Closed Robbepop closed 7 years ago
Work on this has been done some time ago. Yet, the implementation never became stable so an entire redesign of the crate was initiated in order to provide better abstractions for better maintainability.
However, the new redesigned layer architecture implements this layer-size behaviour so this issue can be closed.
The entire neural network concrete layers were designed to be very memory efficient which resulted in a design with assymetric layer sizes (because of the way bias neurons are represented). This has led to several issues and implementation difficulties preventing the usage of more efficiently implemented lower-level algorithms provided by
ndarray
and other libraries. This refactoring of layer sizes also helps with implementing the new layer and topology layer types to path the way for Convolutional Layers in the end.