Introduction to Unsupervised, Deep and Reinforcement Learning

Nội dung khóa học

What You'll Learn:

Describe the main classes of clustering techniques

Implement k-means and hierarchical clustering

Motivate the need and choice of dimensionality reduction techniques

Implement Principal Component Analysis (PCA) for feature extraction

Explain how deep neural networks work and their advantages

Train deep neural networks for classification and regression tasks

Explain the basic concepts and techniques of reinforcement learning

Describe how reinforcement learning could be applied in real world applications

Thông tin khác

Course Syllabus:

Topic 1: Introduction
This is an introduction to the course with an overview of the topics.

Topic 2: Clustering
Clustering techniques are used to identify similar data/objects and patterns from your engineering datasets.
You will learn about the problem of clustering, the main classes of clustering techniques and how we can implement k-means and hierarchical clustering.

Introduction to clustering

Formalizing the problem of clustering

Similarity and dissimilarity measures

k-means clustering

Hierarchical clustering

Topic 3: Dimensionality Reduction
Dimensionality reduction techniques are used to reduce the number of features representing a given dataset, while retaining the structure of the dataset as much as possible.
You will learn what dimensionality reduction is, why it is needed and how to use it. You will learn about Principal Component Analysis dimensionality reduction technique and how and when to apply it.

What is dimensionality reduction?

Why dimensionality reduction techniques are used

Feature selection vs. feature extraction techniques

Principal component analysis feature-extraction technique

Topic 4: Introduction to Deep Learning
Deep learning is a broader family of machine learning methods based on artificial neural networks.
You will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about fully connected neural networks, some theoretical aspects of deep learning, the back-propagation algorithm, Adam, and much more.

What neural networks are

Architecture of fully connected neural networks

Capabilities of neural networks

The benefits of deep architectures

Training deep neural networks with stochastic gradient descent and Adam

Topic 5: Introduction to Reinforcement Learning
Reinforcement learning teaches an AI to interact with an environment.
You will be introduced to basic reinforcement learning concepts and techniques, and how they could be applied in real world applications.

How an AI interacts with the environment

The formalization of this as a Markov Decision Process

An agent’s behavior as a policy

The optimal policy found using tabular Q-learning

Why tabular reinforcement learning does not scale well

Neural networks for deep reinforcement learning to scale up to interesting applications

Course License: CC BY-NC-SA 4.0

Course uses content from TU Delft (https://www.tudelft.nl/)

Chương trình học

Các thông báo

0.1.1 Welcome to Unsupervised, Deep and Reinforcement Learning

0.1.2 Video Introduction

0.1.3 Meet Your Teachers

1.1.1 Overview

1.1.2 Why use Machine Learning?

1.1.3 Machine Learning Basics and Terminology

1.1.4 The biggest challenge with Machine Learning and Frameworks

1.2.1 Predicting the number of sales with regression

1.2.2 What is a “good” regression model? MSE, MAE

1.3.1 Terminology and Basics

1.4.1 Want to learn more?

2.1.1 Welcome

2.1.2 Meet your Teachers

2.1.3 Video: Introduction to Clustering

2.1.4 Video: Similarity and Dissimilarity

2.2.1 Overview

2.2.2 Video: Formalizing the problem of clustering

2.2.3 Video: Clustering based on centroid and density

2.2.4 Video: Clustering based on distribution and connectivity

2.3.1 Overview

2.3.2 Video: K-Means Clustering

2.3.3 Reading material and interactive demos

2.4.1 Overview

2.4.2 Video: Hierarchical clustering

2.5.1 Overview

2.5.2 Video: Wrap up clustering

3.1.1 Welcome

3.1.2 Meet your Teacher

3.1.3 Video: Dimensionality Reduction

3.1.4 Video: Feature Selection vs Feature Extraction

3.2.1 Overview

3.2.2 Video: Principal Component Analysis (PCA)

3.2.3 Video: Principal Component Analysis Mathematically

3.2.4 Video: Dimension Reduction and Variance Coverage

4.1.1 Welcome

4.1.2 Meet your teacher

4.1.3 Video: Introduction to Neural Networks

4.1.4 Video: From the Perceptron to Deep Neural Networks

4.2.1 Overview

4.2.2 Video: Neural Networks are Universal Approximators

4.3.1 Overview

4.3.2 Video: Backpropagation Algorithm

4.3.3 Video: Stochastic Gradient Descent

4.3.4 Video: Stochastic Gradient Descent with Momentum

4.3.5 Video: Adam Optimization Algorithm

5.1.1 Welcome

5.1.2 Meet your teacher

5.1.3 Recommended Reading

5.1.4 Video: Learning to Interact

5.2.1 Overview

5.2.2 Video: Tabular Q-Learning

5.3.1 Overview

5.3.2 Video: Deep Reinforcement Learning

6.1.1 See you again!

6.1.2 Other online courses

Chứng chỉ hoàn thành khóa học

Xem Thêm

Các thông báo

0 phút

Các thông tin phổ biến và các thông báo

Nội dung khóa học

What You'll Learn:

Kỹ năng đạt được

Thông tin khác

Course Syllabus:

Chương trình học

Khóa học liên quan