Breaking News
News & Analysis

IBM demos cognitive computer chips

8/18/2011 04:01 AM EDT
28 comments
NO RATINGS
Page 1 / 2 Next >
More Related Links
View Comments: Newest First | Oldest First | Threaded View
Page 1 / 3   >   >>
Zuben
User Rank
Author
re: IBM demos cognitive computer chips
Zuben   1/17/2012 5:49:05 PM
NO RATINGS
You seem to be confused regarding the difference between programming a computer to beat people at Pong (which obviously happened when the Pong console came out) and having a computer learn to do the same thing. That's fine; being confused is fine. Matched with your arrogance, however, and your confusion becomes tiresome.

allinenriq
User Rank
Author
re: IBM demos cognitive computer chips
allinenriq   8/24/2011 6:57:17 AM
NO RATINGS
Say thanks a lot for your time and effort to have put these things together on this blog. Mary and I very much loved your ideas through the articles on certain things. http://www.elektronische-zigarette24.de elektrische Zigarette

Amir Rahat
User Rank
Author
re: IBM demos cognitive computer chips
Amir Rahat   8/21/2011 8:41:46 AM
NO RATINGS
So little progress has been made since 1957 and the Perceptron! See the original papers or check out Wiki http://en.wikipedia.org/wiki/Perceptron

TFCSD
User Rank
Author
re: IBM demos cognitive computer chips
TFCSD   8/20/2011 9:25:55 PM
NO RATINGS
There are a few morons (managers) who could use a few more neurons. Could these chips be used on the pointy haired boss so he can understand Dilbert the engineer?

resistion
User Rank
Author
re: IBM demos cognitive computer chips
resistion   8/19/2011 10:03:35 PM
NO RATINGS
That's an interesting implementation there, Ron. I wonder if there is also any overlap there with memristors.

Charles.Desassure
User Rank
Author
re: IBM demos cognitive computer chips
Charles.Desassure   8/19/2011 8:27:06 PM
NO RATINGS
Thanks for this article. I think IBM is on to something big here.

R G.Neale
User Rank
Author
re: IBM demos cognitive computer chips
R G.Neale   8/19/2011 5:14:08 PM
NO RATINGS
I have just been asked to explain the final sentence in my posting above, there was a typo. It should have read: "However, that path tends to lead to the conclusion that CBRAM might offer a superior solution." I meant the Conducting Bridge RAM, that offers, by electrochemical action the precision to add and remove individual layers of atoms. Without that is the need for melting, high temperatures and high current densities associated with "reset" in conventional PCM. Apologies.

resistion
User Rank
Author
re: IBM demos cognitive computer chips
resistion   8/19/2011 1:21:38 PM
NO RATINGS
Ok it's just SRAM and CPU, specifically wired, apparently. http://www.scientificamerican.com/article.cfm?id=inside-ibms-cognitive-chip

entity279
User Rank
Author
re: IBM demos cognitive computer chips
entity279   8/19/2011 7:19:19 AM
NO RATINGS
Implementation aside, why is this any better than any regular (software, hardware or.. FPGA) ANN?

resistion
User Rank
Author
re: IBM demos cognitive computer chips
resistion   8/19/2011 6:21:59 AM
NO RATINGS
I think I missed something, such as how the neurons are implemented. Phase change? Charge accumulation?

Page 1 / 3   >   >>
Most Recent Comments
michigan0
 
SteveHarris0
 
realjjj
 
SteveHarris0
 
SteveHarris0
 
VicVat
 
Les_Slater
 
SSDWEM
 
witeken
Most Recent Messages
9/25/2016
4:48:30 PM
michigan0 Sang Kim First, 28nm bulk is in volume manufacturing for several years by the major semiconductor companies but not 28nm FDSOI today yet. Why not? Simply because unlike 28nm bulk the LDD(Lightly Doped Drain) to minimize hot carrier generation can't be implemented in 28nm FDSOI. Furthermore, hot carrier reliability becomes worse with scaling, That is the major reason why 28nm FDSOI is not manufacturable today and will not be. Second, how can you suppress the leakage currents from such ultra short 7nm due to the short channel effects? How thin SOI thickness is required to prevent punch-through of un-dopped 7nm FDSOI? Possibly less than 4nm. Depositing such an ultra thin film less then 4nm filum uniformly and reliably over 12" wafers at the manufacturing line is extremely difficult or not even manufacturable. If not manufacturable, the 7nm FDSOI debate is over!Third, what happens when hot carriers are generated near the drain at normal operation of 7nm FDSOI? Electrons go to the positively biased drain with no harm but where the holes to go? The holes can't go to the substrate because of the thin BOX layer. Some holes may become trapped at the BOX layer causing Vt shift. However, the vast majority of holes drift through the the un-dopped SOI channel toward the N+Source,...

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
Like Us on Facebook
EE Times on Twitter
EE Times Twitter Feed