Free MIT Courses and book on Calculus: The Key to Understanding Deep Learning

Course: https://ocw.mit.edu/resources/res-18-005-highlights-of-calculus-spring-2010/

@ai_machinelearning_big_data

How Gödel’s Proof Works

His incompleteness theorems destroyed the search for a mathematical theory of everything. Nearly a century later, we’re still coming to grips with the consequences.

Every mathematical system will have some statements that can never be proved.

Read article here

AN AMAZING PYTHON DJANGO PROJECT
Time to Master the Art of Web Development 🔥✅💯🔝



https://data-flair.training/blogs/django-project-news-aggregator-app/

DeText: A Deep Neural Text Understanding Framework

DeText can be applied to many tasks, including search & recommendation ranking, multi-class classification and query understanding tasks.

Github: https://github.com/linkedin/detext

Paper: https://arxiv.org/abs/2008.02460v1

@ai_machinelearning_big_data

📗 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

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

AN AMAZING COMPUTER VISION PROJECT
A sneak peek into the self-driven cars 🔥🔝💯✅



https://data-flair.training/blogs/road-lane-line-detection/

DeepMind's Traffic Prediction with Advanced Graph Neural Networks

A new blog post by DeepMind has been released recently that describes how you can apply GNN for travel time predictions. There are not many details about the model itself (which makes me wonder if deep net trained across all supersegments would suffice), but there are curious details about training.

1. As the road network is huge I suppose, they use sampling sampling of subgraphs in proportion to traffic density. This should be similar to GraphSAGE-like approaches.

2. Sampled subgraphs can vary a lot in a single batch. So they use RL to select subgraph properly. I guess it's some form of imitation learning that selects graphs in a batch based on some objective value.

3. They use MetaGradients algorithm to select a learning rate, which was previously used to parametrize returns in RL. I guess it parametrizes learning rate instead in this blog post.