CSEP 546 Machine Learning Course Overview
This course, led by Geoff Hulten and TAs Alon Milchgrub and Andrew Wei, delves into important machine learning algorithms and model production techniques. Topics covered include logistic regression, feature engineering, decision trees, intelligent user experiences, computer vision basics, neural networks, reinforcement learning, and more. The course aims to equip students with the tools to create working machine learning systems and explore various intelligent architectures. Lectures cover a wide array of machine learning topics, providing a comprehensive understanding of the field.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
CSEP 546 Machine Learning Lecturer: Geoff Hulten TAs: Alon Milchgrub, Andrew Wei
Logistics Course website: https://courses.cs.washington.edu/courses/csep546/19au/ Canvas site: https://canvas.uw.edu/courses/1331659 Discussion board: http://piazza.com/washington/fall2019/csep546/home/
Introducing Myself Geoff Hulten ghulten@cs.washington.edu https://www.linkedin.com/in/geoff-hulten-58136a1/ What I ve worked on Why I m here
Introducing our TAs Alon Milchgrub alonmil@cs.washington.edu Andrew Wei nowei@cs.washington.edu Quick Intro Quick Intro Office hours: Tues: 5:30 6:30 CSE 674 Office Hours: Tues: 4:30 6:20 CSE 007 Virtual hours for people viewing from MS? Mail me.
Introducing the Class What types of jobs? Engineering? Data science? Management/PM? Other? Math? Not really? Can do? I think in math? Machine learning experience? This is my first class? Several classes / exploration? Do it for a living? Python? Never used? Some experience? No problem?
Overview of the Course 1) Learn important machine learning algorithms (the tools) 2) Learn how to produce models (use the tools) 3) Learn how to produce working systems (ML Engineering)
Lecture Overview Lecture 1 1 1 1 2 2 2 3 3 3 4 4 4 5 5 5 Topic Lecture 6 6 6 6 7 7 8 8 8 9 9 10 Topic Introduction Overview of machine learning Basics of Evaluating Models Logistic Regression Feature Engineering Na ve Bayes ROC Curves and Operating Points Implementing with Machine Learning Bounds and Comparing Models Defining Success with ML systems Decision Trees Intelligent User Experiences Design Pattern - Closed Loop Overfitting and Underfitting Design Pattern - Adversarial Ensembles 1 - Bagging & Random Forests Ensembles 2 - Stacking & Boosting Design Pattern - Corpus Based Basics of Computer Vision Clustering and Instance Based Neural Networks Approaching an ML Problem Neural Network Architectures Intelligence Architectures Intelligence Management Reinforcement Learning Orchestrating Intelligent Systems Design Pattern - Ranking Other Important Machine Learning Algorithms Review of the Course 10 10 Subject to change
Assignments Logistic Regression Feature Engineering (text) Decision Trees Ensembles (Random Forests) Clustering & Instance Based Feature Engineering (Vision) Neural Networks Reinforcement Learning Model building & interpreting And several Kaggle style competitions
Evaluation Assignments: Exam: There will be reading assignments every week (~10% of grade) and coding / modeling assignments most weeks (~40% of final grade) and three Kaggle style competitions (~25% of final grade). There will be an exam worth ~25% of the final grade (although you must score at least 50% on the exam to pass the course). Assignments due two weeks after they are assigned. Except (possibly) for the last assignment, which is due before the start of the final lecture (so we can submit final course grades in a timely fashion). This will be online and timed (2 3 hours). Tentatively scheduled for Dec 9th (complete it any time before midnight) Clarity of communication is critical in machine learning, so your answers must be concise and easy to follow. If the TA can t evaluate the answers in reasonable time they will have to give reduced credit. This exam will be based on the assignments, readings, and lectures.
The Textbooks and why All royalties to be donated
