Efficient PyTorch I/O library for Large Datasets, Many Files, Many GPUs
https://pytorch.org/blog/efficient-pytorch-io-library-for-large-datasets-many-files-many-gpus/
Github: https://github.com/tmbdev/webdataset
Documentation: https://webdataset.readthedocs.io/en/latest/
@ai_machinelearning_big_data
https://pytorch.org/blog/efficient-pytorch-io-library-for-large-datasets-many-files-many-gpus/
Github: https://github.com/tmbdev/webdataset
Documentation: https://webdataset.readthedocs.io/en/latest/
@ai_machinelearning_big_data
Content-Based Recommendation System using Word Embeddings
https://www.kdnuggets.com/2020/08/content-based-recommendation-system-word-embeddings.html
Code: https://github.com/sdhilip200/Content-Based-Recommendation---Good-Reads-data
@ai_machinelearning_big_data
https://www.kdnuggets.com/2020/08/content-based-recommendation-system-word-embeddings.html
Code: https://github.com/sdhilip200/Content-Based-Recommendation---Good-Reads-data
@ai_machinelearning_big_data
KDnuggets
Content-Based Recommendation System using Word Embeddings - KDnuggets
This article explores how average Word2Vec and TF-IDF Word2Vec can be used to build a recommendation engine.
PyTorch 1.6 now includes Stochastic Weight Averaging
https://pytorch.org/blog/pytorch-1.6-now-includes-stochastic-weight-averaging/
@ai_machinelearning_big_data
https://pytorch.org/blog/pytorch-1.6-now-includes-stochastic-weight-averaging/
@ai_machinelearning_big_data
Understanding Deep Learning on Controlled Noisy Labels
https://ai.googleblog.com/2020/08/understanding-deep-learning-on.html
Code: https://github.com/google-research/google-research/tree/master/mentormix
Dataset: https://google.github.io/controlled-noisy-web-labels/index.html
@ai_machinelearning_big_data
https://ai.googleblog.com/2020/08/understanding-deep-learning-on.html
Code: https://github.com/google-research/google-research/tree/master/mentormix
Dataset: https://google.github.io/controlled-noisy-web-labels/index.html
@ai_machinelearning_big_data
Googleblog
Understanding Deep Learning on Controlled Noisy Labels
📗 Forward from the 'Deep Learning for Coders' Book
Post: https://www.fast.ai/2020/08/20/soumith-forward/
Free Book in Jupiter: https://github.com/fastai/fastbook/blob/master/01_intro.ipynb
Github: https://github.com/fastai/fastbook
@ai_machinelearning_big_data
Post: https://www.fast.ai/2020/08/20/soumith-forward/
Free Book in Jupiter: https://github.com/fastai/fastbook/blob/master/01_intro.ipynb
Github: https://github.com/fastai/fastbook
@ai_machinelearning_big_data
👍1
Facebook research at ECCV 2020
https://ai.facebook.com/blog/facebook-research-at-eccv-2020/
@ai_machinelearning_big_data
https://ai.facebook.com/blog/facebook-research-at-eccv-2020/
@ai_machinelearning_big_data
Facebook
Facebook research at ECCV 2020
Facebook researchers and engineers specializing in computer vision, AR/VR, artificial intelligence, infrastructure, and more will be presenting their research…
Introducing Semantic Reactor: Explore NLP in Google Sheets
https://blog.tensorflow.org/2020/08/introducing-semantic-reactor-explore-nlp-sheets.html
Code sample: https://github.com/google/making_with_ml/blob/master/semantic_ml/use_sample.js
@ai_machinelearning_big_data
https://blog.tensorflow.org/2020/08/introducing-semantic-reactor-explore-nlp-sheets.html
Code sample: https://github.com/google/making_with_ml/blob/master/semantic_ml/use_sample.js
@ai_machinelearning_big_data
blog.tensorflow.org
Introducing Semantic Reactor: Explore NLP in Google Sheets
The Semantic Reactor is a new plugin for Google Sheets that lets you run natural language understanding (NLU) models on your own data, right from a spreadsheet.
Building a Neural Network to Predict Loan Risk
https://tymick.me/blog/loan-risk-neural-network
Github: https://github.com/tywmick/loan-risk-neural-network
@ai_machinelearning_big_data
https://tymick.me/blog/loan-risk-neural-network
Github: https://github.com/tywmick/loan-risk-neural-network
@ai_machinelearning_big_data
Ty Mick
Building a Neural Network to Predict Loan Risk - Ty Mick
or, Ty Goes Into Far Too Much Detail About Cleaning Data
PyTorch framework for cryptographically secure random number generation, torchcsprng, now available
https://pytorch.org/blog/torchcsprng-release-blog/
https://pytorch.org/blog/torchcsprng-release-blog/
Introducing TF-Coder, a tool that writes tricky TensorFlow expressions for you
https://blog.tensorflow.org/2020/08/introducing-tensorflow-coder-tool.html
Paper: https://arxiv.org/abs/2003.09040
Code: https://github.com/google-research/tensorflow-coder
Colab: https://colab.research.google.com/github/google-research/tensorflow-coder/blob/master/TF-Coder_Colab.ipynb
https://blog.tensorflow.org/2020/08/introducing-tensorflow-coder-tool.html
Paper: https://arxiv.org/abs/2003.09040
Code: https://github.com/google-research/tensorflow-coder
Colab: https://colab.research.google.com/github/google-research/tensorflow-coder/blob/master/TF-Coder_Colab.ipynb
blog.tensorflow.org
Introducing TF-Coder, a tool that writes tricky TensorFlow expressions for you!
TF-Coder is a program synthesis tool that helps you write TensorFlow code. Instead of coding a tricky tensor manipulation directly, you can just demonstrate it through an illustrative example, and TF-Coder provides the corresponding code automatically.
This media is not supported in your browser
VIEW IN TELEGRAM
👄 Wav2Lip: Accurately Lip-syncing Videos In The Wild
Lip-sync videos to any target speech with high accuracy. Try our interactive demo.
Github: https://github.com/Rudrabha/Wav2Lip
Paper: https://arxiv.org/abs/2008.10010
Interactive Demo: https://bhaasha.iiit.ac.in/lipsync/
Colab: https://colab.research.google.com/drive/1tZpDWXz49W6wDcTprANRGLo2D_EbD5J8?usp=sharing
@ai_machinelearning_big_data
Lip-sync videos to any target speech with high accuracy. Try our interactive demo.
Github: https://github.com/Rudrabha/Wav2Lip
Paper: https://arxiv.org/abs/2008.10010
Interactive Demo: https://bhaasha.iiit.ac.in/lipsync/
Colab: https://colab.research.google.com/drive/1tZpDWXz49W6wDcTprANRGLo2D_EbD5J8?usp=sharing
@ai_machinelearning_big_data
Microsoft’s DoWhy is a Cool Framework for Causal Inference
https://www.kdnuggets.com/2020/08/microsoft-dowhy-framework-causal-inference.html
Github: https://github.com/microsoft/dowhy
@ai_machinelearning_big_data
https://www.kdnuggets.com/2020/08/microsoft-dowhy-framework-causal-inference.html
Github: https://github.com/microsoft/dowhy
@ai_machinelearning_big_data
KDnuggets
Microsoft’s DoWhy is a Cool Framework for Causal Inference - KDnuggets
Inspired by Judea Pearl’s do-calculus for causal inference, the open source framework provides a programmatic interface for popular causal inference methods.
This media is not supported in your browser
VIEW IN TELEGRAM
The Hessian Penalty — Official Implementation
It efficiently optimizes the Hessian of your neural network to be diagonal in an input, leading to disentanglement in that input.
https://www.wpeebles.com/hessian-penalty
Github: https://github.com/wpeebles/hessian_penalty
Paper: https://arxiv.org/abs/2008.10599
Video: https://www.youtube.com/watch?v=uZyIcTkSSXA&feature=youtu.be
@ai_machinelearning_big_data
It efficiently optimizes the Hessian of your neural network to be diagonal in an input, leading to disentanglement in that input.
https://www.wpeebles.com/hessian-penalty
Github: https://github.com/wpeebles/hessian_penalty
Paper: https://arxiv.org/abs/2008.10599
Video: https://www.youtube.com/watch?v=uZyIcTkSSXA&feature=youtu.be
@ai_machinelearning_big_data
Introducing Opacus: A high-speed library for training PyTorch models with differential privacy
https://ai.facebook.com/blog/introducing-opacus-a-high-speed-library-for-training-pytorch-models-with-differential-privacy/
Github: https://github.com/pytorch/opacus
Differential Privacy Series Part 1 | DP-SGD Algorithm Explained: https://medium.com/pytorch/differential-privacy-series-part-1-dp-sgd-algorithm-explained-12512c3959a3
https://ai.facebook.com/blog/introducing-opacus-a-high-speed-library-for-training-pytorch-models-with-differential-privacy/
Github: https://github.com/pytorch/opacus
Differential Privacy Series Part 1 | DP-SGD Algorithm Explained: https://medium.com/pytorch/differential-privacy-series-part-1-dp-sgd-algorithm-explained-12512c3959a3
Meta
Introducing Opacus: A high-speed library for training PyTorch models with differential privacy
We are releasing Opacus, a new high-speed library for training PyTorch models with differential privacy (DP) that’s more scalable than existing state-of-the-art methods.
Top2Vec
Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.
Github: https://github.com/ddangelov/Top2Vec
Paper: https://arxiv.org/abs/2008.09470v1
Doc2vec: https://radimrehurek.com/gensim/models/doc2vec.html
Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.
Github: https://github.com/ddangelov/Top2Vec
Paper: https://arxiv.org/abs/2008.09470v1
Doc2vec: https://radimrehurek.com/gensim/models/doc2vec.html
GitHub
GitHub - ddangelov/Top2Vec: Top2Vec learns jointly embedded topic, document and word vectors.
Top2Vec learns jointly embedded topic, document and word vectors. - ddangelov/Top2Vec
Awsome-domain-adaptation
This repo is a collection of AWESOME things about domain adaptation, including papers, code, etc. Feel free to star and fork.
Github: https://github.com/zhaoxin94/awesome-domain-adaptation
Paper: https://arxiv.org/abs/2009.00155v1
This repo is a collection of AWESOME things about domain adaptation, including papers, code, etc. Feel free to star and fork.
Github: https://github.com/zhaoxin94/awesome-domain-adaptation
Paper: https://arxiv.org/abs/2009.00155v1
Auto-Sklearn for Automated Machine Learning in Python
https://machinelearningmastery.com/auto-sklearn-for-automated-machine-learning-in-python/
https://machinelearningmastery.com/auto-sklearn-for-automated-machine-learning-in-python/
The Little W-Net that Could
State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models.
Github: https://github.com/agaldran/lwnet
Paper: https://arxiv.org/abs/2009.01907v1
State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models.
Github: https://github.com/agaldran/lwnet
Paper: https://arxiv.org/abs/2009.01907v1
KILT: a Benchmark for Knowledge Intensive Language Tasks
All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures.
Github: https://github.com/facebookresearch/KILT
Paper: https://arxiv.org/abs/2009.02252
@ai_machinelearning_big_data
All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures.
Github: https://github.com/facebookresearch/KILT
Paper: https://arxiv.org/abs/2009.02252
@ai_machinelearning_big_data