Japan Store
Applied Machine Learning
Course Description
In the past decade, we have observed the expeditious evolution and tremendous application of machine learning, such as unmanned vehicles, autonomous language translation, and smart healthcare. This course will introduce the fundamental knowledge of machine learning techniques via a series of hands-on real-world examples in Python. The aim is to provide the students with a good understanding of machine-learning technologies, build machine learning with Python, and apply machine-learning technologies to address real-world problems. In the course projects, students will also have an opportunity to explore cutting-edge machine-learning technologies and develop their machine-learning-based solutions.
Learning Outcomes
At the end of this course, you should be able to:
- Explain the relationship (math mechanisms, internal logic, computing, components, and the usage constraints) of 8 machine learning models (Linear Regression, Logistic Regression, Fully-Connected Neural Network (FCNN), Convolutional Neural Network (CNN), Recurrent Neural Network (Rnn), Autoencoder, general Adversarial Network (GAN), and Reinforcement Learning (RL)).
- Describe the common operations in developing machine learning applications.
- Apply machine learning for manufacturing analytics.
Throughout the course, learners can practice what they learned with a hands-on practice activity (ungraded). In the activities, the learners till be asked to program machine learning models with Python via the online platform https://colab.research.google.com/ A tutorial on how to use the online platform has been provided. Another tutorial demonstrating how to program a linear regression model has also been provided to enable an easier start for the learners. These activities are ungraded and will not count toward your grade. An example solution will be provided that demonstrates the correct programming.
|
Module |
Topic & Readings |
|
1 |
What is Machine Learning What is the Insight of Machine Learning |
|
2 |
Linear Regression Application Linear Regression Implementation |
|
3 |
Logistic Regression Formulation and Implementation Solving the Robust Regression Problem |
|
4 |
Introduction of Neural Networks Application Fully Connected Neural Network Implementation |
|
5 |
Convolutional Neural Network Application Convolutional Neural Network Implementation |
|
6 |
Recurrent Neural Network Application Recurrent Neural Network Implementation |
|
7 |
Auto-Encoder Application and Implementation Generative Adversarial Network Application and Implementation Deep Reinforcement Learning Models Application and Implementation |
Course Schedule and Duration
Below is the course schedule. It is recommended that you work through one module per week. The entire course is estimated to take 15 hours to complete. Upon submitting the four module knowledge checks with an 80% completion score, learners will be awarded a course completion certificate. The certificate is delivered within the Awards tool in the Brightspace course. *Schedule and assignments are subject to change. Any changes will be posted in Brightspace.
This product has no reviews yet.