This algorithm implements software realization of the smallest unit of an artificial neural network. One version is written in C language; the second in Python/Tensorflow/Keras. This single perceptron is able to solve simple logical operations like AND, OR, NAND, NOR, and NOT. Coefficients that are calculated are two weights and one bias in a backpropagation sort of learning process. In C code is added the logging functionality of all coefficients, over iteration process of learning, into one textual file which can be analyzed later. In Python code there is tracking of loss with chart creation. This algorithm can not resolve XOR or XNOR logical operations.
-
Notifications
You must be signed in to change notification settings - Fork 1
This algorithm implements software realization of the smallest unit of an artificial neural network. One version is written in C language; the second in Python/Tensorflow/Keras. This single perceptron is able to solve simple logical operations like AND, OR, NAND, NOR, and NOT. Coefficients that are calculated are two weights and one bias in a ba…
DusanRandD/SPBA
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
This algorithm implements software realization of the smallest unit of an artificial neural network. One version is written in C language; the second in Python/Tensorflow/Keras. This single perceptron is able to solve simple logical operations like AND, OR, NAND, NOR, and NOT. Coefficients that are calculated are two weights and one bias in a ba…
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published