Adversarial Examples in Deep Learning.

https://blog.djsarkar.ai/adversarial-learning-attacks-1/

Github: https://github.com/dipanjanS/adversarial-learning-robustness

@ArtificialIntelligencedl

TJU-DHD dataset (object detection and pedestrian detection)

Github: https://github.com/tjubiit/TJU-DHD

Paper: https://arxiv.org/abs/2011.09170v1

@ai_machinelearning_big_data

FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance

Github: https://github.com/AI4Finance-LLC/FinRL-Library

Paper: https://arxiv.org/abs/2011.09607

@ai_machinelearning_big_data

Computer Vision at Scale With Dask And PyTorch

https://www.saturncloud.io/s/computer-vision-at-scale-with-dask-and-pytorch/

Code: https://github.com/saturncloud/saturn-cloud-examples/tree/main/pytorch-demo

@ai_machinelearning_big_data

Object Detection Using Mask R-CNN with TensorFlow 2.0 and Keras.

https://blog.paperspace.com/mask-r-cnn-tensorflow-2-0-keras/

Mask_RCNN project: https://github.com/matterport/Mask_RCNN

@ai_machinelearning_big_data

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

Github: https://github.com/PeizeSun/SparseR-CNN

Paper: https://arxiv.org/abs/2011.12450

@ai_machinelearning_big_data

PyTorch Static Quantization.

https://leimao.github.io/blog/PyTorch-Static-Quantization/

Code: https://github.com/leimao/PyTorch-Static-Quantization

Quantization for Neural Networks: https://leimao.github.io/article/Neural-Networks-Quantization/

@ai_machinelearning_big_data

Deep & Cross Network (DCN).

https://www.tensorflow.org/recommenders/examples/dcn

Code: https://github.com/tensorflow/recommenders/blob/main/docs/examples/dcn.ipynb

TensorFlow Recommenders: Scalable retrieval and feature interaction modelling: https://blog.tensorflow.org/2020/11/tensorflow-recommenders-scalable-retrieval-feature-interaction-modelling.html

Paper: https://arxiv.org/pdf/2008.13535.pdf

@ai_machinelearning_big_data

Learning to Summarize from Human Feedback

Github: https://github.com/openai/summarize-from-feedback

Dataset: https://openaipublic.blob.core.windows.net/summarize-from-feedback/website/index.html#/

Paper: https://proceedings.neurips.cc//paper/2020/file/1f89885d556929e98d3ef9b86448f951-Paper.pdf

@ai_machinelearning_big_data

A Photogrammetry-based Framework to Facilitate Image-based Modeling and Automatic Camera Tracking

Github: https://github.com/SBCV/Blender-Addon-Photogrammetry-Importer

Paper: https://arxiv.org/abs/2012.01044v1

@ai_machinelearning_big_data

pixelNeRF: Neural Radiance Fields from One or Few Images.

Github: https://github.com/sxyu/pixel-nerf

Paper: http://arxiv.org/abs/2012.02190

@ai_machinelearning_big_data

Tensorflow TPU

https://www.tensorflow.org/guide/tpu

Code: https://github.com/tensorflow/docs/blob/master/site/en/guide/tpu.ipynb

SavedModel Guide: https://www.tensorflow.org/guide/saved_model

@ai_machinelearning_big_data

Learnable Tree Filter V2.

Github: https://github.com/StevenGrove/LearnableTreeFilterV2

Paper: https://arxiv.org/abs/2012.03482v1

@ai_machinelearning_big_data

Hello colleagues!

Today I would like to share great news with you - we have opensourced our python framework LightAutoML (LAMA) aimed at Automated Machine Learning. It is designed to be lightweight and efficient for various tasks (binary/multiclass classifcation and regression) on tabular datasets which contains different types of features: numeric, categorical, dates, texts etc.

LAMA provides not only presets suite for end-to-end ML tasks solving, but also the easy-to-use ML pipeline creation constructor including data preprocessing elements, advanced feature generation, CV schemes (including nested CVs), hyperparameters tuning, different models and composition building methods. It also gives the user an option to generate model training and profiling reports to check model results and find insights which are not obvious from initial dataset.

Here are some examples of LAMA usage on binary classification task:
⁃ Blackbox pipeline = https://www.kaggle.com/simakov/lama-tabularautoml-preset-example
⁃ Interpretable model = https://www.kaggle.com/simakov/lama-whitebox-preset-example
⁃ Custom elements + existing ones = https://www.kaggle.com/simakov/lama-custom-automl-pipeline-example

Official documentation is here: https://lightautoml.readthedocs.io
Github: https://github.com/sberbank-ai-lab/LightAutoML
Slack community: https://lightautoml-slack.herokuapp.com

Please enjoy! :)

River: machine learning for streaming data in Python

https://github.com/online-ml/river

Paper: https://arxiv.org/abs/2012.04740v1

Online machine learning: https://www.wikiwand.com/en/Online_machine_learning

@ai_machinelearning_big_data

Implementation of Adam and AMSGrad Optimizers

Project: https://lab-ml.com/labml_nn/optimizers/adam.html

AMSGrad: https://lab-ml.com/labml_nn/optimizers/amsgrad.html

GitHub: https://github.com/lab-ml/nn

Full list: https://lab-ml.com/labml_nn/index.html

@ArtificialIntelligencedl