a wonderful Self Supervised Learning 122 page lecture notebook by Andrew Zisserman from Deepmind
Download Link: https://project.inria.fr/paiss/files/2018/07/zisserman-self-supervised.pdf

Cool paper written by Yoshua Bengio’s MILA team.

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.

Paper: arxiv.org/abs/1905.10437
GitHub for M4 dataset: https://github.com/M4Competition/M4-methods/tree/master/Dataset
#timeseries #deeplearning

Divide and Conquer the Embedding Space for Metric Learning, CVPR 2019

code https://github.com/CompVis/metric-learning-divide-and-conquer

Beyond data and model parallelism for deep neural networks
https://blog.acolyer.org/2019/06/12/beyond-data-and-model-parallelism/

Research suggests that fatherhood could increase oxytocin (a hormone associated with social bonding) and decrease testosterone (a hormone associated with aggression) as it develops neurons and alters activity in the brain.

https://m.washingtontimes.com/news/2019/jun/15/fatherhood-changes-mens-brains-and-minds-studies-s/

Contrastive Multiview Coding
Tian et al.: https://arxiv.org/abs/1906.05849
Code: https://github.com/HobbitLong/CMC/
#artificialintelligence #deeplearning #selfsupervisedlearning

Best paper ICML 2019


Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Locatello et al.: https://arxiv.org/pdf/1811.12359.pdf
#deeplearning #disentangledrepresentations #unsupervisedlearning

TOP 10 BOOKS ON ARTIFICIAL INTELLIGENCE

https://www.analyticsinsight.net/top-10-books-on-artificial-intelligence-you-cannot-afford-to-miss/

Jacobian Policy Optimizations. arxiv.org/abs/1906.05437

tf.keras for Researchers: Crash Course
"That's all you need to get started with reimplementing most deep learning research papers in TensorFlow 2.0 and Keras!"
Code by François Chollet: https://colab.research.google.com/drive/14CvUNTaX1OFHDfaKaaZzrBsvMfhCOHIR
#deeplearning #keras #tensorflow #tutorial

Congrats to legendary scientists Yoshua Bengio, Yann LeCun and Geoffrey Hinton for receiving Turing Award today at ceremony hosted by ACM.Google Senior Fellow Jeff Dean is handing over this prestigious award to these legends. ACM - Association for Computing Machinery Facebook AI Google AI Google Universite De Montreal - Campus Laval

A Rhythmic Theory of Attention


https://www.sciencedirect.com/science/article/abs/pii/S136466131830281X

Best paper award at #ICML2019 main idea: unsupervised learning of disentangled representations is fundamentally
impossible without inductive biases. Verified theoretically & experimentally. https://arxiv.org/pdf/1811.12359.pdf

TensorFlow 2.0.0-beta0 CPU, Python 3.5, ARMv7 for Raspberry Pi
Code: https://github.com/yaroslavvb/tensorflow-community-wheels/issues/114
#tensorflow #raspberrypi #machinelearning #python3 #artificialintelligence

Apprentissage automatique pour la visualisation

Par Ian Johnson : https://medium.com/@enjalot/machine-learning-for-visualization-927a9dff1cab

#intelligenceartificielle

SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition With Distractors
https://openaccess.thecvf.com/content_CVPRW_2019/html/WiCV/Jalal_SIDOD_A_Synthetic_Image_Dataset_for_3D_Object_Pose_Recognition_CVPRW_2019_paper.html

Eye Contact Correction using Deep Neural Networks. arxiv.org/abs/1906.05378

Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values.

Article: weightagnostic.github.io
PDF: arxiv.org/abs/1906.04358

Generative Modeling and Model Based Reasoning for Robotics and AI Yann LeCun https://www.youtube.com/watch?v=cQvyPNmpFgc https://t.iss.one/ArtificialIntelligenceArticles

AI that learns to write code!

Researchers combine deep learning and symbolic reasoning for a more flexible way of teaching computers to program.

https://www.profillic.com/paper/arxiv:1902.06349