09-28-2024, 08:53 AM
(This post was last modified: 09-28-2024, 08:59 AM by AbsoluteBeginner.)
(translated by Google translator)
Hi all.
Today I woke up feeling completely confident that we should not try to create a neuron that can do ANY job well.
What facts do we have?..
At the moment, the process of creating and training a neural network is a separate operation. The process of using a neural network is a different separate operation.
Each operation solves its own tasks.
But the classical neuron is designed in such a way that it itself has to both learn and work.
( as a result, he does both the first and second poorly )
Now we are creating a neural network that should not self-learn.
Therefore, we have the opportunity to create a SB-Neuron that will work very well, but will not learn at all.
The design of the SB-Neurons in our SB-Neural Network will be determined by the TRAINING PROGRAM.
Our training program will:
( Cool. Right? )
Hi all.
Today I woke up feeling completely confident that we should not try to create a neuron that can do ANY job well.
What facts do we have?..
At the moment, the process of creating and training a neural network is a separate operation. The process of using a neural network is a different separate operation.
Each operation solves its own tasks.
But the classical neuron is designed in such a way that it itself has to both learn and work.
( as a result, he does both the first and second poorly )
Now we are creating a neural network that should not self-learn.
Therefore, we have the opportunity to create a SB-Neuron that will work very well, but will not learn at all.
The design of the SB-Neurons in our SB-Neural Network will be determined by the TRAINING PROGRAM.
Our training program will:
- collect training information;
- analyze and process this information;
- create an activation function for the SB-Neurons that best matches the received training information.
( Cool. Right? )