I've read part of John Harris' blog/book, but I stopped after a couple of chapters because it is purely hypothetical rambling, with only a passing basis in neuroscience or what we know about neurons and the brain. To be fair, it's not really intended to be realistic though. It is intended to be a hypothetical meandering into how we might build a brain from scratch, ignoring biology, assuming we could engineer a better solution than evolution was able to produce."This book is about what would happen if, as a thought experiment, we were to rewire the human nervous system using a multichannel neuron. It explores the impact of this hypothetical "smarter" neuron on vision, memory and the brain."
Regarding "How to Build a Brain", it's on my reading ToDo list, thought I am somewhat familiar with it's content, having worked a fair amount with the Nengo simulator and having studied the Spaun model in depth before I came to the NUPIC project. There is quite a bit of information about their approach on the nengo.ca website as well (without having to purchase the not-so-inexpensive book). I find Chris Eliasmith's approach very appealing and likely to succeed, but being a spiking neuron model it is extremely resource intensive. Using the initial Spaun model (which is a highly simplified model of just a few brain structures) it takes about 2.5 hours of processing time to simulate one second of real-time. Therefore, it's a promising approach for brain emulation, but not really suitable for machine learning applications. For running neural simulations it's not nearly as realistic as some others (such as Nest, NEURON or Genesis), but it has an easy to use GUI interface for building experimental networks so it's definitely work checking out if you want to dip your toes into computational neuroscience. On Mon, Mar 31, 2014 at 7:36 PM, David Ragazzi <[email protected]>wrote: > My professor during my MSc program also recommended Chris Eliasmith's > papers as above mentioned.. His talk on TED: > > https://www.youtube.com/watch?v=g2HHJfovb5E > > > On 31 March 2014 21:20, Chetan Surpur <[email protected]> wrote: > >> The full comment [1] is a useful read: >> >> Let a thousand flowers bloom >> >> On academic researchers having reservations about Hawkins approach, let >> me say it's not all of us. >> >> I was doing my M.Sc. in Computer Intelligence by the time *On >> Intelligence* was launched, and I have since followed his work with keen >> interest. My M.Sc. professor's work is centred on Weightless Neural >> Networks, a model largely developed in the UK which share many ideas with >> Sparse Distributed Memory, so Hawkin's Cortical Learning Algorithm isn't >> that alien to me. In fact I'm just now reviewing the CLA white paper with a >> view to get some ideas for my Ph.D. research. >> >> Besides Hawkin's work, in the last years there have been other attempts >> at modelling the brain that deserve mention. >> >> Chris Eliasmith's work on the Neural Engineering Framework (NEF) and >> Semantic Pointer Architecture (SPA) is based on perceptron-like neurons and >> gives more emphasis to pre-cortical brain structures. It's also more >> academic-friendly, with a number of peer-reviewed papers published. He >> recently published a book compiling the current state of his programme, How >> to Build a >> Brain<http://www.amazon.com/How-Build-Brain-Architecture-Architectures/dp/0199794545>, >> and maintains a web page for his Nengo <http://nengo.ca/> neural >> simulator. >> >> John Harris' Rewiring Neuroscience<http://www.rewiring-neuroscience.com/> is >> an intriguing, highly heretical work that starts with a seemingly >> out-of-the-blue assumption (what if neural output isn't a single bit, but >> can in fact convey a range of values) and from that draws together a number >> of overlooked results and fringe research into a surprisingly appealing >> model of brain function. I have tried to >> implement<https://www.researchgate.net/publication/225066202_A_Biologically-Based_Image_Template-Matching_Framework> >> some >> of his ideas with limited but encouraging results. >> >> I can't speak for other researchers, but personally I rather like all >> this work on AI and computer intelligence coming from private companies. >> Frankly, let to its own devices, academia does tend to drift around, and I >> think the private sector's need for results and solutions to practical >> problems is an important counterweight to this tendency. With the current >> interest in architectural models of intelligence, and the "coopetition" >> between companies and universities to achieve fulfilling implementations, >> maybe we can make Ray Kurzweil's 2030's deadline? >> >> >> I want to read John Harris's book, and will start it soon. >> >> Has anyone read the other book mentioned in the comment (How to Build a >> Brain)? >> >> [1] >> http://forums.theregister.co.uk/forum/1/2014/03/29/hawkins_ai_feature/#c_2148782 >> >> >> On Mon, Mar 31, 2014 at 12:03 AM, Vinh <[email protected]> wrote: >> >>> In the comment section, a guy mentioned John Harris and his book: >>> http://www.rewiring-neuroscience.com/ >>> >>> Is there anyone who has read his book and his research? What do you >>> think of his works? >>> >>> >>> >>> >>> On Sunday 30,March,2014 06:47:10 AM SGT, Chetan Surpur wrote: >>> >>>> This is a pretty good overview on the history and approach Numenta is >>>> taking towards machine intelligence. It's nice to see such balanced >>>> and forward-thinking coverage :) >>>> >>>> >>>> On Sat, Mar 29, 2014 at 2:09 PM, Viraj Sinha <[email protected] >>>> <mailto:[email protected]>> wrote: >>>> >>>> The Register published an extensive article on Jeff, goals for >>>> Numenta, and how Numenta relates to other machine learning >>>> approaches such as Vicarious. Check it out: >>>> >>>> http://www.theregister.co.uk/2014/03/29/hawkins_ai_feature/ >>>> >>>> >>>> _______________________________________________ >>>> nupic mailing list >>>> [email protected] <mailto:[email protected]> >>>> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >>>> >>>> >>>> >>>> >>>> >>>> _______________________________________________ >>>> nupic mailing list >>>> [email protected] >>>> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >>>> >>> >>> >>> >>> _______________________________________________ >>> nupic mailing list >>> [email protected] >>> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >>> >> >> >> _______________________________________________ >> nupic mailing list >> [email protected] >> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >> >> > > > -- > David Ragazzi > OS Community Commiter > Numenta.org > -- > "I think James Connonly, the Irish revolutionary, is right when he says that > the only prophets are those who make their future. So we're not > anticipating, we're working for it." > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
