How can computers detect fraud, predict floods or forecast demand?
This 2-day course gets you started in answering such questions. The core topic centers around Data Modelling, which is building computer models that:
You will be taught by industry experts who will guide you step-by-step applying advanced Machine Learning techniques to solving data modelling problems.
This 2-day data analytics course (6 lectures and 6 lab sessions) is 50% lecture and 50% hands-on labs.
We specially designed the labs so you immediately apply advanced machine learning techniques to a challenging real-world data modelling problem: calibrating weather radar data. The problem set was selected from part of our own work to showcase how machine learning can be applied and pitfalls to avoid. The techniques you learn can be applied to a wide variety of real-world problems.
The key advantage of machine learning is to generate computer models for prediction automatically.
We will study the foundational approaches to Machine Learning and apply them to three different data modelling approaches, including Deep Learning with neural networks. Our focus is always practical application and mathematical machinery is included only to support this goal. After every lecture, you will get the opportunity to apply each technique on your own computer during the lab session. We want you to take away a solid understanding of these techniques and confidently apply to your own problem space.
Machine learning encompasses a wide range of tools and techniques which can be confusing for newcomers.
Simpler "black box" tools often give suboptimal results while more advanced techniques require care and expertise in their handling. In this course, we will especially cover neural networks, which are arguably the most powerful technique for data modelling. To apply them successfully in your projects requires a deep understanding of how they work and how to overcome the many difficulties in using them.
It is challenging to apply Machine Learning successfully to real-world problems because of the many pitfalls.
Our approach is to deep-dive into a real-world problem, namely calibrating weather radar. Weather radar plays a huge role in rain and flood forecasting. The challenge is to correctly calibrate radar backscatter readings against observed rainfall at fixed stations. This involves building models that captures the behaviour of radar signals and translates it into rainfall. While this is a tough problem to solve, it provides a thorough guide to the hurdles you will face in your own applications. The end result is competency and confidence in advanced Data Analytics.
The next decade will be the Golden Age of Artificial Intelligence.
This revolution will impact every industry and economy. We believe AI will have many positive effects for society, but without doubt, it will come at a cost. The disruptive effects of AI will mean adverse consequences for those not able to adapt. We believe our course will take you one step towards embracing and leading change, rather than being buffeted by it.
Our course plan extends even after the course is officially over: Students excelling in our take-home project will be awarded the coveted Certificate of Accomplishment. All our courses come with a focussed discussion group so you can continue to ask questions and learn. If you feel you have an interesting industry problem, you can also contact your instructors for followup and consultation.
Each lab has a set of quizzes and learning goals. Participants successfully completing these goals will receive a Certificate of Completion.
However, this course also has a substantial take-home project component to be completed after the course. We award the best student submissions of this take-home project with a Certificate of Accomplishment, and a place in our Terra AI Hall of Fame online. We issue these certificates selectively only to the best student projects.
This course is designed for non-programmers, but requires university-level calculus.
Samuel Wang holds a masters' degree in experimental Physics from the National University of Singapore (NUS). He is a Data Scientist at Terra-AI.SG and will be the lead trainer for this course. Samuel has contributed to the development of TW Caffe, 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-AI.SG and is the lead developer of Autocaffe and the Smojo Programming Language we use for data processing at Terra-AI.SG. Arnold is an industry veteran with over 20 years' experience in implementing AI and automation in various organizations, including leading change in our parent company, Terra Weather. The result has been significant improvements in quality and customer satisfaction as well as extensive cost-savings through better use of manpower.
Contact Mr Christian Jonathan 6515 4775 or email email@example.com.
|Venue:||Devan Nair Institute for Employment and Employability 80 Jurong East St 21, Singapore 609607.|
|Time:||2 days. 8:30am-5:00pm|
Lecture 1 (09:00 - 09:45)
Lab 1 (09:45 - 11:00)
Lecture 2 (11:00 - 12:00)
LUNCH BREAK (12:00 - 13:00)
Lab 2 (13:00 - 14:00)
Lecture 3 (14:00 - 14:45)
Assessment #1: (14:45 - 15:30)
Lab 3 (15:30 - 17:00)
Lecture 4 (09:00 - 10:00)
Lab 4 (10:00 - 11:00)
Lecture 5 (11:00 - 12:00)
LUNCH BREAK (12:00 - 13:00)
Lab 5 (13:00 - 14:30)
Lecture 6 (14:30 - 15:30)
Lab 6 (15:30 - 16:00)
Wrap Up (16:30 - 17:00)
Terra-AI.SG is a division of Terra Weather, a technology company specializing in developing cutting-edge prediction technology and Artificial Intelligence based solutions. Our weather AI processes data from multiple sources such as satellites and sensors and converts them into highly accurate weather predictions. We enable multi-national Oil and Gas, Marine Transportation and Marine Consultancy companies work safely and successfully worldwide.