🔥 DeiT: Data-efficient Image Transformers

Gittub: https://github.com/facebookresearch/deit

Facebook’s research: https://ai.facebook.com/blog/data-efficient-image-transformers-a-promising-new-technique-for-image-classification/

Paper: https://arxiv.org/abs/2012.12877v1

Vision Transformer: https://github.com/lucidrains/vit-pytorch

@ai_machinelearning_big_data

🌐 Global Context Networks

Github: https://github.com/xvjiarui/GCNet

Paper: https://arxiv.org/abs/2012.13375v1


@ai_machinelearning_big_data

Check the data science channel there you will find a lot of articles, links and advanced researches .
Join and learn hot topics of data science @opendatascience

​​Solving Mixed Integer Programs Using Neural Networks

Article on speeding up Mixed Integer Programs with ML. Mixed Integer Programs are usually NP-hard problems:

- Problems solved with linear programming
- Production planning (pipeline optimization)
- Scheduling / Dispatching

Or any problems where integers represent various decisions (including some of the graph problems).

ArXiV: https://arxiv.org/abs/2012.13349
Wikipedia on Mixed Integer Programming: https://en.wikipedia.org/wiki/Integer_programming

#NPhard #MILP #DeepMind #productionml #linearprogramming #optimizationproblem

Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders

Project: https://taldatech.github.io/soft-intro-vae-web/

Github: https://github.com/taldatech/soft-intro-vae-pytorch

Paper: https://arxiv.org/abs/2012.13253v1

@ai_machinelearning_big_data

💉 MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining

Github: https://github.com/BruceWen120/medal

Paper: https://arxiv.org/abs/2012.13978v1

Dataset: https://www.kaggle.com/xhlulu/medal-emnlp

Pre-trained: https://huggingface.co/xhlu/electra-medal

@ai_machinelearning_big_data

🧠 2020: A Year Full of Amazing AI Papers — A Review

https://www.kdnuggets.com/2020/12/2020-amazing-ai-papers.html

@ai_machinelearning_big_data

🎨 Colorization Transformer

Github: https://github.com/satoshiiizuka/siggraphasia2019_remastering

Results: http://iizuka.cs.tsukuba.ac.jp/projects/remastering/en/index.html

Paper: https://openreview.net/forum?id=5NA1PinlGFu

@ai_machinelearning_big_data

🗒 Machine Learning Cheat Sheets

https://sites.google.com/view/datascience-cheat-sheets

Machine Learning Animations: https://sites.google.com/view/mlingifs#h.341bzfgiuxfx

@ai_machinelearning_big_data

👁‍🗨 LambdaNetworks: Modeling long-range Interactions without Attention

New approach to image recognition that reaches SOTA on ImageNet

Github: https://github.com/leaderj1001/LambdaNetworks

Paper: https://openreview.net/forum?id=xTJEN-ggl1b

Fork: https://github.com/leaderj1001/LambdaNetworks

@ai_machinelearning_big_data

Not All Memories are Created Equal: Learning to Expire

Github: https://github.com/lucidrains/learning-to-expire-pytorch

Paper: https://openreview.net/forum?id=ZVBtN6B_6i7

@ai_machinelearning_big_data

🦠 COVID-Affinity-Model

Github: https://github.com/AlexTS1980/COVID-Affinity-Model

Paper: https://www.medrxiv.org/content/10.1101/2020.12.29.20248987v1.full.pdf

@ai_machinelearning_big_data

🚀 DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions

Introduction: https://openai.com/blog/tags/multimodal/

Deepmind Blog: https://openai.com/blog/dall-e/

Github: https://github.com/openai/CLIP

Paper: https://cdn.openai.com/papers/Learning_Transferable_Visual_Models_From_Natural_Language.pdf

Colab: https://colab.research.google.com/github/openai/clip/blob/master/Interacting_with_CLIP.ipynb

@ai_machinelearning_big_data

🦾 Volumetric Grasping Network.

Github: https://github.com/ethz-asl/vgn

Paper: https://arxiv.org/abs/2101.01132

Video: https://www.youtube.com/watch?v=FXjvFDcV6E0&feature=youtu.be

@ai_machinelearning_big_data

🔇 Deep Noise Suppression Challenge – ICASSP 2021

Github: https://github.com/microsoft/DNS-Challenge

Paper: https://arxiv.org/abs/2101.01902v1

Training and test datasets: https://github.com/microsoft/DNS-Challenge/tree/master/datasets

Challenge: https://www.microsoft.com/en-us/research/academic-program/deep-noise-suppression-challenge-icassp-2021/

@ai_machinelearning_big_data

📛Sharded: A New Technique To Double The Size Of PyTorch Models

Article: https://towardsdatascience.com/sharded-a-new-technique-to-double-the-size-of-pytorch-models-3af057466dba

Habr ru: https://habr.com/ru/company/skillfactory/blog/536394/

ZeRO: Memory Optimizations Paper: https://arxiv.org/abs/1910.02054

@ai_machinelearning_big_data

🔝 Top 10 Computer Vision Papers 2020

https://www.kdnuggets.com/2021/01/top-10-computer-vision-papers-2020.html

@ai_machinelearning_big_data

Datasets

Datasets collected for network science, deep learning and general machine learning research.

Github: https://github.com/benedekrozemberczki/datasets

Paper: https://arxiv.org/abs/2101.03091v1

@ai_machinelearning_big_data