Welcome to the “Laplace” reading group, a series of seminars and informal discussions organized by the CFM-ENS Chair “Modèles et Sciences des Données”.
In these meetings, researchers can give presentations about their current research interests or discuss interesting papers. As with the Data Science Colloquium, the goal is to initiate discussions between researchers from different fields that all have a common interest in large scale or high-dimensional data. You can check the list of the next seminars below and the list of past reading groups.
All are welcome to attend, feel free to propose topics that you would like to see discussed, or work that you would like to present (contact at the bottom).
May 18th, 2018, 11h-12h, room U/V, DMA, ENS (45 rue d'Ulm, basement).
Jonathan Dong (LKB)
Title: Scaling up Random Projections with multiple light scattering
Abstract: Random Projections have proven extremely useful in many signal processing and machine learning applications. However, they often require either to store a very large random matrix, or to use a different, structured matrix to reduce the computational and memory costs. We overcome this difficulty with an analog, optical device, that performs the random projections literally at the speed of light without having to store any matrix in memory. This is achieved using the physical properties of multiple coherent scattering of light in random media. These efficient optical random projections are used in two different settings: to generate Random Features for kernel approximation and to iterate an Echo-State Network (a Recurrent Neural Network with fixed internal weights). This new method is fast, power efficient and easily scalable to very large networks: we reach sizes that exceed the RAM memory limit.
If you want to subscribe to (or unsubscribe from) the mailing list please send a mail to Nicolas Keriven (ENS).