| layout | title | permalink |
|---|---|---|
page |
Introduction to Deep Learning on ShARC's DGX-1 |
/education/intro_dl_sharc_dgx1/ |
RSES is pleased to announce that there will be a 2 afternoon Deep Learning training course held at the University of Sheffield on February 16th and 23rd 2017 (from 13:00-17:00 on both days).
The course aims to introduce core concepts of deep learning and how it can be applied to your research in a practical way. The course will specifically look at the use of Caffe deep learning package on the DGX-1 deep learning supercomputer hosted in our new ShARC cluster. Through practical examples you will learn to:
- Implement convolution models for image classification
- Implement recurrent models for serial inputs and outputs such as text prediction
- Visually debugging your model by visualising their weights
- Use and refine existing pre-trained models to your needs
- Utilise multiple GPUs to accelerate the training of your models
The course will be delivered by Twin Karmakharm with assistance from Dr. Mozhgan Kabiri Chimeh from the Research Software Engineering Sheffield group.
Familiarity with Linux, the use of command line, Python and basic understanding of neural network. If you're not familiar with Nueral Networks please see Stephen Welch's Neural Networks Demystified to get a better understanding. Working through his code exercises may also be useful but is not essential for the course:
- Slides: Introduction to Deep Learning Day 1
- Lab 00: Getting Started
- Lab 01: A Simple Neural Network Model
- Lab 02: Convolution Neural Network
- Lab 03: Deploying and using your trained model
- Slides: Introduction to Deep Learning Day 2
- Lab 04: Using and visualising pre-trained models
- Lab 05: Multi-GPU and Benchmarking
- Lab 06: Recurrent Neural Networks
- See a neural network in action at the Neural Network Playground
- For deeper understanding on the subject of Machine Learning and Neural Networks, see Andrew Ng's excellent Machine Learning module on Coursera