Students from across Brown, including DSI Master’s students, CCMB/CNTR PhD students, and Data Fluency undergraduates, participated in this year’s two-day event held in Alumnae Hall.
Deep Learning Day(s) is an annual event hosted at the end of the CSCI 1470/2470: Deep Learning course where students present talks and posters on their end-of-semester projects, covering a wide range of deep learning techniques and applications. DSI/CCMB Professor Ritambhara Singh has been teaching CSCI 1470/2470 and putting on this expansive event since Spring 2022.
This year’s event gathered the 398 students in CSCI 1470/2470 into Brown’s Alumnae Hall over the span of two days (this year on May 6 and 7). Each day, the event hosted presentations and poster sessions in four categories:
- Computer Vision
- Language Processing
- Science and Health
- Art, Music, Fashion, Finance.
Capstone and graduate students (CSCI 2470) presented 10 minute talks on their projects, while undergraduate students (CSCI 1470) prepared research posters.
Photos (above) from the event feature presentations from DSI/CCMB/CNTR students.
CSCI 1470/2470: Deep Learning Course Description:
Over the past few years, Deep Learning has become a popular area, with deep neural network methods obtaining state-of-the-art results on applications in computer vision (Self-Driving Cars), natural language processing (Google Translate), and reinforcement learning (AlphaGo). These technologies are having transformative effects on our society, including some undesirable ones (e.g. deep fakes).
This course gives students a practical understanding of how Deep Learning works, how to implement neural networks, and how to apply them ethically. It introduces students to the core concepts of deep neural networks and surveys the techniques used to model complex processes within the contexts of computer vision and natural language processing.
This course emphasizes and requires students to think critically about potential ethical pitfalls that can result from mis-application of these powerful models. The course is taught using the Tensorflow deep learning framework