NVIDIA Deep Learning Workshop


All activities will be held in room 1030 at the NCSA Building, 1205 W. Clark St., Urbana, Illinois, unless otherwise noted.

Monday, April 3

9:00 a.m.
Lecture: Deep Learning Demystified
A high level, general introduction to deep learning that provides a background on the technology. We will provide key definitions used in the industry, talk about how deep learning is effective across many domains, why it works as a technology and how NVIDIA services and software and hardware assist organizations to quickly take advantage of deep learning attributes.

Lecture: Best Practices for Applying Deep Learning
Learn the characteristics of problems that benefit from deep learning and the dataset/project attributes that make deep learning successful. Specific life science/bioinformatics use cases will be used.
10:30 a.m.
10:45 a.m.
Lab: Getting Started with Deep Learning
Learn how to leverage deep neural networks (DNN) within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS. You will walk through the process of data preparation, model definition, model training and troubleshooting. You will use validation data to test and try different strategies for improving model performance using GPUs. On completion of this lab, you will be able to use NVIDIA DIGITS to train a DNN on your own image classification application.
12:15 p.m.
1:15 p.m.
Lab Review and Questions
1:45 p.m.
Lab: Approaches to Object Detection
This lab explores three approaches to identify a specific feature within an image. Each approach is measured in relation to three metrics: model training time, model accuracy and speed of detection during deployment. On completion of this lab, you will understand the merits of each approach and learn how to detect objects using neural networks trained on NVIDIA DIGITS on real-world datasets.
4:00 p.m.
Lab Review and Questions
4:30 p.m.
End Day 1

Tuesday, April 4

9:00 a.m.
Day 1 Recap
9:30 a.m.
Lab: Deep Learning for Image Segmentation
There are a variety of important applications that need to go beyond detecting individual objects within an image, and that will instead segment the image into spatial regions of interest. An example of image segmentation involves medical imagery analysis, where it is often important to separate the pixels corresponding to different types of tissue, blood or abnormal cells, so that you can isolate a particular organ. Another example includes self-driving cars, where it is used to understand road scenes. In this lab, you will learn how to train and evaluate an image segmentation network.
1:00 p.m.
Lab: Neural Network Deployment
Once a deep neural network (DNN) has been trained using GPU acceleration, it needs to be deployed into production. The step after training is called inference, as it uses a trained DNN to make predictions of new data. This lab will show three approaches for deployment. The first approach is to directly use inference functionality within a deep learning framework, in this case DIGITS and Caffe. The second approach is to integrate inference within a custom application by using a deep learning framework API, again using Caffe, but this time through its Python API. The final approach is to use the NVIDIA TensorRT™, which will automatically create an optimized inference run-time from a trained Caffe model and network description file. You will learn about the role of batch size in inference performance, as well as various optimizations that can be made in the inference process. You will also explore inference for a variety of different DNN architectures trained in other DLI labs.
2:00 p.m.
Lab Review and Questions
2:30 p.m.
End Day 2