IC Colloquium : Understanding and simplifying deep learning
Event details
Date | 30.03.2017 |
Hour | 10:15 › 11:30 |
Location | |
Category | Conferences - Seminars |
By : Armand Joulin - Facebook Artificial Intelligence Research
IC Faculty candidate
Abstract :
Recently, deep learning has been very successful in many applications. However these approaches are often computationally expensive and do not scale to the tremendous amount of data available nowadays. It also often works as a black box making its results hard to interpret for the practitioner. In this talk, I will discuss some of the recent efforts in understanding the performance and limitations of deep learning based methods as well as how this insight can help to design simpler and faster solution to challenging problems.
Bio :
Armand is a research scientist in the Facebook AI Research lab. Prior to this position, he was a postdoctoral fellow at Stanford University working with Fei-Fei Li and Daphne Koller. He did his PhD in INRIA and Ecole Normale Superieure, under the supervision of Francis Bach and Jean Ponce. He did his undergrad at Ecole Polytechnique. His subjects of interest are machine learning, computer vision and natural language processing.
More information
IC Faculty candidate
Abstract :
Recently, deep learning has been very successful in many applications. However these approaches are often computationally expensive and do not scale to the tremendous amount of data available nowadays. It also often works as a black box making its results hard to interpret for the practitioner. In this talk, I will discuss some of the recent efforts in understanding the performance and limitations of deep learning based methods as well as how this insight can help to design simpler and faster solution to challenging problems.
Bio :
Armand is a research scientist in the Facebook AI Research lab. Prior to this position, he was a postdoctoral fellow at Stanford University working with Fei-Fei Li and Daphne Koller. He did his PhD in INRIA and Ecole Normale Superieure, under the supervision of Francis Bach and Jean Ponce. He did his undergrad at Ecole Polytechnique. His subjects of interest are machine learning, computer vision and natural language processing.
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host : Pascal Fua