Publications

February 12, 2020

This article presents the application of the proprietary technology of dynamic graph CNNs into heterogeneous, multiprocessing systems.

July 20, 2019

This article presents a new, radical CNN dynamic pruning approach targeting to the parsimonious inference by learning to exploit and dynamically remove the redundant capacity of a CNN architecture.

March 06, 2017

This article presents the application of the process of neural plasticity to deep learning.

March 02, 2017

A summary of metrics for a CPU-only implementation of a deep-learning network on various mobile embedded systems

February 03, 2017

This article presents a new radical method able to make every CNN model many times faster!