MUMBAI  Dec 5, 2016
Presented by

Deep Learning Training

Presented by

Deep Learining Institute

Hosted By

gcoe

IIT BOMBAY

Train directly with NVIDIA Deep Learning Institute trained instructor-led labs at GTCx India. Learn how advanced deep learning techniques are being applied to rich data sets in order to help solve big problems. Upon completion of an NVIDIA Deep Learning Institute training lab, you will receive a certificate of attendance and online training credits.

DATE: DECEMBER 5 2016 -IIT BOMBAY

VENUE: Lecture Auditorium-102, Lecture Hall Complex (L-3) Behind Chemical Engineering Department, IIT Bombay, Powai, Mumbai-400076. (Entry from IIT Bombay Main gate)

Deep learning is giving machines near human levels of visual recognition capabilities and disrupting many applications by replacing hand-coded software with predictive models learned directly from data. This lab introduces the machine learning workflow and provides hands-on experience with using deep neural networks (DNN) to solve a real-world image classification problem. You will walk through the process of data preparation, model definition, model training and troubleshooting, validation testing and strategies for improving model performance. You’ll also see the benefits of GPU acceleration in the model training process. On completion of this lab you will have the knowledge to use NVIDIA DIGITS to train a DNN on your own image classification dataset.

Prerequisites: Basic knowledge of data science and machine learning

Audience Level: Beginner

Building upon the foundational understanding of how deep learning is applied to image classification, this lab explores different approaches to the more challenging problem of detecting if an object of interest is present within an image and recognizing its precise location within the image. Numerous approaches have been proposed for training deep neural networks for this task, each having pros and cons in relation to model training time, model accuracy and speed of detection during deployment. On completion of this lab, you will understand each approach and their relative merits. You’ll receive hands-on training applying cutting edge object detection networks trained using NVIDIA DIGITS on a challenging real-world dataset.

Prerequisites: Basic knowledge of data science and machine learning

Audience Level: Beginner


Deep learning software frameworks leverage GPU acceleration to train deep neural networks (DNNs). But what do you do with a DNN once you have trained it? The process of applying a trained DNN to new test data is often referred to as ‘inference’ or ‘deployment’. In this lab you will test three different approaches to deploying a trained DNN for inference. 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 it’s 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’ll also explore inference for a variety of different DNN architectures trained in other DLI labs.

Prerequisites: C++ programming experience

Audience Level: Intermediate


Please scroll down for detailed agenda, date & venue, hall address, contact information and link to to registration page.

Deep Learning Institute

See what the Deep Learning Institute program is all about. Learn how advanced deep learning techniques are being applied to these rich datasets to help solve problems.

Learn More

Deep Learning Self-Paced Courses

Learn everything you need to design, train, and integrate neural network powered machine learning into our applications with widely used open-source frameworks and the NVIDIA deep learning platform.

Get Started

Minimum Requirement

IMPORTANT NOTE:

If you are taking any of these Deep Learning Institute courses, you MUST bring your own laptop. Laptops WILL NOT be provided at the class. Minimum laptop specification is as follows.

  • > CPU: Core i3 / i5 @ 2 GHz
  • > Memory: 8 GB RAM
  • > Browser: IE 11, Chrome or Firefox

AGENDA

TITLE GCOE NVIDIA DEEP LEARNING INSTITUTE TRAINING
DATE DECEMBER 5 2016-IIT BOMBAY
VENUE ADDRESS LECTURE AUDITORIUM-102, LECTURE HALL COMPLEX (L-3) BEHIND CHEMICAL ENGINEERING DEPARTMENT, IIT BOMBAY, POWAI, MUMBAI-400076. ( Entry from IIT Bombay Main gate )
CONTACT ROHIT BIDDAPPA 9845016525 rbiddappa@nvidia.com
MODULE 1-BEGINNER
TIME TITLE LEVEL PREREQUISITE
9:00 AM - 11:00 AM Getting Started with Deep Learning (End-to-end Series Part 1) Beginner Basic knowledge of data science and machine learning
11:00 a.m. - 11:15 A.M. BREAK
11:15 AM - 1:15 PM Deep Learning for Object Detection (End-to-end Series Part 2) Beginner Basic knowledge of data science and machine learning
1:15 PM - 2:00 PM LUNCH
MODULE 2-INTERMEDIATE
TIME TITLE LEVEL PREREQUISITE
2:30 PM-4:30PM Deep Learning Network Deployment (End-to-end Series Part 3) Intermediate C++ programming experience

Sign up for one or more Deep Learning trainings at GTCx India and receive online training credits. Space is limited.

CONNECT WITH US

#GTCxINDIA16

SUBSCRIBE FOR UPDATES

GO