TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Neural network chip built using memristors

149 pointsby Grognakabout 10 years ago

12 comments

themeekabout 10 years ago
This is one of the exotic devices in DARPA&#x27;s UPSIDE competition for exascale computing. This initiative seeks to find non-state (non-transistor) based approaches to computation: exploitation of nanoscale response properties of discrete components to perform some restricted, non-binary, forms of computation. Essentially, exotic ways to abuse silicon lithography to get analog computation.<p>The idea, and this can be seen on DARPA&#x27;s slides (<a href="http:&#x2F;&#x2F;www.darpa.mil&#x2F;workarea&#x2F;downloadasset.aspx?id=2147485714" rel="nofollow">http:&#x2F;&#x2F;www.darpa.mil&#x2F;workarea&#x2F;downloadasset.aspx?id=21474857...</a>), is to get computation that is several orders of magnitude higher for their specialized sets of problems than what can theoretically be reached by traditional computing models even if Moore&#x27;s law continues.<p>DARPA would like to first apply this technology to ARGUS drone systems (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=QGxNyaXfJsA" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=QGxNyaXfJsA</a>) and related technology because streaming video can&#x27;t be done to the ground, tracking and decision making must be done on board - yet traditional processing platforms can only track a few orders of magnitude fewer targets that what the military would like.<p>In a more advanced phase, if memristor or coupled oscillator (etc) approaches to building inference models become possible, then programs written in DARPA&#x27;s other initiative (Probablistic Programming) could be programmed into these exotic solid state devices to compute in a way more analogous to today&#x27;s generic computation. And indeed, eventually the adoption of Probablistic Programming will train programmers to write code for quantum computers - while more complicated, replacing Probablistic Programming&#x27;s PDFs with probability amplitudes almost get one there.<p>I hope to see more journalistic coverage of some of the other exotic devices.
评论 #9504063 未加载
评论 #9503454 未加载
评论 #9507797 未加载
评论 #9503847 未加载
FractalNerveabout 10 years ago
I&#x27;m very excited about this! Is there any possibility for me to work in a company working on similar stuff? That would make a dream come true for me! I live in Germany and would love to write my masters thesis a related topic!<p>This is so amazing! Btw. I have found an HP Invent sign in my town, but the security guard didn&#x27;t answer any questions about it. The only thing he said was that I won&#x27;t find any address or telephone number for it. That made me curious, because HP is working on a memristor based Computer, but I doubt that they produce it in Germany.
评论 #9502833 未加载
superfxabout 10 years ago
Link to original paper: <a href="http:&#x2F;&#x2F;rdcu.be&#x2F;cJ0x" rel="nofollow">http:&#x2F;&#x2F;rdcu.be&#x2F;cJ0x</a>
评论 #9502388 未加载
mericabout 10 years ago
A neural network chip semi-conductor startup: <a href="http:&#x2F;&#x2F;brainchipinc.com&#x2F;technology&#x2F;" rel="nofollow">http:&#x2F;&#x2F;brainchipinc.com&#x2F;technology&#x2F;</a><p>They &quot;backdoor listed&quot; on to an Australian mining company, share price went from 1 cent to 27 cents: <a href="https:&#x2F;&#x2F;www.google.com&#x2F;finance?cid=11163357" rel="nofollow">https:&#x2F;&#x2F;www.google.com&#x2F;finance?cid=11163357</a><p>Valued at $57m.
评论 #9503506 未加载
p1eskabout 10 years ago
Memristor crossbars are exciting even outside of neural network applications: it can be used as a very dense, non-volatile memory. If this design can be scaled up, it could potentially replace both flash memory storage, and RAM.
评论 #9503210 未加载
noobiemcfoobabout 10 years ago
I have nothing to say but that this is a cool application of memristors. My graduate research is in cognitive computing and the thought of using circuitry to represent the synaptic weights as opposed to hardware&#x2F;software based adders and multipliers is pretty awesome.
Loziabout 10 years ago
The general theory of memristors, meminductors, memcapacitors of any order (first order memristor is the genuine one invented in 1971 by Professor Leon Chua, however he generalized recently his discover to second, third order memristor, etc.)is published in a paper I wrote with him on september 2014 in International Journal of Bifurcation and Chaos. One can download it freely from the site <a href="https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;261676241_MEMFRACTANCE_A_MATHEMATICAL_PARADIGM_FOR_CIRCUIT_ELEMENTS_WITH_MEMORY" rel="nofollow">https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;261676241_MEMFRACTA...</a>
chimtimabout 10 years ago
This looks cool but I&#x27;m somewhat skeptical. I would be more interested in seeing what problem the system solves better or decently (say even MNIST) rather than how it was built using memristors.<p>There is a lesson from IBM trying to mimic a rat&#x27;s brain -- that is you try to solve a problem rather than just burn power.
评论 #9502872 未加载
return0about 10 years ago
The technology sounds very promising but if the goal is to simulate the brain, the ANN models we have today are inadequate. Current evidence suggests that it needs to incorporate dendritic dynamics and , soon, molecular computation.
评论 #9503949 未加载
peter303about 10 years ago
Memristers are supposed to be the main memory of HP&#x27;s future computing project called The Machine. It is supposed to be as fast as register memory and compact as flash.
CamperBob2about 10 years ago
Lemme know when I can order a few on cut tape from DigiKey.
评论 #9502474 未加载
andylabout 10 years ago
&quot;Even on a 30 nm process, it would be possible to place 25 million cells in a square centimeter, with 10,000 synapses on each cell. And all that would dissipate about a Watt.&quot;<p>Wow - seems like a lot.<p>Human brain by comparison (sourced by google): - 12 watts - 100 billion neurons - 1000 trillion connections<p>Computing with memsisters is going to be very interesting.
评论 #9503349 未加载
评论 #9502326 未加载
评论 #9502317 未加载