Entrepreneur-turned-cognitive neuroscientist Jeff Hawkins is distributing a “research release” of their experimental code base implementing his idea of hierarchical temporal memory described in his book, “On Intelligence”. Hawkins drew inspiration for the model from his own reading about the structure and function of the human neocortex and believes that it represents the foundation for developing intelligent machines.
Jeff explains this surprising move to open source the code for the Numenta Platform for Intelligent Computing (NuPIC) on the Numenta web site:
Why are we making NuPIC available now?
We have been contacted by dozens of researchers and scientists who are excited about HTM and by our work at Numenta. These people are anxious to work on HTM, are willing to be pioneers, and are willing to accept the uncertainty associated with a new technology. We are making our tools available so that these sophisticated developers can start building a community around HTM technology. NuPIC has been under development for 18 months, is pretty solid, and is well documented - including several examples to make it easy to get started - so we’re ready to open up to more developers, even while knowing that we do not yet have benchmarking data, and we cannot make guarantees about applicability to specific problems.
Neurodudes is actively soliciting code reviews of the newly released software. Is NuPIC the next big thing, or are you left feeling cold? Post your thoughts yourself using the instructions on the right-hand column, or let us know at contactus -AT- neurodudes.com!
Recently, a company named AnyBots appears to have been able to build a humanoid walking robot whose gait is much more humanlike that Honda’s Asimo (If you aren’t familiar with Asimo, check it out)
The robot is named Dexter, and here’s a link to a blog explaining why its better than Asimo. From the blog:
There are of course biped robots that walk. The Honda Asimo is the best known. But the Asimo doesn’t balance dynamically. Its walk is preprogrammed; if you had it walk twice across the same space, it would put its feet down in exactly the same place the second time. And of course the floor has to be hard and flat.
Dynamically balancing—the way we walk—is much harder. It looks fairly smooth when we do it, but it’s really a controlled fall. At any given moment you have to think (or at least, your body does) about which direction you’re falling, and put your foot down in exactly the right place to push you in the direction you want to go. Practice makes it seem easy to us, but it’s a very hard problem to solve. Something as tall as a human becomes irretrievably off balance very rapidly.
This is important because robots that dynamically balance can handle arbitrary terrains and can withstand attempts to knock them over, much like the Big Dog robot we reported on earlier, whereas pre-programmed robots like Asimo cannot. If Honda were smart, they’d buy AnyBot ASAP.
In September, 2006, I described my “new brain/mind theory” here and received some challenging criticism from Eric Thomson and Mike S. (see below). To meet these challenges, I prepared a reduced model discussed in a web page linked to a paper in .pdf form. Since my approach is based on little-known thermodynamics, I have also written about mechanical metaphors that may be helpful in explaining my ideas.
(UPDATE 03-05-2007 - Upon closer inspection, it is clear that while the surgery has enabled the woman to have sensation in the nerves of her missing hand when the surface of her chest is touched, the arm she is fitted with at the time of publication did not relay sensory signals from the arm back to her chest. As soon as she is fitted with an arm that has the appropriate sensors, however, she will not have to undergo further surgery to have this kind of direct feedback. Thanks to astute readers for pointing this out.)
The Guardian reports on an article published today in the Lancet about a successful surgical procedure giving an amputee a bionic arm that both responds to motor commands from her remaining motor nerves to control it and provides sensory feedback to sensory nerves when it is touched. If there was any doubt left, the worlds of neural prosthetics and brain-machine interfaces have officially collided.
The Lancet article is accompanied by two movies of the woman using the arm that you should really check out.
”
Nature has always been a source of inspiration for science problem solving….Both the techniques based in cell or natural organisms performance, as well as those based on evolutionary theories, have a wide success record when applied to real problems…. we are in the process of editing the “Encyclopedia of Artificial Intelligence ” that will provide comprehensive coverage and definitions of the most important issues, concepts, trends and technologies in Artificial Intelligence.
”
HOW CAN TECHNOLOGY EMULATE BIOLOGICAL INTELLIGENCE?
The conference is aimed at researchers and students of computational neuroscience, cognitive science, neural networks, neuromorphic engineering, and artificial intelligence. It includes invited lectures and contributed lectures and posters by experts on the biology and technology of how the brain and other intelligent systems adapt to a changing world. The conference is particularly interested in exploring how the brain and biologically-inspired algorithms and systems in engineering and technology can learn. Single-track oral and poster sessions enable all presented work to be highly visible. Three-hour poster sessions with no conflicting events will be held on two of the conference days. Posters will be up all day, and can also be viewed during breaks in the talk schedule.
Center for Adaptive Systems and
Department of Cognitive and Neural Systems (http://www.cns.bu.edu/)
with financial support from the National Science Foundation (http://cns.bu.edu/CELEST/)
Dear Members,
I am a prospective graduate student interested in taking up Neural Engineering under EE or Biomedical Engg for research. But I have a lot of concerns and need help from a person who knows about the field well.
1. I have studied VLSI, DSP, Image Processing, Wireless Communication, Control Systems and Embedded Systems as graduate and undergraduate courses and have some research interest in Neural Networks and Machine Learning(That’s how I got interested in Neural Engg and Prosthetics). Which of these subjects will be of help in Neural Engg/Prosthetics research. Which will be of most relevance. Please list them in the order of relevance(high->low).
2. What are the applications of the research ?
3. What is the research and JOB scope for this field? Are there any companies who recruit people with this specialisation? How is the job scene in academia? How many univs are doing research in this field in US? Please let me know about the career progression in academia, like how much time does it take to get full time academic position after PhD?
4. Especially, what are the applications of this research in Robotics?
5. What are the current problems and research themes in universities?
6. What imaging technologies are used in this research?
Though my queries may seem a bit ameteuristic, it is very important for me to get clarity on these doubts.
Hope my queries will be answered.
Thanking all of you in advance,
sudhi
My website “Quad Nets: Device Models of Brains” is online at www.quadnets.com.
(link)
“Quad Nets” proposes a new kind of “artificial intelligence” that uses devices other than computers. Chiefly presented through Images, the Quad Net approach integrates physics, neuroscience and psychology in primal forms, initially rudimentary, but suitable for unlimited development in size and complexity.
I am an amateur and have privately worked in these areas for many years. Unfortunately, I have not found a means of communication through established channels. I hope that the readers of this blog will provide needed critical review. Thanks to the “neurodudes” for making this medium available.
Today MIT’s Technology Review magazine released its annual list of innovators under the age of 35 who were nominated for recognition. Interestingly, almost a full quarter are doing work relating to or impacting the field of neuroengineering — including ways to tag synapses with quantum dots, activate neurons remotely, improve machine vision, classify whole-brain states for prosthetic purposes, and make nanowire arrays.
Last year, the Redwood Center for Theoretical Neuroscience moved from the Redwood Neuroscience Institute in Meno Park to the Helen Wills Neuroscience Institute at Berkeley. In October they held a symposium with several interesting speakers presenting on various topics within Theoretical Neuroscience.
neurodudes is intended to be an open forum at the intersection of neuroscience and ai. regular readers are encouraged to post appropriate material. just follow the directions below and get the discussion started!
Neurodudes is moderated by Neville Sanjana, Bayle Shanks, and Stephen Larson. Comments that you post might be delayed so that we can tell our software that it's not spam -- however, not all comments are pre-screened so don't assume that we have read them, either. None of us are medical doctors so please don't ask for medical advice. Contact us here.
