mirrors/tinn
1
0
Fork 0
mirror of https://github.com/glouw/tinn synced 2024-11-21 22:11:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

readme update

Browse Source
This commit is contained in:
Gustav Louw 2018-04-10 18:50:31 -07:00
parent 01e075b78c
commit 005a5445c0
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -14,6 +14,7 @@ Tinn (Tiny Neural Network) is a 200 line dependency free neural network library
int main() int main()
{ {
// This example learns XOR.
float in[SETS][NIPS] = { float in[SETS][NIPS] = {
{ 0, 0 }, { 0, 0 },
{ 0, 1 }, { 0, 1 },
@ -47,11 +48,11 @@ Tinn (Tiny Neural Network) is a 200 line dependency free neural network library
return 0; return 0;
} }
For a quick demo, get some training data: For a more complicated demo on how to learn hand written digits, get some training data:
wget http://archive.ics.uci.edu/ml/machine-learning-databases/semeion/semeion.data wget http://archive.ics.uci.edu/ml/machine-learning-databases/semeion/semeion.data
And if you're on Linux / MacOS just build and run: And if you're on Linux / MacOS just build and run Tinn with the test file:
make; ./tinn make; ./tinn
@ -59,6 +60,10 @@ If you're on Windows it's:
mingw32-make & tinn.exe mingw32-make & tinn.exe
For the layman not accustomed to makefiles the makefile devolves into:
gcc test.c Tinn.c -lm
The training data consists of hand written digits written both slowly and quickly. The training data consists of hand written digits written both slowly and quickly.
Each line in the data set corresponds to one handwritten digit. Each digit is 16x16 pixels in size Each line in the data set corresponds to one handwritten digit. Each digit is 16x16 pixels in size
giving 256 inputs to the neural network. giving 256 inputs to the neural network.