readme update

This commit is contained in:
Gustav Louw 2018-04-11 09:23:23 -07:00
parent 501321b8a2
commit 9ea4e51a38
1 changed files with 8 additions and 0 deletions

View File

@ -32,6 +32,14 @@ This gives 10 outputs to the neural network. The test program will output the
accuracy for each digit. Expect above 99% accuracy for the correct digit, and
less that 0.1% accuracy for the other digits.
# Features
* Portable - Runs on Windows, MacOS, Linux, and embedded chips like ARM, AVR, and Microchip
* Sigmoidal activation.
* One hidden layer.
# Tips
* Tinn will never use more than the C standard library.