CSCI 3345 Machine Learning
This course provides an introduction to the field of machine learning. Specific learning paradigms to be covered include decision trees, neural networks, genetic algorithms, probabilistic models, and instance-based learning. General concepts include supervised and unsupervised adaptation, inductive bias, generalization, and fundamental tradeoffs. Applications to areas such as human-machine interaction, machine vision, bioinformatics, and computational science will be discussed.
Course overview
- Department
- Computer Science
- School
- MCAS
- Credits
- 3
- Level
- Undergraduate
- Offered
- Every Fall
Catalog details
- Prerequisites
- CSCI2244 or MATH4426 and CSCI1102
Requirements fulfilled
- Computer Science B.A.: CSCI 2000-level-or-higher elective (Current University Catalog; students should confirm their catalog year)
- Computer Science B.A.: CSCI 3000-level-or-higher elective (Current University Catalog; students should confirm their catalog year)
- Computer Science B.S.: CSCI 3000-level-or-higher elective (Current University Catalog; students should confirm their catalog year)
- Neuroscience B.S.: Electives (18 Credits, excluding laboratory credits) — named courses (Current University Catalog; students should confirm their catalog year)
- Mathematics B.S.: Natural science, computer science, or economics corequisites (Current University Catalog; students should confirm their catalog year)
Official evaluation summary
3.47 / 5
Data freshness
Instructors
Sections
- Section 01