Simon Kornblith | Understanding neural networks from a representational perspective: effects of width and depth
Guest Lecture
- Date: Jul 19, 2021
- Time: 04:00 PM - 05:00 PM (Local Time Germany)
- Speaker: Simon Kornblith
- Research scientist, Google, Mountain View, California, USA
- Location: MPI for Human Cognitive and Brain Sciences
- Room: Zoom Meeting
- Host: CBS CoCoNUT
Deep learning involves complex interactions between data, architecture, and training objectives. In this talk, I will present work toward understanding these interactions through the lens of neural network representations. I will first introduce the challenges of measuring similarity between neural network representations. I will then discuss the use of centered kernel alignment (CKA) as a similarity index between representations, and show that it addresses these challenges. Finally, I will describe our recent work applying CKA and other tools to understand how neural network representations change as networks become wider or deeper.
Meeting ID: 961 0650 8785