Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
AI Hardware Technology

'Memtransistor' Brings World Closer To Brain-Like Computing 94

the gmr writes: According to a recent article published in the journal Nature, researchers at Northwestern University's McCormick School of Engineering have developed a "memtransistor," a device that both stores information in memory and processes information. The combined transistor and memory resistor work more like a neuron and purports to make computing more brain-like. The new "memtransistor" would use less energy than digital computers and eliminate the need to run memory and processing as separate functions while also being more brain-like. Lead researcher Mark C. Hersam clarified the brain-like efficacy of the memtransistor: "...in the brain, we don't usually have one neuron connected to only one other neuron. Instead, one neuron is connected to multiple other neurons to form a network. Our device structure allows multiple contacts, which is similar to the multiple synapses in neurons... [but] making dozens of devices, as we have done in our paper, is different than making a billion, which is done with conventional transistor technology today." Hersam reported no barriers to scaling up to billions of devices. This new technology would make smart devices more capable and possibly more seemingly-human. The devices may also promote advances in neural networks and brain-computer interfaces, new technologies also recently reported at Futurism.
This discussion has been archived. No new comments can be posted.

'Memtransistor' Brings World Closer To Brain-Like Computing

Comments Filter:
  • Comment removed (Score:5, Informative)

    by account_deleted ( 4530225 ) on Sunday February 25, 2018 @08:30PM (#56185659)
    Comment removed based on user account deletion
    • by postbigbang ( 761081 ) on Sunday February 25, 2018 @09:45PM (#56185749)

      The problem with the passive components is the same as it's always been, and why Von Neumann idealized state machines as computing elements. Adding a state value helps, but causes multiple concurrent states.

      Memtransistors don't have checksums, and their state isn't arbitrated in such a way as to give them the capacity to be shared without other active components. Because there is no checksum or CRC easily possible, coupled to the logic that sets (and checks) their value, means that they have limited architectural applications until several facets of their nature can be changed.

      Look at 100 people, and 33 of them have faulty neurons. Analogizing states in this way, memtransistors, could also be capacitive arrays, inductive arrays, LC/LCR arrays, and so forth. Their present state of changeability comes nothing close to the high speed memory (transient and charged state--think nv-ram) present today.

      There are great potential applications in ASICs, (fp) gate arrays, and other constructions, but just as GPUs don't replace CPUs, arrays made of memtransistors aren't going to replace either CPUs or GPUs, FPGAs, ASICs, etc. They're not more "brain-like", rather, they're a different architectural models whose limitations still haven't been surmounted.

      It's not a fully passive device-- it's a resistor with a third leg in terms of boolean logic.

      • I have the distinct impression that the above jibberish spew was composed by a buzz word compliant hidden markov model.

        • Comment was obviously written by a bot using AI running on a memristors platform, as a demonstration of the technology.
      • It's not a fully passive device-- it's a resistor with a third leg in terms of boolean logic.

        Before you post something so bafflingly irrelevant maybe re-read the parent's post and wikipedia article. Start with the 5th word in the post title.

        • I read both of those. This is a logic gate, a resistor that looks like a standard logic element transistor. If you want to be less baffled, look into electronics engineering as it applies to both computing, and also the history of how microcomputers were originally designed against the state machine model(s).

          • I read both of those. This is a logic gate, a resistor that looks like a standard logic element transistor. If you want to be less baffled, look into electronics engineering as it applies to both computing, and also the history of how microcomputers were originally designed against the state machine model(s).

            CORRECT.

            1T1C (or any two-terminal implementation of a non-volatile memory element) is a goal of extreme interest for the big CMOS foundries. Density!

            I believe that it is still 2T2C available on the market, but RAMtron is likely to have fixed that a while ago. It was a hot topic in 2000.

          • You clearly never red Von Fredircks fifth postulate of public discourse, please read Willhems essayist, and rodgers publik speaking and it's effect on reason, or sargentzi's Das Discobolus in the original German before you recommend better educations to people ob slashdot.

          • This is a logic gate

            So you DIDN'T read it then. A memristor doesn't have a gate. It's a 2 terminal passive device.

            Keep trying. You'll get there eventually.

    • by SumDog ( 466607 )

      Yea I found this summary pretty sensational. I've heard the term you used, "memristors," and how HP was working on them a few years back. I might have understood the concept wrong though. Typically memory is where you store data and registers are units on the processor that act on that data (add, subtract, bitshift, or more complex instructions).

      As I understood it, memristors would allow instructions to operate directly on memory without having to load or store. If you had enough memristors to load your pro

      • Yea I found this summary pretty sensational. I've heard the term you used, "memristors," and how HP was working on them a few years back. I might have understood the concept wrong though. Typically memory is where you store data and registers are units on the processor that act on that data (add, subtract, bitshift, or more complex instructions).

        As I understood it, memristors would allow instructions to operate directly on memory without having to load or store. If you had enough memristors to load your program into them, you'd effectively run everything incredibly fast in place. However this would change the entire way we write programs and compilers.

        You'd probably no longer have a stack, the purpose of a program counter would change entirely, and you'd start to get into the very gritty details of immutability and self modifying code. . .

        Zero boot-up time! Zero program-loading time! Everything resident in storage is de facto resident in memory, if your Memristor storage is equal to your RAM in size, and are one and the same, then you can do general computing at closer to L3 to L1 cache speeds! Vroom!

        Oh, this would open huge new security holes now, wouldn't it? Hmmn.

        I imagine that there would be some kind of redundancy built-in --- You don't want your code or purchased apps being altered after installation! Pernicious worms/virii hidde

    • by gweihir ( 88907 )

      Except that a memresistor is not really a passive component as it has state. And there is no "missing" passive component either. I don't know why this obvious BS is being repeated and repeated all over the place. A great success for marketing nonsense, a great loss for actual truth in engineering.

      • by mark-t ( 151149 )

        Except that a memresistor is not really a passive component as it has state.

        So I suppose you think capacitors are not passive either, then?

        Or do you think that retention of charge doesn't count as "state"?

        You may find that your own definition of active vs passive components is not the same as the actual one.

        • by gweihir ( 88907 )

          A capacitor does not have state. It has a potential charge, but that level is not dependent of its history. The history just somehow has to provide that charge, but it is completely irrelevant how it was provided. Furthermore, a capacitor's charge does not influence its behavior (voltage change on charge-change). That is up to a point, of course. When you reach the breakdown voltage, a capacitor does indeed become an active element for a brief time. As this is outside of normal operating parameters, it is n

      • The sad truth is that the marketing wank is what funds the engineering.

      • Except that a memresistor is not really a passive component as it has state. And there is no "missing" passive component either. I don't know why this obvious BS is being repeated and repeated all over the place. A great success for marketing nonsense, a great loss for actual truth in engineering.

        The actual article was sensationalistic. All they did was implement a hybrid memristor (assumed, TL;DR) incorporated with a transistor. So they combined two of the four basic circuit components into one with two leads. Big deal --- Ancillary circuitry will be needed to send "write" currents sometimes, and "read" voltages other times. Those must be put somewhere on the die.

        Call the memristor a passive component if you want. The fact is, though, that a memristor can be "set" to a certain resistance, mean

    • Yeah, but because we're all stupid now Futurism has a to write the clickbait article as 'new magic component will lead to ELECTRONIC BRAINS'. As if the problem of AI is going to be solved by some low level component as opposed to understanding the high level organisation.

      • Please call me when somebody gets to artificial neural networks again. There are some interesting conjectures I'd like to make so as to see the response from better-informed than I.
    • What exactly is "passive" on/in a capacitor or inductor?

      • They just stay where you put them.
      • Capacitors and inductors don't directly modify voltage or current; Rather they store energy. The way in which they do is essentially reciprocal. An inductor stores the energy as a magnetic field, which then collapses when current falls off. This collapse puts energy back into the circuit. In essence, it effectively creates an effect analogous to storing momentum if this were applied to plumbing or hydraulics.

        Capacitors store charge by blocking flow and accumulating charge up to their "capacity" with a volta

        • I'm not sure, but I think I learned that in 7th grade, thank you for the fresh up.
          Did you answer to the wrong person?

          P.S. non of your explanations has anything to do with active/passive (for me at least ;D )

  • by Anonymous Coward

    Timeouts, pages hanging... 40x/50x status codes ...what's the deal?
    Whole website is dog slow and seems to be getting worse. Not that management cares, but this is usually what precedes a total failure.

    Anybody seen this too?

    • Yup, Bad Gateway errors for awhile now. Not timeouts (504) just plain 502 no one there. Coming off the RSS feed seems to be worse...
    • by HiThere ( 15173 )

      Yes. Just timeouts, but lots of them for the last several days. At first I suspected a ddos, but then they went down for maintenance, and when they came back up it was worse. Maybe someone's mining bitcoins on the site.

    • Perhaps they're using a new server that runs on memristors.

      "Okay, what's two plus two?"

      -thinks- "... two."

      "What happened to the other two?"

      "... I forgot about it.

      • Perhaps they're using a new server that runs on memristors.

        "Okay, what's two plus two?"

        -thinks- "... two."

        "What happened to the other two?"

        "... I forgot about it." [emphasis mine]

        That sounds more like a quantum-computer's q-bit effect. Although, DRAM capacitors do indeed have to be re-written after their state is read, so I guess it applies in your example.

        A memristor is a two-terminal device, and can be used in logic in this form, but with the added overhead of combining write-lines w/read-signal lines. . . and the same thing with reading it, ostensibly, is an oopsie could erase the persistent state of the memristor bit. I'm not a circuit designer, so can say nothing about whic

    • by TheRaven64 ( 641858 ) on Monday February 26, 2018 @05:17AM (#56186705) Journal
      Yup. SourceForge has also been suffering, so I imagine that the 486 in the corner that's handling both sites is now completely full of dust.
    • Timeouts, pages hanging... 40x/50x status codes ...what's the deal? Whole website is dog slow and seems to be getting worse.

      The FCC revocation of Net Neutrality got published last week, so ...

  • Nobody knows how the brain works. In fact, the closer we look and the more we know, the more mysterious its workings become. Claiming to bring anything "closer" to its working is a direct lie.

    • We have a pretty good idea of how neurons work and behave individually and also some brain components are understood up to a point - eg visual system which has allowed some pretty good advances in artificial neural networks. However how individual systems in the brain link up and produce a conciousness - the ghost in the machine - is still frankly anyones guess. There are lots of idea but nobody really has a clue yet.

  • How is this different than HPs memristor from a decade ago?

    • by dohzer ( 867770 )

      Completely different. This is a memTrANSistor

    • How is this different than HPs memristor from a decade ago?

      The memristor was first theorized as the 'fourth basic electronic component' in a paper in the 60's or 70's.

      HP gets credit for being first-to-market (with a sub-optimal active-layer material). But, of course, they ran with the material that they had Patent protection for. That keeps their marketplace lead open for a while... Hopefully, they figure out the next leap before everyone catches up with them. (That did not happen.)

  • CyberDyne Systems announces their new "Neural Net CPU". Based on recent breakthroughs of quantum computing and memtransistors, the combination of these technologies promises "many more computations can be done each second, quadrillions of switching positions are possible, many of them simultaneous at each quantum level."
  • Another millimeter in a race the distance of which we have yet to understand?
  • I am a nanotechnologist, and this is the BS typical of our field.

    The effect they're looking at is reversibly changing the gate properties of the transistor by carefully spiking the voltage on one input. This is something you can do with a silicon transistor; the magnitude and reproducibility of the effect is driven by the defect density and thickness of the gate oxide. It's temperature dependent, atmosphere dependent... all this stuff is very scientifically interesting, there are a lot of papers and PhD th

Don't tell me how hard you work. Tell me how much you get done. -- James J. Ling

Working...