Our architecture demonstrates exceptional performance on benchmark datasets. Below you can find vies cases on each model version.
The testing of Neural Network automatically built by Neural Network builder showed great results. The graphs with comporison classical neural network and automatically built with our architecture achieved impressive training stability and energy efficiency.
The goal is to make time consuming computation in low-level programing language instead of Python. After this the training time will be drastically improved so it's even better classical neural network timings.