ECS 111: Applied Machine Learning for Non-Majors

ECS 111
Applied Machine Learning for Non-Majors
Effective Term
2023 Fall Quarter
Learning Activities
Lecture: 3 hours
Discussion: 1 hour
Machine learning methods and their application. Theory, design and evaluation of supervised/unsupervised machine learning algorithms. Practical use of matching learning methods and their challenges. No credit if student has taken ECS 171; not intended for Computer Science and Computer Science Engineering Majors. GE: SE.
(ECS 032B or ECS 036C); (MAT 135A or STA 035C)
Credit Limitation
No credit if student has taken ECS 171; not intended for Computer Science and Computer Science Engineering Majors.
Enrollment Restrictions
Pass One restricted to Data Science majors; Pass Two restricted to undergraduates.

Summary of Course Content
An introduction to preliminaries of machine learning methods, their theory and applications. This course focuses on the challenges of applying machine learning solutions to problems in several popular domains, such as object recognition, real-estate housing price prediction, computer security, mobile health, and cloud resource management. Students will explore the application and practical aspects of supervised learning, unsupervised learning, reinforcement learning, and deep learning applied to various problems such as sequence classification, image classification, and time-series prediction. Through hands-on projects and examples as well as programming assignments, students practice the implementation aspect of developing machine learning solutions using various libraries and tools for information visualization, such as matplotlib, Bokeh, leather. Furthermore, students exercise incorporating important Python packages such as scikit learn, tensorflow and keras in-depth.   

  1. Exploratory Data Analysis and Visualization

  2. Supervised learning

    1. Regression

    2. Support Vector Machines

    3. Naive Bayes Classifiers

    4. K-Nearest Neighbors

    5. Artificial Neural Networks

    6. Ensemble Learning 

  3. Unsupervised learning

    1. Clustering (K-means, Fuzzy C-means, hierarchical)

    2. Dimensionality reduction methods (t-SNE, PCA)

  4. Deep Learning

    1. Types of neurons and learning single neurons

    2. Learning networks of neurons

    3. Classic network structures

      1. Auto-encoder

      2. Convolutional Neural Networks

      3. Generative Neural Networks

      4. Generative Adversarial Networks

  5. Evaluation Metrics

  6. ML applications

    1. Real-Estate Housing Price Prediction

    2. Image understanding and object detection

    3. Computer Security

    4. Mobile Health

    5. Cloud Resource Management

  7. Ethics in Machine Learning

Students will (1) Acquire fundamental knowledge of learning theory; (2) Learn how to design and evaluate supervised and unsupervised machine learning algorithms; (3) Understand the challenges related to application of ML in different domains; and (4) Learn how to use machine learning methods for multivariate data analysis in various scientific field domains.

Illustrative Reading
Setareh Rafatirad, Houman Homayoun, Zhiqian Chen, and Sai Manoj Pudukotai Dinakarrao, Machine Learning for Computer Scientists and Data Analysts, From Applied Perspective, Springer,  ISBN 978-3-030-96756-7

Potential Course Overlap
Course overlaps with  ECS 171  in terms of machine learning techniques, which are used for deeper understanding of data through predictive analysis and building insightful models to discover the meaning of data. Course has minimal overlap with ECS 170 in terms of AI.

Final Exam
Yes Final Exam

Course Category