Russian corpus collection
https://natasha.github.io/corus/
https://github.com/natasha/corus
https://nbviewer.jupyter.org/github/natasha/corus/blob/master/docs.ipynb
#Corpus #Dataset

https://github.com/fbdesignpro/sweetviz In-depth EDA (target analysis, comparison, feature analysis, correlation) #Library #Tools
example of use: http://cooltiming.com/SV/SWEETVIZ_REPORT_COMPARED.html

https://github.com/jessevig/bertviz
BertViz is a tool for visualizing attention in the Transformer model, supporting most models from the transformers library (BERT, GPT-2, XLNet, RoBERTa, XLM, CTRL, MarianMT, etc.). #Library #Tools

https://pycaret.org/
An open source low-code machine learning library.|
#Library #Framework

https://github.com/calculatedcontent/weightwatcher
WeightWatcher (WW): is an open-source, diagnostic tool for analyzing Deep Neural Networks (DNN), without needing access to training or even test data.
#Diagnostic #Tool

https://nv-tlabs.github.io/datasetGAN/ #paper

https://github.com/p-lambda/verified_calibration
confidence calibration framework #Framework

https://github.com/fabiankueppers/calibration-framework
confidence calibration framework #Framework

https://github.com/tensorflow/lucid
Lucid is a collection of infrastructure and tools for research in neural network interpretability. #Framework
https://github.com/greentfrapp/lucent

https://umap-learn.readthedocs.io/en/latest/ Uniform Manifold Approximation and Projection (UMAP) is a dimension reduction technique that can be used for visualisation similarly to t-SNE, but also for general non-linear dimension reduction. #Framework #Tools

https://elastiknn.com/ Elasticsearch Plugin for Nearest Neighbor Search on dense vectors
#Tools #Library

https://github.com/EthicalML/awesome-production-machine-learning #Library #Frameworks #Tools

https://arxiv.org/pdf/2103.14030.pdf #paper
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

https://shap.readthedocs.io/en/latest/index.html
SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions.
#Framework

https://www.datagym.ai/ #annotation #tools

https://docs.determined.ai/latest/index.html#
#Framework distributed training, hyperparameter tuning

https://www.determined.ai/blog/data-version-control-determined

https://keras.io/keras_tuner/
#Framework KerasTuner is an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search.

https://www.microsoft.com/en-us/research/project/document-ai/
Microsoft Document AI (Intelligent Document Processing) #Framework

https://www.linkedin.com/posts/smasis_machinelearning-math-datascience-activity-6951137542079467520-4Bb8/
grid search vs Bayesian Optimization for hyperparameter tuning