HP's "Memristor" Could Replace Transistors
HP's discovery could lead to AI that can see and understand speech.
The New York Times reports that a team of Hewlett-Packard scientists have designed an electrical resistor with memory properties called "memristor." The technology is simpler than existing transistors, and do not require a constant electrical current to retain information. Originally revealed in the science journal Nature Wednesday, the team believes that its new memory technology will lead to powerful yet extremely small computers that imitate biological functions.
The article covers different applications of memristor including to possibility of creating dense memory chips that use less power than DRAM memory chips of today. But the big bonus prize is that HP's technology can store and retrieve values outside the standard 1's and 0's--a vast array of intermediate values as the NYT claims--allowing the resistors to function like biological synapses.
With that said, this could be a breakthrough for artificial intelligence development, leading to a possible understanding of speech or actual machine "vision." R. Stanley Williams, director of the quantum science research group at H.P., believes that the memristor technology should become commercialized rather quick. "This is on a fast track," he said.
The group stumbled upon the new technology while looking for a new class of organic molecules to serve as nano-sized switches. The research, spanning decades, would eventually lead to switches the size of a single molecule, and take the place of electronic circuits made with photolithographic techniques. However the researchers instead found memory properties in thin spots of titanium dioxide, thus leading them to the current memristor technology today.
“I can see all kinds of new technologies and I’m thrilled,” Williams said. For the full article, head over to the New York Times here.
- New Unisys Enterprise Servers Support Intel Xeon
- Say Goodbye to the "I'm a Mac/I'm a PC" Ads!
- Dell Adds New Business Notebooks to E Series
- Business Warming Up to Windows 7, Cooling on XP
- New IBM Platform Rivals Oracle's Exadata
- TSA: We Don't Need to See Your Netbooks, Tablets
- IT Software Vendor, CA, to Cut 1,000 Jobs
- Windows 7 SP1 Beta Leaks to P2P; is Version 7601
- $259.60: Cost of Components to an iPad 16GB
- StarCraft II Special Edition to be Packed at $100
- Ford Turning Off PCs at Night to Save $1.2M
- Eight Pictures of the World's Stunning Datacenters
- Intel to Ship Experimental Chips With 48 Cores
- HP Releases Three More Pavilions for Desktop Line
- Thecus Expands NAS Line with N8800+ Rackmount
- Microsoft to Patch 25 Windows Vulnerabilities
- Alienware M11x to Get Optimus, New Intel CPUs
- Microsoft Shows Off Exchange 2010 SP1
If this gets patented like rambus then perhaps nobody will be interested.
Cylons!?
If this gets patented like rambus then perhaps nobody will be interested.
Agreed. I seriously doubt that would happen however.
Anyways, I expect this to become mainstream for CPUs in 5-10 years.
Cylons!?
No.
HAL 9000.
hmm, memristors are discovered in 2008?
http://www.hpl.hp.com/news/2008/apr-jun/memristor.html
No.
HAL 9000.
What are you doing, Dave?
hmm, memristors are discovered in 2008?http://www.hpl.hp.com/news/2008/apr-jun/memristor.html
Appearently "rather quick" is still much longer than 10 years. Either that or the technology was abandoned. Ideas anyone?
See speech?
For a list of developments in 2009 and 2010:
http://en.wikipedia.org/wiki/Memristor
could this be the first good thing from hp, ever? my first few hp's tell me otherwise.
HP will be buying google in 3 years.
hmm, memristors are discovered in 2008?http://www.hpl.hp.com/news/2008/apr-jun/memristor.html
That is correct, however according to BBC they just created the "working" stuff recently:
http://news.bbc.co.uk/2/hi/technology/8609885.stm
Protocol Droids!
Speech recognition and AI has never been a problem of technology. No amount of speed or capacity can compensate for the simple fact that science still does not understand how our minds "work." Both require the understanding of context; it's not just an exercise in brute force resolution of pattern matches and decision trees. This claim gets rehashed every couple of years and will continue to do so for the foreseeable future.
I've seen something good come from HP...
The money I've made fixing their shit.
I'm a cybernetic organism... living tissue over metal endoskeleton...
I'm having a real difficult time imagining software that can make use of a CPU (or RAM) composed of switches with more than two possible values.
As cool as C3PO is, I do not want to have a bunch of whiny robots running around talking about being doomed and bragging about abilities...
Cannot wait for Memristor based RAM. You switch off the computer, go to bed, turn it on in the morning, it is ready after 2 sec of initial Boot Up.
This is old news- "Published: May 1, 2008". I knew I read this somewhere before, scientific america I think. When I clicked on the link they posted, it shows the publishing date right at the top of each page. Proving my theory that Toms is running out of articles. Starting to look through old news. LOL.
Please see post by Shadow. They only created the working stuff recently.
how about the realistic practical applications...
loomis - fuzzy logic.
Skynet?
Nothing like a vague description, I was looking to see a structural diagram with doping levels and their material construction that can sustain saturation when no base current is flowing. Unless this is just another name for Zram(sounds like it anyways) technology that I read about 3-4 years ago in which this is not really a new concept and just a combination of a transistor and a capacitor as a single device and doesn't retain memory when off.
See speech?
I agree, but after reading it a 2nd time, I understood that it can see and it can understand speech.
I'm having a real difficult time imagining software that can make use of a CPU (or RAM) composed of switches with more than two possible values.
As you should. As we all should. This means more than just smaller, faster, computers. This means that computers no longer have to be digital. They can essentially be analog, like us.
NOOOOOOOOOOOOOOOOOO!!!!!!!!!!!!! SKYYYYYYNEEEEEEEEEETTTTTTT!!!!!!!!!!!!
T600 then T800 NOOOOOOOOOOOOOOOOOOOOOOO!!!!!!!!!!!
I, Robot !!!?
Protocol Droids!
Geth
Helios.
No, if this tech DOESN'T get covered up for 50 years as to not destabilize the current status quo of the tech market it could lead to something cool. Call me a skeptic, but so much good tech has been buried for financial reasons in the last decades of technological improvement that it's not worth mentioning.
This is old news- "Published: May 1, 2008". I knew I read this somewhere before, scientific america I think. When I clicked on the link they posted, it shows the publishing date right at the top of each page. Proving my theory that Toms is running out of articles. Starting to look through old news. LOL.
Why was this guy voted down? He's right. The least that could have been done is a little research and including info from the BBC article.
http://news.bbc.co.uk/2/hi/technology/8609885.stm