Join SignalFire for an AMA with Subutai Ahmad, VP of Research at Numenta. During this AMA he’ll discuss his work in biologically-driven AI. You can find out more and think of some questions in advance by reading from his abstract below. Click on the website link to register.
Biologically driven AI: How a new framework for understanding the neocortex can help us build intelligent machines
Abstract
Human intelligence is the brain’s ability to learn continuously from experience, predict sensations and events, adapt to new situations, understand abstract concepts, and use knowledge to manipulate environments. Current machine learning systems cannot come close to this level of flexibility and generality. Is it possible to learn from the brain and improve today’s learning systems? Recent advances in reverse-engineering the neocortex, the part of the brain responsible for intelligence, reveal that it’s a highly-distributed sensory-motor modeling system, with a repeating circuit known as a “cortical column”. This new framework presents us with a biologically inspired way of addressing common machine learning challenges. In this webinar I’ll introduce its key properties, then describe how these elements can be injected into current systems to improve their learning capabilities, robustness, and power requirements.