Introduction to Deep Learning with NVIDIA GPUs

3-Day Instructor-Led Course | HRDF Claimable!

In Partnership With

Deep Learning Course Overview

Deep Learning (DL) is the fastest-growing field in Machine Learning and Artificial Intelligence (AI) that enables machines to be far more efficient, advanced and intelligent at predicting things. It uses many layered Deep Neural Networks (DNNs) to make sense of data such as images, sound and text, and powers some of the most interesting applications in the world like autonomous vehicles (driverless cars), speech recognition, image recognition, preventive healthcare, and more.

Developers, Engineers and Business Leaders of today cannot ignore the impact of Deep Learning for powering modern applications as more and more organisations are investing heavily in research and using the technology in many practical machine assists, from startups to Fortune 500 companies. DL is enabling immense progress in all kinds of emerging markets and will be instrumental in ways yet to be imagined!

Today’s advanced DNNs use algorithms, big data, and the computational power of Graphic Processing Units (GPUs) so machines can learn at the speed, accuracy and scale that are driving true AI computing. To understand how you can harness the power of DL for your organisation or invention, start by getting an Introduction to Deep Learning with NVIDIA GPUs. During the Course, you’ll learn the latest techniques on how to design, train and deploy neural network-powered machine learning in your applications. You’ll also explore explore widely used open-source frameworks and NVIDIA’s latest GPU-accelerated deep learning platforms.

Key Topics Covered:

Introduction to Deep Learning (DL) • Getting Started with DL • Approaches to Object Detection using DIGITS • DL for Image Segmentation • DL Network Deployment • Medical Image Segmentation using DIGITS • Introduction to DL with R and MXNET • Introduction to RNNs • Signal Processing using DIGITS • DL with Electronic Health Record

Course Outline


Day 1

  • Deep Learning as a branch of AI
  • Neural networks and their history and relationship to neurons
  • Creating a neural network in Python

  • Understanding the neuron and neuroscience
  • The activation function (utility function or loss function)
  • How do NN’s work?
  • How do NN’s learn?
  • Gradient descent
  • Stochastic Gradient descent
  • Backpropagation

  • Getting the python libraries
  • Constructing ANN
  • Using the bank customer churn dataset
  • Predicting if customer will leave or not

  • Evaluating the ANN
  • Improving the ANN
  • Tuning the ANN

  • Participants will be asked to build the ANN from the previous exercise
  • Participants will be asked to improve the accuracy of their ANN

  • What are CNN’s?
  • Convolution operation
  • ReLU Layer
  • Pooling
  • Flattening
  • Full Connection
  • Softmax and Cross-entropy

  • Getting the python libraries
  • Constructing a CNN
  • Using the Image classification dataset
  • Predicting the class of an image

Day 2

  • Evaluating the CNN
  • Improving the CNN
  • Tuning the CNN

  • Participants will be asked to build the CNN from the previous exercise
  • Participants will be asked to improve the accuracy of their CNN

  • What are RNN’s?
  • Vanishing Gradient problem
  • LSTMs
  • Practical intuition
  • LSTM variations

  • Getting the python libraries
  • Constructing RNN
  • Using the stock prediction dataset
  • Predicting stock price

  • Evaluating the RNN
  • Improving the RNN
  • Tuning the RNN

  • Participants will be asked to build the RNN from the previous exercise
  • Participants will be asked to improve the accuracy of their RNN

Day 3

  • How to leverage deep neutral networks (DNN) within the deep learning workflow
  • Process of data preparation, model definition, model training and troubleshooting, validation testing and strategies for improving model performance using GPUs.
  • Train a DNN on your own image classification application

  • Train and evaluate an image segmentation network

  • Uses a trained DNN to make predictions from new data
  • Show different approaches to deploying a trained DNN for inference
  • learn about the role of batch size in inference performance as well as virus optimisations that can be made in the inference process
  • Closing comments and questions



You bet it is! Our Certification Body for this course is iTrain Asia Pte Ltd, the region’s top Certifications Tech Provider headquartered in Singapore, with branch offices in Malaysia and Indonesia.

This is a 3-day course at an instructor-led training centre.

Mac machines are provided for iTrain students. However participants can also use their own computers if they wish to.