CSCI 335:
Machine Learning
RIT CS Department, Fall 2024 (Section 1)
Instructor: Prof. Zanibbi
RIT CS Department, Fall 2024 (Section 1)
Instructor: Prof. Zanibbi
In this final week, we will meet to plan for the final project, and review materials from the course.
This week of the holidays, we will take stock and discuss the final deliverables in the course.
This week we will discuss the course project, and start looking at sequence-to-sequence models (seq2seq).
This week we will discuss the course project, and start looking at sequence-to-sequence models (seq2seq).
This week we will continue our discussion of Recurrent Neural Networks (RNNs).
This week we will talk about Recurrent Neural Networks (RNNs).
This week we will talk about Recurrent Neural Networks (RNNs), and on Thursday the project proposal will be discussed. Your groups (v2) are defined in MyCourses (see the 'groups' link).
Reminder: Monday and Tuesday (Oct. 14 + 15) is the RIT October Break.
Heads-up: The course project will be assigned next week; Groups have been randomly assigned in MyCourses (see Groups link).
This week we will finish our introduction to convolutional neural networks.
Reminder: Next Monday and Tuesday (Oct. 14 + 15) is the RIT October Break.
Heads-up: The course project will be assigned in Wk 9 (the week after break). Groups have already been randomly assigned in MyCourses (see Groups link).
This week we continue our introduction to neural networks, and backpropagation.
This week we continue our introduction to neural networks, and backpropagation.
This week will review some neural network fundamentals, including loss functions, and the backpropagation technique used to tune network weights.
In Wk 4 we'll continue our discussion of Bayesian decision theory, and parametric probability models for Bayesian classification. Readings are the same as last week.
**The remaining lectures in the course will be in-person, with Zoom recordings.
This week we'll begin discussing Bayesian Decision Theory, which defines optimal classification using probability. Some review materials related to statistical pattern recognition and Bayesian Decision are provided in the readings.
**Tuesday and Thursday's lecture will be recorded. And provided through Zoom links in MyCourses.
This week we will continue to talk about classification and regression, and in particular linear classifiers, and nearest neighbor classifiers.
**Tuesday's lecture will be recorded. It will be provided (in two parts) through the Zoom link in MyCourses.
**Thursdays lecture will be in-person in SLA-2150 (Slaughter Building, Building 78)
Welcome to the Fall 2024 (Section 1) Machine Learning course web pages. These web pages will be used to communicate information about the course, along with news, deadlines, etc.
10 quizzes will be given out weekly beginning in Week 2 of the semester. The two lowest quiz grades will be dropped.
Quizzes will be available through a "Quizzes" link in MyCourses. Students are permitted to retake a quiz as many times as they like, and will receive the highest score that they receive across these attempts before the deadline. Students will have at least one day (24 hrs) to complete each quiz.
5 assignments will be given, with the first due in Week 3 of the semester.
Assignments involve both writing and programming questions. Students are expected to follow submission instructions as provided in the assignments carefully.
Instead of an exam, students will complete a group project at the end of the semester in groups of 3 students. The project involves designing, executing, and reporting on an experiment with a machine learning model.
The first deliverable for the project is an experiment design, and a draft of the final experiment report and materials to be delivered for the final project.
Instead of an exam, students will complete a group project at the end of the semester in groups of 3 students. The project involves designing, executing, and reporting on an experiment with a machine learning model.
The final deliverable for the project are the experimental results, code, and experiment report (15%), along with a short 5-10 minute presentation given during the exam slot (5%).