Interpretable Convolutional Filters with SincNet"

Paper by Mirco Ravanelli, Yoshua Bengio: https://arxiv.org/abs/1811.09725

Code: https://github.com/mravanelli/pytorch-kaldi

Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
https://arxiv.org/abs/1811.09236

Code (Fully Advesarial Mosaics):https://github.com/zalandoresearch/famos

Machine Learning Open Source of the Month (v.Nov 2018)

https://goo.gl/oiGj3b

Matching Features without Descriptors: Implicitly Matched Interest Points (IMIPs)

By Cieslewski et al.: https://arxiv.org/abs/1811.10681

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

By Huang et al.: https://arxiv.org/abs/1811.06965

#ArtificialIntelligence #ComputerVision #DeepLearning #MachineLearning

A General Method for Amortizing Variational Filtering"

By Marino et al.: https://www.yisongyue.com/publications/nips2018_filtering.pdf

#DeepLearning #MachineLearning #NeuralNetworks #NIPS2018

Partial Convolution based Padding

By Liu et al.: https://arxiv.org/pdf/1811.11718.pdf

Code: https://github.com/NVIDIA/partialconv

#artificialintelligence #deeplearning #machinelearning #technology

Summaries of Top AI Research Papers of 2018

By Mariya Yao: https://www.topbots.com/most-important-ai-research-papers-2018/

A combined network and machine learning approaches for product market forecasting

By Fan et al.: https://arxiv.org/abs/1811.10273

#Technology #Physics #Society @ArtificialIntelligenceArticles

Deep Learning for the Masses (… and The Semantic Layer)
https://www.kdnuggets.com/2018/11/deep-learning-masses-semantic-layer.html

The Roles of Supervised Machine Learning in Systems Neuroscience https://arxiv.org/abs/1805.08239

Deep Learning in the Brain, by Blake Richards. Nice to think about whether backprop-ish processes happen in brains. https://www.youtube.com/watch?v=dZwB5Mj-PPM

"Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups"
https://goo.gl/tUysBT

Self-Attention Generative Adversarial Networks"

Tensorflow implementation: https://github.com/brain-research/self-attention-gan

Paper by Zhang et al.: https://arxiv.org/abs/1805.08318

Synthesizing Tabular Data using Generative Adversarial Networks

By Lei Xu, Kalyan Veeramachaneni: https://arxiv.org/abs/1811.11264

Robust Artificial Intelligence and Robust Human Organizations

Thomas G. Dietterich: https://arxiv.org/abs/1811.10840

MIT can now reproduce paintings using deep learning & 3D-printing https://news.mit.edu/2018/mit-csail-repaint-system-reproducing-paintings-make-impression-1129

A Complete Guide to Choosing the Best #MachineLearning Course https://www.kdnuggets.com/2018/11/simplilearn-complete-guide-machine-learning-course.html

Facebook at NeurIPS 2018
https://research.fb.com/facebook-at-neurips-2018/

After Google released Bilateral NN for image enhancement (https://groups.csail.mit.edu/graphics/hdrnet/) they not stopped and created new cool Night Sight algorithm (https://www.theverge.com/2018/11/14/18092660/google-night-sight-review-pixel-2-3-camera-photos-image-quality)
Hope we will see paper for it soon))

Great second talk in the Algorithmic Fairness session on de-biasing image classification datasets. Reported on the results of the Inclusive Images Kaggle competition.

https://www.kaggle.com/c/inclusive-images-challenge
#NeurIPS2018