Publications

April 22, 2024

Personalization in Distributed tinyML Applications via Adaptive Clustered Federated Learning

This article presents our approach embracing Personalized Federated Learning (PFL) by using a unique model interpolation approach based on hierarchical clustering, achieving a significant increase in performance.

February 12, 2020

Deep Learning Inference with Dynamic Graphs on Heterogeneous Platforms

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

July 20, 2019

Dynamic Pruning of CNN networks

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

Deep Neural Networks: Adding Neural Plastisity to boost computing efficiency

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

March 02, 2017

Mobile, CPU-only Deep Learning Inference: How fast can it be?

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

February 03, 2017

Parsimonious Inference: Towards rapid-eye deep-learning inference

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