All very interesting, but the information seems to suggest a bottom-end frequency response of a few hunred Hz. The figures, at least, seem to stop at 400Hz.
Now... 400Hz is quite high really. For the musically inclined, concert A is 440Hz. Off the top of my head that's significantly higher than the fundamental frequencies involved in, say, male speech. Until they can get that extended down to somewhere closer to 150Hz (remember - this is logarithmic so one octave is a doubling / halving of frequency) I would think there will be difficulties in using it.
Nick.
PS - Did anyone count the number of `TM's around the place!!
Good points! Many people still have the idea of a neural network as a `magic' solution to problems (just throw your data at a network and hey presto! it'll magically `learn' the right answer...).
Although the original work on neural networks was (in part) biologically inspired this soon became more of a hindrance than a help. These days, although there is work being done in computational neurology, most of the areas where neural networks are used for practical problem-solving treat them as a statistical method.
In reading the article you need to forget ideas about aritificial intelligence and the like. This sounds like a standard net implemented in hardware which means that training on larger datasets may be possible. However, this (as pointed out before) is the BIG problem --- training is difficult.
Anyway... basically there are a lot of rather out-dated perceptions about the use of neural nets floating around. When it comes down to it, a NN is just a non-linear function.
Read the name under which the submission was made.
Crackers don't make money, Hackers need new name
on
"Hackers" are Dumb
·
· Score: 1
Personally I'd go for `software engineer'. I like it, employers like it, the media like it, it sums up what I do (including all the bits about taking design decisions to produce a working solution quickly --- that's why it's software engineer and not computer scientist... that's my opinion anyway).
Slashdot Mirror
All very interesting, but the information seems to suggest a bottom-end frequency response of a few hunred Hz. The figures, at least, seem to stop at 400Hz.
Now... 400Hz is quite high really. For the musically inclined, concert A is 440Hz. Off the top of my head that's significantly higher than the fundamental frequencies involved in, say, male speech. Until they can get that extended down to somewhere closer to 150Hz (remember - this is logarithmic so one octave is a doubling / halving of frequency) I would think there will be difficulties in using it.
Nick.
PS - Did anyone count the number of `TM's around the place!!
Good points! Many people still have the idea of a neural network as a `magic' solution to problems (just throw your data at a network and hey presto! it'll magically `learn' the right answer...).
Although the original work on neural networks was (in part) biologically inspired this soon became more of a hindrance than a help. These days, although there is work being done in computational neurology, most of the areas where neural networks are used for practical problem-solving treat them as a statistical method.
In reading the article you need to forget ideas about aritificial intelligence and the like. This sounds like a standard net implemented in hardware which means that training on larger datasets may be possible. However, this (as pointed out before) is the BIG problem --- training is difficult.
Anyway... basically there are a lot of rather out-dated perceptions about the use of neural nets floating around. When it comes down to it, a NN is just a non-linear function.
Please, please, please...
Read the name under which the submission was made.
Personally I'd go for `software engineer'. I like it, employers like it, the media like it, it sums up what I do (including all the bits about taking design decisions to produce a working solution quickly --- that's why it's software engineer and not computer scientist... that's my opinion anyway).
Perhaps that's a little tame for some of you...