AI4IMPACT Live Classroom - Forecasting with Neural Networks [4 Sessions]

Event Information

Share this event

Date and Time

Refund Policy

Refund Policy

Refunds up to 7 days before event

Eventbrite's fee is nonrefundable.

Event description


NOTE: Due to popular requests, the starting date of the workshop is shifted from 29 April to 13 May 2020.

Ever wondered how Amazon can predict what their customers are buying next? Want to learn how to build AI algorithms that power Grab's intelligent demand system?

Neural networks (famously known as Deep Learning) are the "superpower" for building the most effective predictive AI systems. In this course, you will learn practical AI concepts applied by industry practitioners and use them right away to build your own deep learning applications.

Zero experience in AI? No worries! Our experts will be there to mentor you. No prior programming experience needed.


  • Simple-but-powerful AI techniques used by industry practitioners.
  • Hands-on experience developing your own AI applications from start to end.
  • Proven framework on how to use AI effectively for solving industry problems.


  • You want to enhance your career portfolio through real-world AI projects.
  • You want to use AI for solving prediction problems.
  • You want to apply AI techniques to your research or projects.


  • Session 1 - May 13th - 7PM to 8.30PM
  • Session 2 - May 20th - 7PM to 8.30PM
  • Session 3 - May 27th - 7PM to 8.30PM
  • Session 4 - June 3rd - 7PM to 8.30PM


Session 1: Introduction to Forecasting

  • Four basic concepts
  • The Perceptron
  • Feedforward Networks
  • Windowing
  • Introduction to Autocaffe
  • Summary & Homework

Session 2: Model Training

  • Risk Minimization
  • Backprop & Gradient Descent
  • The Prediction Pipeline
  • Understanding Loss Graphs
  • Windowing in Autocaffe
  • Feature Engineering
  • Summary & Homework

Session 3: Neural Networks

  • Defining the Network
  • Normalization
  • Difference networks
  • Early Stopping, Dropouts and Regularization
  • Homework

Session 4: Solving Real-World Problems

  • Application to SG Temps
  • Application to Energy Demand Forecasting

Snippets of the first session:

Join our community:


ARNOLD DORAY is the Head of AI of Terra AI, a predictive technology company. He has 20+ years of experience building global weather forecasting system for mission-critical operations. Arnold has trained 1200 students from NUS, NTU, and SMU in developing predictive AI applications.

Any question? Please contact

Date and Time


Online Event

Refund Policy

Refunds up to 7 days before event

Eventbrite's fee is nonrefundable.

Save This Event

Event Saved