Design Con 2015
Breaking News
News & Analysis

Qualcomm Reveals Neural Network Progress

10/11/2013 03:40 PM EDT
2 saves
More Related Links
View Comments: Oldest First | Newest First | Threaded View
<<   <   Page 3 / 3
Frank Eory
User Rank
Re: NPU for automotive?
Frank Eory   10/15/2013 7:31:14 PM
To be effective in almost any application, the learning and unlearning needs to be continuous. And yes, unlearning incorrect responses is just as important as learning correct responses.

User Rank
Re: NPU for automotive?
Etmax   10/15/2013 8:17:04 PM
Very true, a lot of humans don't do that well :-(

User Rank
Re: Neural network hardware
jaybus0   10/17/2013 11:04:00 AM
First, I'd like to mention that NN chips will be another processor type in a heterogeneous processor system. Like human brains, ANN chips will not be very fast at solving matrix equations and other deterministic problems. Instead they are good at learning to be decision makers, or in other words they can "solve" NP-complete (Nondeterministic Polynomial time) problems, (like the travelling salesman problem you mention), in a much more efficient way than Harvard architecture computers.

Must they be analog? A good question. Another is, must they be electronic at all? There is a need for the synaptic connections to be analog, or at least to carry a variable signal. Whether electronic or photonic, the signal energy is in fact quantized, and so perhaps there is no such thing as true analog and the only possible signal is a discrete one. As the trace sizes get smaller and smaller, so does the possible number of discrete signal levels. In any case, we don't know how many signal levels are necessary for a usable ANN. Perhaps a relatively small number of signal levels is sufficient, in which case digital synaptic connections are plausible.

Jayna Sheats
User Rank
Re: Neural nets and experience stores
Jayna Sheats   10/17/2013 12:33:17 PM
DrQuine:  your points are well taken; after all, an artificial neural network (if successful) is going to have a lot of the same characteristics as a biological one (some of which are just the ones you list!).  In the spirit of the mixed system mentioned above, I would say that the best way to use neural network processors is as a feed to a final digital system.  Refer again to the TSP: Hopfield's op amps can get the best million (roughly) solutions to a 30-city tour in a few microseconds, but can't go beyond that.  But a digital system can now evaluate a million tours very easily (unlike the 10^30 original possibilities).  The same principle could be used for image recognition.

<<   <   Page 3 / 3
EE Times Senior Technical Editor Martin Rowe will interview EMC engineer Kenneth Wyatt.
Top Comments of the Week
Like Us on Facebook Parts Search

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