190 citations · 1.5k across the 53 of their papers we have counts for
9 papers · 1 filter
Optimizing the Deployment of Tiny Transformers on Low-Power MCUs
Victor J. B. Jung, Alessio Burrello, Moritz Scherer +2
Transformer networks are rapidly becoming SotA in many fields, such as NLP and CV. Similarly to CNN, there is a strong push for deploying Transformer models at the extreme edge, ul…
Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
Georg Rutishauser, Francesco Conti, Luca Benini
Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, late…
Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers
Davide Nadalini, Manuele Rusci, Luca Benini +1
Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models…
Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge
Matteo Risso, Alessio Burrello, Francesco Conti +6
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Obj…
Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari +5
Temporal Convolutional Networks (TCNs) are promising Deep Learning models for time-series processing tasks. One key feature of TCNs is time-dilated convolution, whose optimization…
TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Alessio Burrello, Alberto Dequino, Daniele Jahier Pagliari +5
Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Learning models for Time Series analysis. We introduce an automated exploration approach and a library of optim…
Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference
Gianna Paulin, Francesco Conti, Lukas Cavigelli +1
Recurrent neural networks such as Long Short-Term Memories (LSTMs) learn temporal dependencies by keeping an internal state, making them ideal for time-series problems such as spee…
A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
Leonardo Ravaglia, Manuele Rusci, Davide Nadalini +3
In the last few years, research and development on Deep Learning models and techniques for ultra-low-power devices in a word, TinyML has mainly focused on a train-then-deploy assum…
Technical Report: NEMO DNN Quantization for Deployment Model
Francesco Conti
This technical report aims at defining a formal framework for Deep Neural Network (DNN) layer-wise quantization, focusing in particular on the problems related to the final deploym…