7 citations · 32 across the 21 of their papers we have counts for
22 papers
Memory-Efficient Integer-Only Training of Deep Neural Networks
Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri
Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision benchmarks retain floating-poi…
What changes after deployment? A survey on On-device Learning in TinyML
Massimo Pavan, Luca Pezzarossa, Fabrizio Pittorino +2
Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static models. On-device learning (OD…
HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transit…
SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks
Matteo Gambella, Fabrizio Pittorino, Giuliano Casale +1
Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approac…
DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic
Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo +2
The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails…
InfoQ: Mixed-Precision Quantization via Global Information Flow
Mehmet Emre Akbulut, Hazem Hesham Yousef Shalby, Fabrizio Pittorino +1
Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a comp…
TActiLE: Tiny Active LEarning for wearable devices
Massimo Pavan, Claudio Galimberti, Manuel Roveri
Tiny Machine Learning (TinyML) algorithms have seen extensive use in recent years, enabling wearable devices to be not only connected but also genuinely intelligent by running mach…
SEAL: Searching Expandable Architectures for Incremental Learning
Matteo Gambella, Manuel Roveri
Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new t…
DYNAMAX: Dynamic computing for Transformers and Mamba based architectures
Miguel Nogales, Matteo Gambella, Manuel Roveri
Early exits (EEs) offer a promising approach to reducing computational costs and latency by dynamically terminating inference once a satisfactory prediction confidence on a data sa…
On-Sensor Convolutional Neural Networks with Early-Exits
Hazem Hesham Yousef Shalby, Arianna De Vecchi, Alice Scandelli +4
Tiny Machine Learning (TinyML) is a novel research field aiming at integrating Machine Learning (ML) within embedded devices with limited memory, computation, and energy. Recently,…
Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
Hazem Hesham Yousef Shalby, Manuel Roveri
Human activity recognition (HAR) is a research field that employs Machine Learning (ML) techniques to identify user activities. Recent studies have prioritized the development of H…
Architecture-Aware Minimization (AM): How to Find Flat Minima in Neural Architecture Search
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neura…
Quantifying Cryptocurrency Unpredictability: A Comprehensive Study of Complexity and Forecasting
Francesco Puoti, Fabrizio Pittorino, Manuel Roveri
This paper offers a thorough examination of the univariate predictability in cryptocurrency time-series. By exploiting a combination of complexity measure and model predictions we…
EmbBERT: Attention Under 2 MB Memory
Riccardo Bravin, Massimo Pavan, Hazem Hesham Yousef Shalby +2
Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. Howev…
Training Multi-Layer Binary Neural Networks With Local Binary Error Signals
Luca Colombo, Fabrizio Pittorino, Manuel Roveri
Binary Neural Networks (BNNs) significantly reduce computational complexity and memory usage in machine and deep learning by representing weights and activations with just one bit.…
TIFeD: a Tiny Integer-based Federated learning algorithm with Direct feedback alignment
Luca Colombo, Alessandro Falcetta, Manuel Roveri
Training machine and deep learning models directly on extremely resource-constrained devices is the next challenge in the field of tiny machine learning. The related literature in…
StreamTinyNet: video streaming analysis with spatial-temporal TinyML
Hazem Hesham Yousef Shalby, Massimo Pavan, Manuel Roveri
Tiny Machine Learning (TinyML) is a branch of Machine Learning (ML) that constitutes a bridge between the ML world and the embedded system ecosystem (i.e., Internet of Things devic…
NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks
Alberto Pirillo, Luca Colombo, Manuel Roveri
Quantization is a pivotal technique for managing the growing computational and memory demands of Deep Neural Networks (DNNs). By reducing the number of bits used to represent weigh…
TinySV: Speaker Verification in TinyML with On-device Learning
Massimo Pavan, Gioele Mombelli, Francesco Sinacori +1
TinyML is a novel area of machine learning that gained huge momentum in the last few years thanks to the ability to execute machine learning algorithms on tiny devices (such as Int…
A Lightweight Neural Architecture Search Model for Medical Image Classification
Lunchen Xie, Eugenio Lomurno, Matteo Gambella +4
Accurate classification of medical images is essential for modern diagnostics. Deep learning advancements led clinicians to increasingly use sophisticated models to make faster and…
FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness
Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
Neural Architecture Search (NAS) paves the way for the automatic definition of Neural Network (NN) architectures, attracting increasing research attention and offering solutions in…
NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
Matteo Gambella, Jary Pomponi, Simone Scardapane +1
Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing whe…