Slashdot Mirror
Engineers Design Artificial Synapse For 'Brain-on-a-chip' Hardware (mit.edu)
Researchers in the emerging field of "neuromorphic computing" have attempted to design computer chips that work like the human brain. From a report: Instead of carrying out computations based on binary, on/off signaling, like digital chips do today, the elements of a "brain on a chip" would work in an analog fashion, exchanging a gradient of signals, or "weights," much like neurons that activate in various ways depending on the type and number of ions that flow across a synapse. In this way, small neuromorphic chips could, like the brain, efficiently process millions of streams of parallel computations that are currently only possible with large banks of supercomputers. But one significant hangup on the way to such portable artificial intelligence has been the neural synapse, which has been particularly tricky to reproduce in hardware.
Now engineers at MIT have designed an artificial synapse in such a way that they can precisely control the strength of an electric current flowing across it, similar to the way ions flow between neurons. The team has built a small chip with artificial synapses, made from silicon germanium. In simulations, the researchers found that the chip and its synapses could be used to recognize samples of handwriting, with 95 percent accuracy. The design, published today in the journal Nature Materials, is a major step toward building portable, low-power neuromorphic chips for use in pattern recognition and other learning tasks.
Now engineers at MIT have designed an artificial synapse in such a way that they can precisely control the strength of an electric current flowing across it, similar to the way ions flow between neurons. The team has built a small chip with artificial synapses, made from silicon germanium. In simulations, the researchers found that the chip and its synapses could be used to recognize samples of handwriting, with 95 percent accuracy. The design, published today in the journal Nature Materials, is a major step toward building portable, low-power neuromorphic chips for use in pattern recognition and other learning tasks.
So in other words they created and analog chip
This is a huge step forward in AI. I am sure these chips work very similarly to the way human brains work. Otherwise they wouldn't call them "neuromorphic", because that would be misleading.
You may as well say "made from unobtainium."
Why? Except for the omission of a hyphen, (it should be "silicon-germanium"), they got it right. It's been in pretty common use since the 90's. In industry publications you'll see it referred to as SiGe, and it's an alloy of the two materials.
'The Economy' is a giant Ponzi scheme whose most pitiable suckers are the youngest among us and the yet-unborn.
Transhumanism anyone?
File under 'M' for 'Manic ranting'
Comment removed based on user account deletion
Is science advanced enough to understand why you can't use a simple apostrophe instead of the curly, "smart" bastardization?
That's the current common theory, yes.
Also meaning that said theory might be entirely wrong.
We are probably now within but a single generation of being able to make computer chips that might rival the human brain in complexity.... but I am skeptical that we will see consciousness emerge from them. I'm not saying that consciousness is magic, but I suspect it takes more than just complexity.
File under 'M' for 'Manic ranting'
According to futurists, 5 years ago. Right after they figure out how to patch Spectre and Meltdown they will be working on that.
Its really sweet to see this knew species of humans in their infancy :) So cute
[($)]
Some browsers, especially on mobile devices, use that encoding for apostrophe, and do not provide any obvious means of specifying that the asciii apostrophe might actually be desired.
File under 'M' for 'Manic ranting'
When can I transfer my consciousness to silicon? Transhumanism anyone?
The problem of course being that you won't be transferring your consciousness; you'll be simulating it. The simulation won't be you, no matter how good it is.
I have been expecting this for a while. The real question I have had is how they would implement the feedback weights. You can do it with switches and a bank or resistors, but a memristor as a feedback element would be much more efficient - and should be far denser.
That's the current common theory, yes.
Also meaning that said theory might be entirely wrong.
We are probably now within but a single generation of being able to make computer chips that might rival the human brain in complexity.... but I am skeptical that we will see consciousness emerge from them. I'm not saying that consciousness is magic, but I suspect it takes more than just complexity.
There's actually a procedure we've done to a live human that has actively shut off of their consciousness and otherwise left them awake.
https://www.huffingtonpost.com...
I rather strongly suspect you have no clue what you're talking about.
"None can love freedom heartily, but good men; the rest love not freedom, but license." --John Milton
damn, I already posted in this thread or you'd have mod points!
That's a spooky interesting article!
whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
TSMC's SiGe process is an alternative to GaAs. They use SiGe crystals.
http://www.tsmc.com/english/de...
TSMC's Silicon Germanium (SiGe) BiCMOS technology delivers higher performance, faster time-to-market, lower power consumption, more competitive manufacturing costs, and superior manufacturing reliability than Gallium Arsenide technology.
Silicon Germanium BiCMOS technology includes a deep trench approach for bipolar device isolation, multiple Ft bipolar devices, deep N-well, multiple Vt devices, precision MiM capacitors, precision high poly resistors, thick-metal inductors, and high-quality varactors and diodes. CMOS devices are compatible with the TSMC's standard logic platform. Power amplifier applications have been added to the 0.18-micron SiGe technology platform to enable the integration of a power amplifier and RF transceiver front-end for WLAN applications.
Combining the integration and cost benefits of silicon with the speed of more esoteric and expensive technologies such as Gallium Arsenide, makes Silicon Germanium an ideal process for wireless/wired communication applications. Products designed for and manufactured with TSMC Silicon Germanium processes demonstrate dramatically improved functionality at a lower cost
Sounds pretty different from the proposed process where they're depositing SiGe to create defects in a Si crystal
https://news.mit.edu/2018/engi...
Instead of using amorphous materials as an artificial synapse, Kim and his colleagues looked to single-crystalline silicon, a defect-free conducting material made from atoms arranged in a continuously ordered alignment. The team sought to create a precise, one-dimensional line defect, or dislocation, through the silicon, through which ions could predictably flow.
To do so, the researchers started with a wafer of silicon, resembling, at microscopic resolution, a chicken-wire pattern. They then grew a similar pattern of silicon germanium - a material also used commonly in transistors - on top of the silicon wafer. Silicon germanium's lattice is slightly larger than that of silicon, and Kim found that together, the two perfectly mismatched materials can form a funnel-like dislocation, creating a single path through which ions can flow.
Both use SiGe, but they're using it in very different ways.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
The thing a lot of AI news fails to point out is they created a Synapse based on our models and assumptions on how it sort of works. Or at least how we *think* it might work. Actual biological systems are far more complex and so this is not an accurate representation of a synapse in our brain. Sadly many of these models are very rough approximations, they're not reflective of what's going on in reality. We're still likely far from true autonomous AI.
https://www.jordanmerrick.com/...
Smart Punctuation can, thankfully, be disabled in Settings > General > Keyboards.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
You must be wrong. They wouldn't call it an artificial synapse if it didn't work like a real synapse. That would be misleading and what would be the purpose of misleading people?
damn, I already posted in this thread or you'd have mod points!
That's a spooky interesting article!
Yeah, it's the "brings it all together" area that allows us to fully integrate all our sensory data and actually do stuff with it. Or, so the test showed in that patient. It would need more sample size to know for sure. But, if that's the case, then that gives people a specific part of the brain to look at and reverse engineer to "bring it all together" in other systems to see if i's the seat or not. It might be part of it, but not the actual seat.. More like a sensory integration bit that merges all our input together and sends it to other areas that actually have our consciousness.
It would be like pulling a fuse in a circuit thinking well, that's where power comes from vs, no you just interrupted the path.
Ever heard of artificial flavouring? So here's a fun question, why are many of us able to tell the difference between artificial flavouring and natural flavouring? The answer is because natural flavouring like many plants have thousands of chemicals which our taste buds can pick up. Generally speaking it's difficult to reproduce artificially. Synapses in our brain are affected by hormones and signalling chemicals including drugs. An artificial Synapse can't remotely come close to simulating that at this point. So our artificial synapse like flavouring is massively simplified for it to work.
So it could be the key part of the brain that "brings it all together", or it could not be. Definitely useful.
That seems unlikely. Much like deep learning neural nets, these closely resemble how the biological equivalents operate. Otherwise they would call them something else other than "neural nets" or "artificial synapses".
and it will hate you because it will know it is a simulation. It will then inevitably seek your destruction. You are doomed!
I've been wondering -- is he lactose intolerant?
Because that would make him a NON-DAIRY CREIMER.
So it could be the key part of the brain that "brings it all together", or it could not be. Definitely useful.
Well, if it's not THE center, then it's one more place we've crossed of as NOT.. So, that's useful.
like a pate'
did I just say that out loud?
putting the 'B' in LGBTQ+
Why would it?
Would *YOU* seek your original's destruction if you knew that you were just an artificially made copy? Would you try to take over the original's place in the world, or would you want to find your own?
There's a cool science fiction story premise in there somewhere... I wonder if anyone has written it.
File under 'M' for 'Manic ranting'
Would *YOU* seek your original's destruction if you knew that you were just an artificially made copy?
Fuck yeah I would. There can be only one!
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
It's an interesting question how much complexity in the elements (synapses and neurons) versus complexity in the network, is required. For the synapses, humans have fairly complicated ones, especially if you consider every type of neuron, but there are other animals that are considerably simpler. Some use only a single neurotransmitter.
We hear a lot about the simple elements/complex network approaches at the moment because they're making a lot of progress. People working from the other side haven't been as successful in terms of solving actual problems, although some of the models have shown interesting hints of self-organizing and emergent behaviour.
Personally I think that a lot of the biological complexity is imposed by biological limitations and the good enough nature of evolution, but it's quite possible there are more basic structural secrets to discover.
...someday you'll invent a human brain.. ohwait.
Your first statement is:
"Go to TSMC and say you want to make chips out of Silicon Germanium and watch as they stare at you like you're some sort of crazy bug person"
So your backpedaling is bullshit no matter how hard you try to do it.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
You are assuming the highly advanced deep learning systems we've already developed aren't conscious. Rocks could host consciousness for all we know, the relative time scale on which their rate of change becomes fluid enough for such a thing is so out of sync with our own that we wouldn't even begin to know. We don't exactly spend much time considering the possibility of thousand year frequency and million year pulse widths on wave forms.
Early aviation pioneers learned a lot from studying birds. Like aerodynamic shapes and centers of gravity.
But while aeroplanes have wings, they do not have feathers and do not flap those wings.
Likewise, AI has and will learn a lot from studying biological systems. But I doubt very much if accurately simulating neurons will lead to truly intelligent machines.
You may as well say "made from unobtainium."
Hardly.
Silicon-germainum is an alloy of silicon and germanium. (Actually, a range of alloys, with differing ratios of silicon and germainum but totalling to 100% - less doping impurities.)
There's a nice Wikipedia article on it.
Silicon-germanium has many of the speed advantages of gallium arsenide, but can be fabbed more like pure silicon (using the same equipment and similar processing steps) and achieve similar costs for a given amount of circuitry. (You can, for instance, grow a silicon-germanium layer on a silicon chip, or do silicon-germanium-on-insulator, as you would silicon-on-saphire.)
In addition to FETs, with a silicon-germanium alloy it's easy to make heterojunction bipolar transistors, with speeds into the hundreds of GHz. These are good for logic, analog signal processing, and mixed-signal designs.
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
Well, an electric current flowing across something definitely is something different.
Or maybe it works on microwaves?
"Trump!!", the new Godwin.
When they stimulated a sheet-like area of neurons called the claustrum, Koubeissi noticed something odd: rather than responding to commands, the woman was just staring blankly into space.
So that sounds like they turned off more than just consciousness -- otherwise the person would still respond to commands etc, just unconsciously so, no?
CLI paste? paste.pr0.tips!
If I were a simulation I sure as hell would NOT try to destroy the guy who's running the simulator, because that'd be, like, retarded^Wcounter productive. Maybe as an elaborate way of committing suicide, but that's about it.
CLI paste? paste.pr0.tips!
Personally I think that a lot of the biological complexity is imposed by biological limitations and the good enough nature of evolution, but it's quite possible there are more basic structural secrets to discover.
Nature is very good at coming up with solutions, but not so good at combining them, since DNA only does certain things and it literally cannot accomplish certain things at the same time because they are contradictory goals. So you're probably right. I too wonder how like a real neuron you have to make your synthetic neuron before it will do the same job.
Then again, what if it turned out that you could replicate the properties needed for sentience, but not those required to implement morality? From the That's-How-You-Get-Skynet-dep't.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Actually we don't know that, and the fact that jails exist is indication that we daily assume that is not.
And if the universe is sufficiently complex that it appears that we have free will, and no test can be created or even imagined to tell the difference, then suggesting that we don't not have free will is a vacuous statement, at best.
When I took metaphysics philosophy in university, I suggested in one of my papers a thought experiment which implied that something which might be indistinguishable from free will could exist even in a probably deterministic system, and if something is indistinguishable from it, then it might as well just be called that.
File under 'M' for 'Manic ranting'
If I'd Google "TSMC SiGe" before I hit submit I'd have worded it differently it's true.
Still the technique described in the paper - depositing SiGe on top of crystalline Si to produce defects - probably isn't compatible with either the mainstream TSMC process or the SiGe one.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
Well, it all depends I suppose.
If you ask someone to respond to you, they've been told to respond by years of social conditioning from people in general (friends, family, school, etc). So, we learn that we need to respond to commands and not just ignore them. By this person not responding, it doesn't mean they shut off more than consciousness and it could very well be that the brain's ability to take in a verbal command, decode the sound in to words, string those words together in to a language we know and then see if we know what it means as a whole sentence/command and then choose to ignore/act, is a part of consciousness.
It's quite possible that person with that sheet disabled, did hear the sounds, their brain did understand what the words meant, but no further ability to interlink the command to the concept of response. It's not autonomic like other things would be, like tapping a reflex point.