Free Resources For Machine Learning
Written by Nikos Vaggalis   
Monday, 06 September 2021

A browser extension and two free courses, "Machine Learning with Graphs" from Stanford and "Introduction to Deep Learning" by Sebastian Raschka are three excellent resources for mastering Machine Learning.

When going through research papers, on arXiv or otherwise, most of the time you have to go through hoops to get to the accompanying source code. CatalyzeX is browser extension, available for Chrome and Firefox, that does that for you.

After enabling it,when searching through Google or visiting arXiv or Google Scholar, you'll see CODE in small letters next to the title of paper; clicking on it takes you to the code, mostly on Github.

When the code is not available, you see  "Request code" which brings up a page with two options: Request code directly from the authors or Get an expert to implement this paper.

The extension's official site is also a great hub for finding research papers. Have a look.

Our next resource is a free course from Stanford - "Machine Learning with Graphs" using PyTorch and NetworkX. Course in this context means all the material, exercises and videos for free for anyone and not that someone can enroll.

The course focuses on the underlying graph structure and its features together with machine learning techniques and data mining tools in order to reveal insights on a variety of networks.

But what can you do by combining Graphs with ML? You can enhance the graphs' utility by finding patterns that a human would not discern as well as achieving better accuracy. By mixing in Neural Networks, you feed the network with graphs and at the other end you get predictions. With that you can build recommendation systems, predict disease outbreak, do social network analysis and much more.

The syllabus is :

  • Introduction; Machine Learning for Graphs
  • Traditional Methods for ML on Graphs
  • Node Embeddings
  • Link Analysis: PageRank
  • Label Propagation for Node Classification
  • Graph Neural Networks 1: GNN Model
  • Graph Neural Networks 2: Design Space
  • Applications of Graph Neural Networks
  • Theory of Graph Neural Networks
  • Knowledge Graph Embeddings
  • Reasoning over Knowledge Graphs
  • Frequent Subgraph Mining with GNNs
  • Community Structure in Networks
  • Traditional Generative Models for Graphs
  • Deep Generative Models for Graphs
  • Advanced Topics on GNNs
  • Scaling Up GNNs
  • Guest Lecture: GNNs for Computational Biology
  • Guest Lecture: Industrial Applications of GNNs
  • GNNs for Science

The last resource is a great collection of deep learning materials using Pytorch, from Sebastian Raschka assistant Professor of Statistics at the University of Wisconsin-Madison and author of Python Machine Learning, included in AI Books To Inspire You, which focuses on deep learning and machine learning research. The material was taught this Spring at his STAT 453 - "Introduction to Deep Learning and Generative Models".

The syllabus consists of a total of 170 videos in the following topics:

Part 1: Introduction

L01: Introduction to deep learning
L02: The brief history of deep learning
L03: Single-layer neural networks: The perceptron algorithm

Part 2: Mathematical and computational foundations

L04: Linear algebra and calculus for deep learning
L05: Parameter optimization with gradient descent
L06: Automatic differentiation with PyTorch
L07: Cluster and cloud computing resources

Part 3: Introduction to neural networks

L08: Multinomial logistic regression / Softmax regression
L09: Multilayer perceptrons and backpropration
L10: Regularization to avoid overfitting
L11: Input normalization and weight initialization
L12: Learning rates and advanced optimization algorithms

Part 4: Deep learning for computer vision and language modeling

L13: Introduction to convolutional neural networks
L14: Convolutional neural networks architectures
L15: Introduction to recurrent neural networks

Part 5: Deep generative models

L16: Autoencoders
L17: Variational autoencoders
L18: Introduction to generative adversarial networks
L19: Self-attention and transformer networks

In contrast to "Machine Learning with Graphs", this is an introductory course targeting beginners and a real goldmine. Using Python and Pytorch makes it already worthwhile, but the amount of the material, abundance of topics, Sebastian's attention to detail and his presentation makes it a top offering. And for free too.



More Information

CatalyzeX Chrome extension 

CatalyzeX the Firefox extension

Machine Learning with Graphs-main

Machine Learning with Graphs-YouTube playlist

Introduction to Deep Learning and Generative Models-main

Introduction to Deep Learning and Generative Models-Lecture notes

Related Articles

AI Books To Inspire You

Microsoft's Machine Learning for Beginners

Program Deep Learning on the GPU with Triton

GAN Theft Auto - The Neural Network Is The Game

Yann LeCun’s Deep Learning Course Free From NYU



To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.


Meet Ambidex and Rookie From NAVER

Robots may not be ready yet for the great takeover of jobs that some people fear, but in South Korea, where there are 1,000 robots per 10,000 workers, service robots are finding a role. 

Microsoft And GitHub Announce Copilot Extensions At Build 2024

Microsoft's Build conference is underway with lots of announcements about Copilot, Microsoft's AI companion software.

More News

C book



or email your comment to:



Last Updated ( Monday, 06 September 2021 )