Jeff Hawkins on the Path to Machine Intelligence

Tuesday, April 8, 2014

 Artificial Intelligence
Jeff Hawkins, founder of Numenta recently gave a talk highlighting his approach to machine intelligence—an approach that is highly dependent on an understanding of the human neocortex.

Understanding how the brain works and building machines that work on the same principles is one of the greatest quests of our time. In a recent talk (video below) by Jeff Hawkins, founder of Palm and now, Numenta describes recent advances in neocortical theory, including why the brain uses sparse distributed representations and how the brain makes predictions from high velocity sensory data streams.

"[Neural networks] may be the right thing to do, but it's not the way brains work and it's not the principles of intelligence, and it's not going to lead to a system that can explore the world or systems that can have behavior."

The talk features a demonstration of Hawkins' product called GROK, that uses a detailed model of neocortical memory to act on machine generated data and how developers can contribute to the development of intelligent machines via the NuPIC open source project.

"I'm surprised by how few people believe they need to understand how the brain works to build intelligent machines," Hawkins says. "I'm disappointed by this."

"I want to bring about intelligent machines, machine intelligence, accelerated greatly from where it was going to happen and I don't want to be consumed – I want to come out at the other end as a normal person with my sanity," Hawkins told The Register recently. "My mission, the mission of Numenta, is to be a catalyst for machine intelligence."

While major firms like Google and Facebook, and small companies like Vicarious, are striding over well-worn paths, Hawkins following the theories he laid out in his book, On Intelligence, believes he is taking a new, and better approach.

Related articles
This approach is also the source of the greatest criticisms of Hawkins' work. With so little actually confirmed about how brain works, he is essentially working from a theory; not evidence.

"No one knows how the cortex works, so there is no way to know if Jeff is on the right track or not," Dr Terry Sejnowski, the laboratory head of the Computational Neurobiology Laboratory at the Salk Institute for Biological Studies in San Diego, California, told The Register. "To the extent that [Hawkins] incorporates new data into his models he may have a shot, and there will be a flood of data coming from the BRAIN Initiative that was announced by Obama last April."

"I know of no other cortical theories or models that incorporate any of the following: active dendrites, differences between proximal and distal dendrites, synapse growth and decay, potential synapses, dendrite growth, depolarization as a mode of prediction, mini-columns, multiple types of inhibition and their corresponding inhibitory neurons, etcetera. The new temporal pooling mechanism we are working on requires metabotropic receptors in the locations they are, and are not, found. Again, I don't know of any theories that have been reduced to practice that incorporate any, let alone all of these concepts," he wrote in a post to the discussion mailing list for Numenta's open-source NuPic.

Numenta's approach also relies on time. Its Cortical Learning Algorithm is essentially an engine for processing streams of information, classifying them, learning to spot differences, and using time-based patterns to make predictions about the future.

SOURCE  The Register, GOTO Conferences

By 33rd SquareEmbed