3rd IML Machine Learning Workshop

Session

Industry talks and panel

Apr 15, 2019, 2:00 PM

500/1-001 - Main Auditorium (CERN)

Conveners

Industry talks and panel

• David Rousseau (LAL-Orsay, FR)
• Markus Stoye (CERN)

10. Introduction

Markus Stoye (CERN)

4/15/19, 2:00 PM

9. Amazon AI: Tensor and Higher-Order Generalizations of the GSVD with Applications to Personalized Cancer Medicine

Dr Priya Ponnapalli (Amazon AI)

4/15/19, 2:20 PM

The number of high-dimensional datasets recording multiple aspects of interrelated phenomena is increasing in many areas, from medicine to finance. This drives the need for mathematical frameworks that can simultaneously identify the similar and dissimilar among multiple matrices and tensors, and thus create a single coherent model from the multiple datasets. The generalized singular value...

11. Google DeepMind: Compressing neural networks

Dr Tim Genewein (DeepMind)

4/15/19, 3:05 PM

Empirically it has been observed numerous times that trained neural networks often have high degrees of parameter-redundancy. It remains an open theoretical question why this parameter redundancy cannot be reduced before training by using smaller neural networks. On the other hand, the recent scientific literature reports a plethora of practical methods to "compress" neural networks during or...

12. B12 Consulting: Big value out of small data

Dr Michel Herquet (B12)

4/15/19, 4:30 PM

Machine Learning (and especially Deep Learning) algorithms often require large amounts of data to accomplish their tasks. However, a common problem when such approaches are applied in business contexts is that only relatively small datasets are initially accessible, leading to a fundamental question: how to apply ML tools when there is apparently not enough data available? In this talk, I will...

13. Industry panel

Dr Michel Herquet (B12), Dr Tim Genewein (DeepMind)

4/15/19, 5:05 PM

2. Coffee break