This is a simple neural network built in Go. It is further discussed here and in Machine Learning with Go.
According to the original article, this should give results in the 97% range.
$ ./gophernet
Accuracy = 0.97
$
However, my results were nowhere close to this:
$ ./gophernet
Accuracy = 0.77
$
[My first result was 87% - so the results vary greatly.]
- Twelve-factor everything
- Allow for a seed value so that results are reproducible and not overly dependent on initial conditions
- Add code to segment data into training and test datasets rather than rely on pre-segmented data
- Investigate pickling in Go