Added the ability to calculate accuracy during training as well as during prediction.
Added confusion matrix calculation and visualization functions in utils.py.
0.1.6
1. Both forward feed and back propagation are now significantly faster, for both NumPy and Cupy versions. 2. Furthermore, several more activation and loss functions are also available now.
0.1.5
Support for CUDA is here via Cupy.
Slower than CPU for smaller networks but the benefits are very evident for larger networks with more than 1.5 Million parameters.