Masm32 SDK description, downloads and other helpful links
Message to All Guests
NB: Posting URL's See here: Posted URL Change

Main Menu

Playing with Neural Network

Started by HSE, June 05, 2020, 10:20:38 AM

Previous topic - Next topic


Hi mineiro!

Quote from: mineiro on May 19, 2021, 12:28:50 AM
Maybe I don't understood your phrase.
That is. You don't understood phrase.

Quote from: HSE on May 18, 2021, 11:04:28 PM
The problem with Neural Network is exactly that solution is beyond understanding.

The problem is not the process, is the solution.

In mathematical functions (exponential, factorial, polynomial ...)  you solve the equations and you can isolate how each variable affect the result, not always easy but in principle always posible. That can help to find real mechanism behind input-ouput asociations.

In Neural Networks you solve input-outputs asociations and you don't know why that work!
Just some months ago Max Tegmark with Brian Keating:
Equations in Assembly: SmplMath


Quote from: LiaoMi on May 19, 2021, 02:15:08 AM
A multy-layer feed-forward neural network implementation in assembly x86 32 bits

It's same kind of problem addressed in DigiBrain by Thomas Bleeker . Work well  :thumbsup:
Equations in Assembly: SmplMath


Quote from: HSE on May 19, 2021, 02:35:35 AM
In Neural Networks you solve input-outputs asociations and you don't know why that work!
Plasticity, neuromorphic, organismic. Like a drunken algorithm.
Organismic computing reveals that trained neural network can forgot things and activate that knowledge later.

John von Neumann:
Anyone who attempts to generate random numbers by deterministic means is, of course, living in a state of sin.
I'd rather be this ambulant metamorphosis than to have that old opinion about everything


Equations in Assembly: SmplMath