Tweet
I believe neural nets are the future of AI...
Quite an advance!
Blessings,
Lee
Quite an advance!
Blessings,
Lee
-
"What I pray of you is, to keep your eye upon Him, for that is everything. Do you say, 'How am I to keep my eye on Him?' I reply, keep your eye off everything else, and you will soon see Him. All depends on the eye of faith being kept on Him. How simple it is!" (J.B. Stoney) -
This is a simulation and not natural reality.Originally posted by lee_merrill View PostGlendower: I can call spirits from the vasty deep.
Hotspur: Why, so can I, or so can any man;
But will they come when you do call for them? Shakespeare’s Henry IV, Part 1, Act III:
go with the flow the river knows . . .
Frank
I do not know, therefore everything is in pencil. -
I believe this is a reference to the greatly increased performance of computers to perform simulations, nothing more.Glendower: I can call spirits from the vasty deep.
Hotspur: Why, so can I, or so can any man;
But will they come when you do call for them? Shakespeare’s Henry IV, Part 1, Act III:
go with the flow the river knows . . .
Frank
I do not know, therefore everything is in pencil.Comment
-
Well, it's using neural networks to replace simulations, so they can run up to a billion times faster, with surprising accuracy!Originally posted by shunyadragon View Post
Blessings,
Lee"What I pray of you is, to keep your eye upon Him, for that is everything. Do you say, 'How am I to keep my eye on Him?' I reply, keep your eye off everything else, and you will soon see Him. All depends on the eye of faith being kept on Him. How simple it is!" (J.B. Stoney)Comment
-
It is a simulation of neural networks, and not natural neural networks, which is the direct of AI for some time.Originally posted by lee_merrill View Post
Source:
"The new emulators are based on neural networks—machine learning systems inspired by the brain’s wiring—and need far less training. Neural networks consist of simple computing elements that link into circuitries particular for different tasks. Normally the connection strengths evolve through training. But with a technique called neural architecture search, the most data-efficient wiring pattern for a given task can be identified.
The technique, called Deep Emulator Network Search (DENSE), relies on a general neural architecture search co-developed by Melody Guan, a computer scientist at Stanford University. It randomly inserts layers of computation between the networks’ input and output, and tests and trains the resulting wiring with the limited data. If an added layer enhances performance, it’s more likely to be included in future variations. Repeating the process improves the emulator. Guan says it’s “exciting” to see her work used “toward scientific discovery.” Muhammad Kasim, a physicist at the University of Oxford who led the study, which was posted on the preprint server arXiv in January, says his team built on Guan’s work because it balanced accuracy and efficiency."
Glendower: I can call spirits from the vasty deep.
Hotspur: Why, so can I, or so can any man;
But will they come when you do call for them? Shakespeare’s Henry IV, Part 1, Act III:
go with the flow the river knows . . .
Frank
I do not know, therefore everything is in pencil.Comment
| Topics | Statistics | Last Post | ||
|---|---|---|---|---|
|
2 responses
27 views
0 likes
|
by rogue06
Yesterday, 07:18 PM
|
|||
|
17 responses
62 views
0 likes
|
by rogue06
04-20-2021, 08:28 AM
|
|||
|
7 responses
51 views
1 like
|
by TheLurch
04-13-2021, 05:16 PM
|
|||
|
1 response
40 views
1 like
|
by shunyadragon
04-14-2021, 08:32 PM
|
|||
|
0 responses
15 views
0 likes
|
by shunyadragon
04-11-2021, 06:59 AM
|
Comment