High Performance Computing Center North
The seminar will be held at Umeå Folkets Hus, Miklagård, Skolgatan 59 (Vasaplan), in Umeå on Tuesday October 23rd, time: 09:00 to 12:00.
There is no cost to join the event, MATLAB only need registration through the link below.
Presenter is Emelie Andersson who is an application engineer at Mathworks specialized in the domain.
09:00 Drop-in Registration & Breakfast
09:30 In the first session, we will look at CLASSICAL MACHINE LEARNING approaches to classification and regression problems. We will discuss how MULTIPLE CPUS SPEEDS UP THE TRAINING PROCESS at the push of a
button, and how intuitive apps can help you in CHOOSING THE APPROPRIATE MODEL.
10:30 Coffee Break
10:45 The second session will cover DEEP LEARNING TECHNIQUES to help solve problems such as object detection, regression, and classification. We will look at how to set up and TRAIN CONVOLUTIONAL NEURAL NETWORKS (CNNS) as well as RECURRENT NEURAL NETWORKS (RNNS), both through training from scratch but also through modifying an existing CNN to fit a new purpose (TRANSFER LEARNING). In the end we will show how the MATLAB code can be AUTOMATICALLY CONVERTED TO CUDA CODE, and then DEPLOYED ON TO GPUS
12:00 Seminar ends
Below please find the link for details on how to register as well as more info:
Should you have any questions please do not hesitate to contact Lisa Ledenvall at Lisa.Ledenvall@mathworks.com
Welcome to the seminar!