Time & Place. Tuesdays/Thursdays 12:30-13:45, Stanley Thomas 302.
Instructor. Parisa Kordjamshidi (Office hours: Stanley Thomas 305 B, Tu/Th 3:30-5:00pm).
Declarative Learning based Programming Workshop/Hackathon , October 9th 9:00am-16:00pm, Location: Gibson Hall, 414. For more information see here, open to every one interested, RSVP email@example.com.
Prof. Kurdia invites you to Git+Github practice session, Thursday, Oct. 6, and next Tuesday, Oct. 11, at 9:30 am-10:45 am, ST 302, open to every one interested.
Machine Learning with MATLAB, Oct. 19th, 4:00-6:00, Gibson Hall, Room 414 provided by MathWorks, open to every one interested, REGISTER.
This course is meant to provide an introduction to machine learning to undergraduate and graduate students. The current undergraduate participants have a coordinate major in computer science, in addition to a major in another discipline such as economics, linguistics, math, even philosophy and some other areas. The graduate participants study physics, linguistics, etc.
Given the popularity of applying intelligent systems mostly including machine learning techniques to a large variety of real world problems and application domains, the goal of this course is to help experts in various fields to understand, design, evaluate and use Machine Learning in their major field of expertise. This course has two parts which will be worked out in parallel. In one part of the course, we study a variety of learning algorithms and techniques that have proved successful in practical applications. We will discuss supervised and unsupervised techniques including decision trees, rule based learning, on-line learning, neural networks, support vector machines, probabilistic approaches and more as well as clustering techniques.
In the other part of the course, we study designing an end-to-end machine learning model when starting from raw data, working on preprocessing, extracting features, designing various model configurations, and evaluation. The students will get familiar with the declarative learning based programming paradigm. This part is mostly practical. The students will choose an application problem related to their major field of study, focus on one of the studied techniques and investigate it in depth. They will make a presentation about the problem and their solution, apply their selected technique and report their evaluation results. For implementing the application models, the students will use an existing prototype language for this paradigm called Saul (GitHub), (short poster video) 1.
The set up of the course is new and hence experimental, some parts of the material as well as the evaluation might change when we proceed during the semester. Your feedback is always very welcome.
 This video was recorded at the Computing Community Consortium (CCC)
Symposium on Computing Research in May 2016, which was supported by NSF
grant 1019343. Any opinions, findings, and conclusions or
recommendations expressed in this video are those of the authors and do
not necessarily reflect the views of the National Science Foundation.