Symposium Artificial Intelligence for Science, Industry and Society

Session

Organization

21 Oct 2019, 08:00

Conveners

Organization: Start of the symposium

• There are no conveners in this block

Organization: Summaries and closing remarks

• Lukas Nellen (Universidad Nacional Autonoma (MX))

Organization: Machine learning tutorial

• Lukas Nellen (Universidad Nacional Autonoma (MX))

Organization: Registration desk open

• There are no conveners in this block

16. Welcome and introduction

21/10/2019, 09:00

Oral

4. OECD summary

Alan Paic (OECD)

25/10/2019, 11:30

5. Symposium summary

Federico Carminati (CERN)

25/10/2019, 12:00

6. Closing remarks

Guy Paic (Universidad Nacional Autonoma (MX)), Lukas Nellen (Universidad Nacional Autonoma (MX))

25/10/2019, 12:45

66. Neural Network optimisation

Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))

25/10/2019, 15:00

Modern neural network architecture reflects the complexity of the problem. So those may become quite complex and computationally heavy. Usually, there are plenty of different meta-parameters to tune: number of layers, activation function, number of neurons per layer, drop-out rate, etc. There many different methods and tools that aimed at tuning those parameters for various reasons - accuracy,...

3. Best poster talks