Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

In-Person Training
NVIDIA Deep Learning Institute bootcamp

Charles Killam (NVIDIA)
Monday, June 26 & Tuesday, June 27, 9:00am - 5:00pm
Location: Bryant
Secondary topics:  Deep Learning
Average rating: ***..
(3.00, 2 ratings)

Participants should plan to attend both days of this 2-day training course. Training passes do not include access to tutorials on Tuesday.

NVIDIA Deep Learning Institute-certified instructor Charlie Killam walks you through solving the most challenging problems with deep learning. You'll start with deep learning basic concepts and quickly move to taking on real-word problems using deep learning.

What you'll learn, and how you can apply it

  • Understand deep learning basic concepts and terminology
  • Learn how to leverage deep neural networks to solve real-world image classification problems, how to detect objected using trained neural networks, and how to train and evaluate an image segmentation network

Hardware and/or installation requirements:

  • In preparation for the workshop, we ask that prior to the event you:
  • Create a Qwiklabs account by going to https://nvlabs.qwiklab.com/
  • Ensure your laptop will run smoothly by going to http://websocketstest.com/
  • Make sure that WebSockets work for you by seeing under Environment, WebSockets is supported and Data Receive, Send and Echo Test all check Yes under WebSockets (Port 80).
  • If there are issues with WebSockets, try updating your browser. Best browsers for qwikLABS are Chrome, FireFox and Safari. The labs will run in IE but it is not an optimal experience.
  • Bring your laptop

NVIDIA Deep Learning Institute-certified instructor Charlie Killam walks you through solving the most challenging problems with deep learning. You’ll start with deep learning basic concepts and quickly move to taking on real-word problems using deep learning.


Day 1

9:00am–9:30am: Deep learning demystified and applied deep learning

  • Lecture: General background on deep learning, key terminology, use cases from various industries, how deep learning differs from previous algorithmic approach, and how a deep neural network gets trained, optimized, and deployed. Plus, learn how to apply deep learning to challenging problems, what types of problems benefit most from deep learning, what skills and knowledge is needed to use deep learning, and the characteristics of successful deep learning projects.

9:30am – 10:30am: Image classification with DIGITS

  • Hands-on exercise: Leverage deep neural networks (DNN) within the deep learning workflow, solve a real-world image classification problem using NVIDIA DIGITS, walk through the process of data preparation, model definition, model training, and troubleshooting, use validation data to test and try different strategies for improving model performance using GPUs, and use NVIDIA DIGITS to train a DNN on your own image classification application.

10:30am–11:00am: Morning break
11:00am–12:30pm: Image classification with DIGITS continued

  • Hands-on exercise: continued

12:30pm–1:30pm: Lunch
1:30pm–3:00pm: Object detection with DIGITS

  • Hands-on exercise: Learn three approaches to identify a specific feature within an image, compare each in relation to model training time, model accuracy, and speed of detection during deployment, understand the merits of each approach, and learn how to detect objects using trained neural networks.

3:00pm–3:30pm: Afternoon break
3:30pm – 5:00pm: Wrap-up and Q&A

Day 2

9:00am–10:30am: Image segmentation with TensorFlow

  • Hands-on exercise: Deep learning for image segmentation—Learn how to train and evaluate an image segmentation network

10:30am–11:00am: Morning break

11:00am–12:30pm: Modeling time series data with recurrent neural networks in Keras

  • Hands-on exercise: Learn how to create training and testing datasets using electronic health records and prepare datasets for use with RNNs. Plus, construct a long short-term memory model (LSTM) using the Keras library with Theano.

12:30pm–1:30pm: Lunch
1:30pm–3:00pm: Neural network deployment with DIGITS and TensorRT

  • Hands-on exercise: Learn three approaches for deployment (directly use inference functionality within a deep learning framework, integrate inference within a custom application, and use the NVIDIA TensorRT), the role of batch size in inference performance, and various optimizations that can be made in the inference process and explore inference for a variety of different DNN architectures.

3:00pm–3:30pm: Afternoon break
3:30pm–5:00pm: Wrap-up and Q&A

About your instructor

Charles Killam is a certified instructor and curriculum designer at NVIDIA’s Deep Learning Institute. Though Charlie works across all verticals, his efforts focus primarily on the application of deep neural networks (DNNs) in the healthcare space. Over his career, Charlie has delivered a data analytics bootcamp for Northeastern University, a geospatial Tableau project for Stanford University, and, working with MADlib, an open source machine learning algorithm library at Pivotal.

Conference registration

Get the Platinum pass or the Training pass to add this course to your package.

Comments on this page are now closed.


07/05/2017 12:37pm EDT

I have attended training, it was great, still need time to digest what we learn, where can we download power point slides. Please provide link.

Picture of Jason Perdue
06/22/2017 1:51pm EDT

See above for hardware and installation instructions. Also look for the email that will be coming shortly.

Vishnu Muralidharan | ASSOCIATE
06/22/2017 12:55pm EDT

What are some prerequisite software/hardware i would require for this session?