Course Overview:

Organizations are using deep learning and AI at every stage of growth, from startups to Fortune 500s. Deep learning, the fastest growing field in AI, is empowering immense progress in all kinds of emerging markets and will be instrumental in ways we haven’t even imagined.

Today’s advanced deep neural networks use algorithms, big data, and the computational power of the GPU to change this dynamic. Machines are now able to learn at a speed, accuracy, and scale that are driving true artificial intelligence and AI Computing.

Course Objectives:

Learn the latest techniques on how to design, train, and deploy neural network-powered machine learning in your applications. You’ll explore widely used open-source frameworks and NVIDIA’s latest GPU-accelerated deep learning platforms.

Pre-requisite

Individual who has diploma / degree in IT, computer science and any computer related study that have learn the basic of programming language.

** For more Python knowledge to review this side 1st as link below.
https://www.python.org/about/gettingstarted/

EXAMINATION:
- No. of Questions: 30 Questions
- Duration - 1 hour
- Exam Type - Multiple Choice Questions (MCQ)
- Compulsory Passing Rate - 70%

Day 1

What is Deep Learning and what are Neural Networks? (30 min):
- 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 (60 min):
- 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

BREAK (15 min)

Building an ANN (60 min):
- Getting the python libraries
- Constructing ANN
- Using the bank customer churn dataset
- Predicting if customer will leave or not

Evaluating Performance of an ANN (60 min):
- Evaluating the ANN
- Improving the ANN
- Tuning the ANN

LUNCH (60 min)

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

BREAK (15 min)

Building a CNN (60 min):
- Getting the python libraries
- Constructing a CNN
- Using the Image classification dataset
- Predicting the class of an image

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

BREAK (15 min)

Recurrent Neural Networks (RNN) Intuition (60 min):
- What are RNN’s?
- Vanishing Gradient problem
- LSTMs
- Practical intuition
- LSTM variations

LUNCH (60 min)

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

BREAK (15 min)

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

Image Classification with DIGITS (90 min):
- 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

BREAK (15 min)

Object Detection with DIGITS (90 min):
- Train and evaluate an image segmentation network

LUNCH (60 min)

Neutral Network Deployment with DIGITS and TensorRT (120 min):
- 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

EXAMINATION:
- No. of Questions: 30 Questions
- Duration - 1 hour
- Exam Type - Multiple Choice Questions (MCQ)
- Compulsory Passing Rate - 70%

Payment can be made by:

    1. Cash or Credit Card or Bank Cheque payable to “Software Park Thailand #2” (a post-dated cheque is not accepted) on the first day of the service or within the last day of the service.
     2. Account transfer and send the proof of the payment (the deposit slip) via fax or email to fax no. 02-583-2884 or email ttd@swpark.or.th

        2.1 Siam Commercial Bank, Chaengwattana Branch
             Saving Account Number: 324-2-56262-0
             Account Name: Software Park Thailand#2

        2.2 Krungsri Bank, Chaengwattana (Software Park) Branch
             Saving Account Number: 329-1-34850-3
             Account Name: Software Park Thailand#2

Notes:
- Withholding tax (3%) is exempt.
- Should you need to withdraw, you must send the notice of the withdrawal in writing no later than 7 working days before the commencement date. The cancellation less than 7 days will be subject to a fine of 40% of the fee.
- Software Park Thailand reserves the rights to cancel courses due to unforeseen circumstances.

For more information, contact our course coordinator on:

Name: Ms.Kotchaphan Aokdeelert

Tel: +66-2583-9992 Ext. 1425

Fax: +66-2583-2884

Email: kotchaphan.aokdeelert@nstda.or.th or ttd@swpark.or.th

You are encouraged to use the course schedule as a guide to plan your training. The schedule is accessible at www.swpark.or.th for more information.