Course Details

  Course Name: An Intuitive Approach To Deep Learning for Time-Series Forecasting
  Course Code: 
  Duration: 5 days, 8.30am to 5.30pm
   Location: 80 Jurong East Street 21 #04- 04, Devan Nair Institute, Singapore 609607
Course Fees: S$4,000 (excl of G.S.T)
Promo Price: S$3,200 (excl of G.S.T)
2018 Course Dates
Tick_Mark_Dark 9 – 13 Jul 2018
Tick_Mark_Dark 3 – 7 Sep 2018
Tick_Mark_Dark 1 – 5 Oct 2018
Tick_Mark_Dark 12 – 16 Nov 2018
Tick_Mark_Dark 3 – 7 Dec 2018
None of the published dates will work for you? Speak to our training consultants for a private tuition arrangement or a closed door training.
Do note that this course listed uses digital courseware. You are required to bring your own device to access the digital manual.

Tick_Mark_Dark Neural Network (NN) techniques for timeseries forecasting. Using the Caffe [1] deep learning framework, we will teach you how to create NN models for timeseries forecasting, which can be applied to any area that requires you to predict future events given time-varying data sources. Planning & Operations: supply chain forecasting, logistics planning, process optimization.

Tick_Mark_Dark Understand how NNs work. To use them effectively, you have to really understand how NNs work. What they can and can’t do. We will take a bottom-up approach to teaching you how to translate the complex math into practical knowledge you can use to design and train NNs. This is reinforced with quizzes and 10 hands-on lab sessions.

Tick_Mark_Dark Best practices for NN based forecasting. How to determine optimum network configurations? How to train complex networks? How to evaluate and track performance? When to apply a technique and when not to? We teach you how to develop an intuition of what will work and what won’t so you can reason for yourself.

Tick_Mark_DarkModule 1: Introduction to Caffe & Linux

Tick_Mark_DarkModule 2: Running Caffe

Tick_Mark_DarkModule 3: Neural Network Basics

Tick_Mark_DarkModule 4: The Backpropagation Algorithm

Tick_Mark_DarkModule 5: Training and Evaluating Neural Networks

Tick_Mark_DarkModule 6: Timeseries Data

Tick_Mark_DarkModule 7: The Loss Function

Tick_Mark_DarkModule 8: Deep Learning & Stacked Autoencoders

Tick_Mark_DarkModule 9: Data Transformations

Tick_Mark_Dark Module 10: Putting it All Together

Click Here for full course outline

 Samuel Wang holds a masters’ degree in Physics from the National University of Singapore (NUS). He is a Data Scientist at AI@TerraWx and will be the lead trainer for this AI Workshop. Samuel has contributed to the development of TW Caffe (see http://ai.terrawx.com), our open-source fork of Caffe specifically aimed at timeseries forecasting. He also works on Autocaffe, a productivity tool to simplify deep learning on Caffe.

 Arnold Doray holds a degree in Physics and masters in Knowledge Engineering from NUS. He leads product development at Terra Weather and is the lead developer of Autocaffe and the Mini scripting language we use for data processing. Arnold is the alternative trainer for this AI Workshop.

Enrol Form

Please Select A Course

For Self Sponsored, please fill in Part A.
For Company Sponsored, please fill in both Part A and Part B.

Part B

Co-ordinator Details

Approving Person Details