Fall 2023
INF 385T Special Topics in Information Science: Deep Learning and Multimodal Systems
DESCRIPTION
Recently Deep Learning (DL) techniques have shown a lot of promise for tasks in various modalities such as speech, language, and vision and DL has become a go-to machine learning paradigm for Artificial Intelligence (AI) based applications. The course aims to cover theoretical and applied aspects of Deep Learning and how it is used to solve real-world problems. Classes in each week may be divided into two segments: (a) Theory and Methods, a concise description of a deep learning algorithm, and (b) Lab Tutorial, a hands-on session on applying the algorithm on multimodal real world data such as textual, visual and audio data.
COURSE NOTES
Deep Learning (DL) is a subfield of machine learning (ML) that is based on artificial neural networks (ANNs) with multiple layers (hence, “deep”), which are designed to perform complex tasks. Unlike traditional ML, deep learners leverage huge amounts of labeled data and powerful computing resources to learn and improve over time, so much so that they can perform tasks in computer vision, speech recognition, and natural language processing with similar accuracies as humans. DL, as a field, has tremendously grown in the last five years or so and has already had a significant impact on many areas of AI, making it a valuable skill to have and an exciting area of research and development. The proposed graduate-level course aims to cover theoretical and applied aspects of Deep Learning and how it is used to solve real-world problems. Classes in each week may be divided into two segments: (a) Theory and Methods, a concise description of a deep learning algorithm, and (b) Lab Tutorial, a hands-on session on applying the algorithm on multimodal real world data such as textual, visual and audio data
PREREQUISITES
Graduate standing.
RESTRICTIONS
Restricted to graduate students in the School of Information through registration periods 1 and 2. Outside students will be permitted to join our waitlists beginning with registration period 3.