Monthly Machine Learning Course Recommendation

As a practicing data scientist and machine learning educator, I’m always taking courses. Suppose you want to go directly to applications, learn the most current software and get a job. In that case, I recommend my IBM Data Science Professional Certificate or IBM Machine Learning Professional Certificate.

This month’s course is Deep Learning at VU University Amsterdam. The slides break down complex topics into simple diagrams with lots of explanations. The course has several instructors, each one focusing on their specialty here is a list:

Instructors

Jakub M. Tomczak

Peter Bloem

Michael Cochez

David Romero

Emile van Krieken

Table of Content

1. 1.0 Introduction
   1. 1.0 Course Introduction
   2. 1.2: A quick intro to AI
   3. 1.3: Probabilistic learning
   4. 1.4: From logistic regression to fully-connected networks
2. 2.0 Neural Networks
   1. Lecture 2.1: A Review of Neural Networks 
   2. Lecture 2.2: Backpropagation, scalar perspective
   3. Lecture 2.3: Backpropagation
   4. Lecture 2.4: Automatic Differentiation 
3. 3.0 : Convolutional Neural Networks 
   1. 3.1: Convolutional Neural Networks – Introduction
   2. 3.2a: 1-Dimensional Convolutional Neural Networks: getting started
   3. 3.2b: 1-Dimensional Convolutional Neural Networks – formalism and solving issues
   4. 3.3: Two-Dimensional Convolutional Neural Networks
   5. 3.4 : An Example of a real-world convolutional neural network: AlexNet
4. 4.0 Tools of the trade
   1. 4.1 General Deep Learning practice
   2. 4.2 Why does deep Learning work? 
   3. 4.3 Optimizers
   4. 4.4 The Bag of Tricks
5. 5.0 Sequential Data
   1. 5.1 Sequence Models
   2. 5.2 Recurrent Neural Networks
   3. 5.3 Long Short-Term Memory
   4. 5.4 – CNNs for Sequential Data
   5. 5.5 ELMo, Word2Vec
6. 6.0 Latent Variable Models (pPCA and VAE)
   1.  6.1: Introduction to Deep Generative Modeling
   2. 6.2: Probabilistic PCA
   3. 6.3: Variational Auto-Encoders
7. 7.0 Generative AdversarialNetwork
   1. Lecture 7.1 Implicit models: Density Networks
   2. Lecture 7.2 Implicit models: GANs
8. 8.0 Learning with Graphs
   1. Lecture 8.1a: Introduction – Graphs
   2. Lecture 8.1b: Introduction – Embeddings
   3. Lecture 8.2: Graph and node embedding
   4. 8.3: Graph Neural Networks
   5. Lecture 8.4: Application – query embedding
9. 9.0 Reinforcement Learning
   1. 9.1: Introduction to Reinforcement Learning
   2. 9.2: The REINFORCE algorithm
   3. 9.3: Gradient Estimation
10. 10 More or Generative Modding
    1. Lecture 10.1: ARM & Flows
    2. 10.2: ARM & Flows
    3. 10.3: ARM & Flows
11. Q-Learning
    1. 11.1: Deep Q-Learning
    2. 11.2: Variance Reduction for Policy Gradient (Actor-Critic)
    3. 11.3: World Models
12. Transformers
    1. 12.1 Self-attention
    2. 12.2 Transformers
    3. 12.3 Famous transformers (BERT, GPT-2, GPT-3)

1.0 Introduction

Course Introduction and a primer on probability

1.0 Course Introduction

1.2: A quick intro to AI

1.3: Probabilistic learning

1.4: From logistic regression to fully-connected networks

Slides for videos are herr

2.0 Neural Networks

An introduction to Neural Networks and how to train them.

Lecture 2.1: A Review of Neural Networks 

Lecture 2.2: Backpropagation, scalar perspective

Lecture 2.3: Backpropagation

Lecture 2.4: Automatic Differentiation 

3.0 : Convolutional Neural Networks 

An introduction to Convolutional Neural Networks \.

3.1: Convolutional Neural Networks – Introduction

3.2a: 1-Dimensional Convolutional Neural Networks: getting started

3.2b: 1-Dimensional Convolutional Neural Networks – formalism and solving issues

3.3: Two-Dimensional Convolutional Neural Networks

3.4 : An Example of a real-world convolutional neural network: AlexNet

4.0 Tools of the trade

Tips and tricks to train Neural Networks

4.1 General Deep Learning practice

4.2 Why does deep Learning work? 

4.3 Optimizers

4.4 The Bag of Tricks

Slides for videos here

5.0 Sequential Data

An introduction to Sequential Data like natural languish processing

5.1 Sequence Models

5.2 Recurrent Neural Networks

5.3 Long Short-Term Memory

5.4 – CNNs for Sequential Data

5.5 ELMo, Word2Vec

slides for videos

6.0 Latent Variable Models (pPCA and VAE)

Generative modelling is used to create data like images.

 6.1: Introduction to Deep Generative Modeling

6.2: Probabilistic PCA

6.3: Variational Auto-Encoders

slides for videos

7.0 Generative AdversarialNetwork

A popular method used for generative modelling

Lecture 7.1 Implicit models: Density Networks

Lecture 7.2 Implicit models: GANs

slides for videos

8.0 Learning with Graphs

Graphs a powerful tool in deep learning

Lecture 8.1a: Introduction – Graphs

Lecture 8.1b: Introduction – Embeddings

Lecture 8.2: Graph and node embedding

8.3: Graph Neural Networks

Lecture 8.4: Application – query embedding

9.0 Reinforcement Learning

How computers learn to do complex sequential tasks like playing games

9.1: Introduction to Reinforcement Learning

9.2: The REINFORCE algorithm

9.3: Gradient Estimation

10 More or Generative Modding

Different types of Generative Modding.

Lecture 10.1: ARM & Flows

10.2: ARM & Flows

10.3: ARM & Flows

Q-Learning

A better method of Reinforcement Learning

11.1: Deep Q-Learning

11.2: Variance Reduction for Policy Gradient (Actor-Critic)

11.3: World Models

Transformers

A new powerful neural network architecture that was originally used in natural languish processing , but is now used everywhere

12.1 Self-attention

12.2 Transformers

12.3 Famous transformers (BERT, GPT-2, GPT-3)