Introduction to Deep Learning with NVIDIA GPUs
Do you want to learn data science from industry experts? This certification course for data science offers just that! Data science is undoubtedly the gold mine of the present and future. It enables you to seek valuable information through data analysis and machine learning functions.
From deriving strategic business decisions, to unlocking new economic values for businesses, data science allows presentation of predictions derived from data evidence.
This Certified Data Science Specialist Certification (CDSS) combines a good balance of theoretical knowledge and practical application. Upon completion of this 5-day course, you will be capable of leveraging data and put yourself in the forefront of any business decisions.
Audience Profile
Anyone interested in to learn more about Deep Learning, or kickstart a career as a Data Scientist. This includes Students, Data Analysts, Business Owners, Entrepreneurs or any individual who wishes to leverage on powerful Deep Learning tools to add value wherever they are.
Participant Prerequisites
Basic high school mathematics knowledge, no Prior Deep Learning knowledge. Basic Python understanding can be used for some exercise.
Course Objectives
Upon completion of this course, you will be able to:
- Introduction to Deep Learning
- Getting Started with Deep Learning
- Approaches to Object Detection using DIGITS
- Deep Learning for Image Segmentation
- Deep Learning Network Deployment
- Medical Image Segmentation using DIGITS
- Introduction to Deep Learning with and MXNET
- Introduction to RNNs
- Signal Processing using DIGITS
- Deep Learning with Electronic Health Record
Course Outline
The following items describe the outline of the course:
Day 1:
What is Deep Learning and what are Neural Networks?
- Deep Learning as a branch of AI
- Neural networks and their history and relationship to neurons
- Creating a neural network in Python
Artificial Neural Networks (ANN) Intuition
- 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
Building an ANN
- Getting the python libraries
- Constructing ANN
- Using the bank customer churn dataset
- Predicting if customer will leave or not
Evaluating Performance of an ANN
- Evaluating the ANN
- Improving the ANN
- Tuning the ANN
Building a CNN (60 min)
- Getting the python libraries
- Constructing a CNN
- Using the Image classification dataset
- Predicting the class of an image
Hands-On Exercise (60 min)
- Participants will be asked to build the ANN from the previous exercise
- Participants will be asked to improve the accuracy of their ANN
Convolutional Neural Networks (CNN) Intuition (60 min)
- What are CNN’s?
- Convolution operation
- ReLU Layer
- Pooling
- Flattening
- Full Connection
- Softmax and Cross-entropy
Day 2:
Evaluating Performance of a CNN (60 min)
- Evaluating the CNN
- Improving the CNN
- Tuning the CNN
Hands-On Exercise (60 min)
- Participants will be asked to build the CNN from the previous exercise
- Participants will be asked to improve the accuracy of their CNN
Recurrent Neural Networks (RNN) Intuition (60 min)
- What are RNN’s?
- Vanishing Gradient problem
- Practical intuition
- LSTM variations
- LSTMs
Building a RNN (60 min)
- Getting the python libraries
- Constructing RNN
- Using the stock prediction dataset
- Predicting stock price
Evaluating Performance of a RNN (60 min)
- Evaluating the RNN
- Improving the RNN
- Tuning the RNN
Hands-On Exercise (60 min)
- 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:
Introduction (45 mins)
Components
- Course Overview
- Getting Started with Deep Learning
Description
Introduction to Deep Learning, situations in which it is useful, key terminology, industry trends, and challenges
Unlock New Capabilities (120 mins)
Components
- The biological inspiration for Deep Neural Networks (DNNs)
- Training DNNs with Big Data
Description
Hands-on exercise: Training neural networks to perform image
classification by harnessing the three main ingredients of deep
learning: Deep Neural Networks, Big Data, and the GPU
Unlock New Capabilities (40 mins)
Components
- Deploying DNN Models
Description
Hands-on exercise: Deployment of trained neural networks from their training environment into real applications
Measuring and Improving Performance (100 mins)
Components
- Optimizing DNN Performance
- Incorporating Object Detection
Description
Hands-on exercise: Neural network performance optimization and applying DNNs to object detection
Summary (20 mins)
Components
- Summary of Key Learnings
Description
Review of concepts and practical takeaways
Assessment (60 mins)
Components
- Assessment Project: Train and Deploy a Deep Neural Network
Description
Validate your learning by applying the deep learning application development workflow (load dataset, train and deploy model) to a new problem
Next Steps (15 mins)
Components
- Workshop Survey
- Setting up your own GPU enabled-environment
- Additional project ideas
Description
Learn how to set up your GPU-enabled environment to begin work on your own projects. Get additional project ideas along with resources to get started with NVIDIA AMI on the cloud, NVIDIA-Docker and the NVIDIA DIGITS container
Course Materials
The following materials are included as part of the course:
- iTrain Asia official digital curriculum
Exam Format
Participant will receive a Beginner Lever certificate from NVIDIA Deep Learning Institute once you have completed the 3-day programme inclusive of participation in the 1-day NVIDIA Deep Learning Lab.
