- This event has passed.
AI Singapore Meetup – Anomaly Detection by Numenta
May 17 @ 6:45 pm - 9:00 pm
Sensors and data streams are proliferating as the ‘Internet of Things’ vision becomes realized. However, using the data from these sensors can be cumbersome. Specifically, being able to identify anomalies in streaming data is surprisingly difficult. Most techniques are in the form of thresholds, i.e. predetermined limits set to identify abnormalities. However, thresholds have some glaring weaknesses, such as finding problems only after an event has happened, rather than before, and not adapting to new states, where false positives often crowd out important signals.
Hierarchical Temporal Memory (HTM) for IT works on a model of the neocortex, a part of the brain which controls many vital processes in our actions and behaviour, thereby, making it the best suited for streaming data applications where the underlying patterns are continually changing.
Come and learn more about the work of Numenta and their Hierarchical Temporal Memory – an innovative non-Deep Learning approach to solve this problem.
Date: 17 May 2018
Time: 6.45pm – 9pm
Venue: Seminar Room, Level One, 3 Research Link, Singapore 117602
6.45pm – 7pm: Welcome Address and Introduction to Streaming Data
7pm – 8pm: Presentation by Matthew Taylor (Open Source Community Manager, Numenta)
8pm – 9pm: Demo and Hands-on by Edward Tiong, AI Engineer, AI Singapore.
Numenta is tackling one of the most important scientific challenges of all time: reverse engineering the neocortex. Studying how the brain works helps us understand the principles of intelligence and build machines that work on the same principles. We believe that understanding how the neocortex works is the fastest path to machine intelligence, and creating intelligent machines is important for the continued success of humankind.