Unsupervised Learning, Recommenders, Reinforcement Learning Free Course For Beginners

Introduction

Unsupervised Learning, Recommenders, Reinforcement Learning is a beginner-friendly course; however, the student is encouraged to have some fundamental understanding of machine learning and its limitations. The students will learn about using unsupervised learning techniques for anomaly detection and clustering. The participants will also get to know about the deep reinforcement learning model and build recommender systems with a collaborative filtering approach. By the end of the course, the students will get to apply all the fundamental concepts of machine learning in the real world. This course does not just limit the student to some overview and key concepts but also offers hands-on experience in the field of machine learning and AI.

What Will You Gain From This Course?

By the end of this course, the students will be able to:

1. Define different unsupervised learning techniques and put these techniques to use in real life.
2. Utilize techniques like clustering and anomaly detection for unsupervised learning.
3. Establish a recommender system along with some advanced approaches like filtering.
4. Design recommender systems that utilize machine learning concepts for a content-based deep learning process.
5. Build a deep reinforcement learning model in real life.
6. Learn about different tools and techniques used in machine learning in general and unsupervised learning in specific.

Skills Acquired:

1. Anomaly Detection
2. Clustering
3. Unsupervised Learning
4. Reinforcement Learning
5. Recommender Systems
6. Collaborative Filtering

Who Can Benefit From This Course?

This online learning program is designed for:

1. AI engineers working with advanced machine learning.
2. Aspirants in machine learning who want to learn more about different techniques and methods used within machine learning.
3. Seasoned engineers within the IT industry who are getting familiar with new concepts in AI for better opportunities.
4. Fresh graduates in the IT industry who want to start a career in machine learning.
5. AI experts who are looking for ways to put advanced machine-learning models to use.
6. IT Professionals struggling with advanced machine-learning concepts, including unsupervised learning and reinforcement learning.

Course Content

46 Videos – 4 Readings - 8 Quizzes – 5 Programming Assignments - 2 Ungraded Lab – Certificate of Completion

Unsupervised Learning

The first module in this course focuses on two main concepts, i.e., clustering and anomaly detection within unsupervised learning. The module starts with a basic introduction to clustering and then gets to the anomaly detection algorithm. Some of the key concepts within this module include clustering, K-means intuition, K-means algorithm, optimization objective, initializing k-means, choosing the number of clusters, finding unusual events, gaussian (normal) distribution, anomaly detection algorithm, developing and evaluating an anomaly detection system and anomaly detection vs. supervised learning.

By the end of the course, there are two assignments for hands-on experience. These assessments help the student put two key concepts in this module, i.e., k-means and anomaly detection, to use. There are two quizzes within the module for assessing the student's knowledge of clustering and anomaly detection.

1. 13 Videos
2. 1 Reading
3. 2 Quizzes
4. 2 Programming Assignments

Recommender System

The second module focuses on a recommender system that mainly utilizes big data to recommend additional products and services to consumers. The students will also be able to choose different criteria for these recommendations.

Some of the concepts covered within this module include using per-item features, collaborative filtering algorithm, binary labels: favs, likes, and clicks, mean normalization, TensorFlow implementation of collaborative filtering, finding related items, collaborative filtering vs content-based filtering, deep learning for content-based filtering, recommending from a large catalog, ethical use of recommender systems and TensorFlow implementation of content-based filtering.

This module also contains three optional concepts: reducing the number of features, the PCA algorithm, and PCA in code. A section dedicated to knowledge assessment ensures that students develop an understanding beyond theory. Moreover, an assignment section offers hands-on experience with a focus on collaborative filtering recommendation systems and deep learning for content-based filtering.

1. 15 Videos
2. 3 Quizzes
3. 2 Programming Assignments
4. 1 Ungraded Lab

Reinforcement Learning

This is the third and last module of this online training program. This module focuses on reinforcement learning within machine learning. For a better understanding, the module also covers this concept with some real-life examples.

Some key concepts in this course include reinforcement learning with the Mars rover example, return in reinforcement learning, decision-making with policies in reinforcement learning, state-action value function definition with an example, bellman equation, lunar lander, and more.

There is also a lesson dedicated to Andrew Ng and Chelsea Finn on AI and Robotics, as well as some optional lessons on random (stochastic) environments, algorithm refinement: mini-batch, and soft updates. By the end of the course, there is an assignment on reinforcement learning so the students can put reinforcement learning to use.

1. 18 Videos
2. 3 Readings
3. 3 Quizzes
4. 1 Programming Assignment
5. 1 Ungraded Lab

Description

This course is part of the machine learning specialization, so it encourages learners to have some basic understanding of machine learning. It covers three main topics: unsupervised Learning, Recommenders, and Reinforcement Learning.

It is a beginner-friendly course that explores some fundamental concepts of machine learning along with different algorithms, frameworks, and techniques that are commonly used. Moreover, the students will understand how to utilize these concepts in real life.

The course focuses on unsupervised learning and concepts like clustering, dimensionality reduction, and recommender systems. By the end of this course, the student is expected to have enough understanding of unsupervised learning to build a project. Moreover, after completing this specialization, the students can get an entry-level job in AI and build a career in machine learning.

Meet the Instructor

Andrew Ng – Instructor - Stanford University- DeepLearning.AI

This course is a joint venture of Stanford University, DeepLearning.AI, and Coursera. Andrew Ng is the head of DeepLearning.AI and co-founder of Coursera. Previously, he worked as a chief scientist at Baidu and as a founding lead of the Google Brain team. He is currently working as an Adjunct Professor at Stanford University and as a General Partner at AI Fund. With his vision and exceptional expertise in machine learning and online education, he has actively contributed to multiple AI-based projects globally. Apart from his work, he is also a researcher and co-author. He has worked on more than 100 research papers in machine learning, robotics, and related fields. Currently, Andrew is focusing on entrepreneurial ventures to boost the role of AI in industry and the global economy.