One more great source of Data Science, Deep Learning, Machine Learning, Computer Vision, AI and more...
Enjoy with hot topics and projects

Learning perturbation sets for robust machine learning

Tackled the problem of defining a perturbation set for real-world perturbations which cannot be easily described with a set of equations.

Paper: https://arxiv.org/abs/2007.08450

Blog post: https://locuslab.github.io/2020-07-20-perturbation/

Code: https://github.com/locuslab/perturbation_learning

Baidu publishes PP-YOLO and pushes the state of the art in object detection research.

80+ Jupyter Notebook tutorials on image classification, object detection and image segmentation in various domains
📌 Agriculture and Food
📌 Medical and Healthcare
📌 Satellite
📌 Security and Surveillance
📌 ADAS and Self Driving Cars
📌 Retail and E-Commerce
📌 Wildlife

Classification library
https://github.com/Tessellate-Imaging/monk_v1

Notebooks - https://github.com/Tessellate-Imaging/monk_v1/tree/master/study_roadmaps/4_image_classification_zoo

Detection and Segmentation Library
https://github.com/Tessellate-Imaging/

Monk_Object_Detection
Notebooks: https://github.com/Tessellate-Imaging/Monk_Object_Detection/tree/master/application_model_zoo

Dive Into Deep Learning
August 2020 and FREE version!!! D2L is the 987-page book that Amazon scientists have compiled over the past two years and has finally been completed... an interactive and ' open source book ' with code, math and discussions.

What makes this book unique is that it was created with Jupyter Notebook and with the idea of ′′ Learning with Practice "... that is, the book in its entirety consists of executable code with adaptations in PyTorch, TensorFlow and MXNet.

FREE PDF download:
https://d2l.ai/d2l-en.pdf

Download the book in 'notebook' format to read and execute locally:
https://d2l.ai/chapter_installation/index.html

Website:
https://d2l.ai

Github:
https://github.com/d2l-ai/d2l-en

Article:
https://www.amazon.science/latest-news/amazon-scientists-author-popular-deep-learning-book

Brian Huge, Antoine Savine :
https://arxiv.org/abs/2005.02347

TF1 implementation notebook on Colab: https://colab.research.google.com/github/differential-machine-learning/notebooks/blob/master/DifferentialML.ipynb

Organize the daily influx of ML content in meaningful ways without feeling overwhelmed,
By Goku Mohandas et al. :
https://madewithml.com/collections/

Here is a new, and free book on Machine Learning from scratch. It includes the math and code examples. Solid reference.

https://dafriedman97.github.io/mlbook/content/table_of_contents.html

And The list of Most Updated and Free Artificial Intelligence, Machine Learning, Data Science, Deep Learning, Mathematics, Python Programming Resources. (Last Update: Sept 9, 2020):

https://www.marktechpost.com/free-resources/?fbclid=IwAR0hc2qkxPMXhQGzsg07ffgFecRr01tSCRqlhb_XMR6PjPt1KNdy68cLy9w

NumPy provides an easily readable, expressive, high-level API for array programming. It takes care of the underlying mechanics that make operations fast.

AI based Rubik's Cube Solver using Flutter and Python

Binary Neural Network (BNN) is best feet for reducing the complexity of deep neural networks. But, it suffers severe performance degradation. Rotation based training leads to around 50% weight flips which maximize the information gain and showed state-of-the-arts in benchmark datasets
Rotated Binary Neural Network (RBNN)