Analyzing Few-Shot Neural Architecture Search in a Metric-Driven Framework
While Neural Architecture Search (NAS) methods help find optimal neural network architectures for diverse tasks, they often come with …
FLoCoRA: Federated Learning Compression With Low-Rank Adaptation
Low-Rank Adaptation (LoRA) methods have gained popularity in efficient parameter fine-tuning of models containing hundreds of billions …
Design Environment of Quantization-Aware Edge AI Hardware for Few-Shot Learning
This study aims to ensure consistency in accuracy throughout the entire design flow in the implementation of edge AI hardware for …
PEFSL: A deployment Pipeline for Embedded Few-Shot Learning on a FPGA SoC
This paper tackles the challenges of implementing few-shot learning on embedded systems, specifically FPGA SoCs, a vital approach for …
Pipelined Architecture for a Semantic Segmentation Neural Network on FPGA
Many machine vision tasks like urban sceneunderstanding rely on machine learning, and more specifically deep neural networks to provide …
Pipelined Architecture for a Semantic Segmentation Neural Network on FPGA
Many machine vision tasks like urban sceneunderstanding rely on machine learning, and more specifically deep neural networks to provide …
Federated learning compression designed for lightweight communications
Federated Learning (FL) is a promising distributed method for edge-level machine learning, particularly for privacysensitive …
Federated learning compression designed for lightweight communications
Federated Learning (FL) is a promising distributed method for edge-level machine learning, particularly for privacysensitive …
Compression de réseaux de neurones pour l'apprentissage fédéré
Federated Learning (FL) is a promising distributed method for edge-level machine learning, particularly for privacysensitive …
Co-conception d'un réseau de neurones convolutif de segmentation sémantique et de son architecture matérielle
De nombreuses tâches de vision machine, comme la compréhension des scènes urbaines, reposent sur l'apprentissage automatique, et plus …
DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables
A lot of recent progress has been made in ultra lowbit quantization, promising significant improvements in latency, memory footprint …
Leveraging Structured Pruning of Convolutional Neural Networks
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many …
Inter-Operability of Compression Techniques for Efficient Deployment of CNNs on Microcontrollers
Machine Learning (ML) has become state of the art for various tasks, including classification of accelerometer data. In the world of …
Inter-Operability of Compression Techniques for Efficient Deployment of CNNs on Microcontrollers
Machine Learning (ML) has become state of the art for various tasks, including classification of accelerometer data. In the world of …
Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU
Deep neural networks are the state of the art in many computer vision tasks. Their deployment in the context of autonomous vehicles is …
Élagage de réseaux profond de neurones par dégradation sélective des pondérations
Les réseaux de neurones profonds sont le standard incontournable de l’apprentissage automatique. Cependant, pour atteindre les …
Investigating the Not-So-Obvious Effects of Structured Pruning
Structured pruning is a popular method to reduce the cost of convolutional neural networks. However, depending on the architecture, …
MOL-based In-Memory Computing of Binary Neural Networks
Convolutional neural networks (CNN) have proven very effective in a variety of practical applications involving Artificial Intelligence …
Rethinking Weight Decay for Efficient Neural Network Pruning
Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks. Despite …
Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Polar codes can theoretically achieve very competitive Frame Error Rates. In practice, their performance may depend on the chosen …
A Flexible and Portable Real-time DVB-S2 Transceiver using Multicore and SIMD CPUs
Software implementation of digital communication systems is more and more used in different contexts. In the case of satellite …
AFF3CT: A Fast Forward Error Correction Toolbox!
AFF3CT is an open source toolbox dedicated to Forward Error Correction (FEC or channel coding). Itsupports a broad range of codes: from …
Fast and Flexible Software Polar List Decoders
Flexibility is one mandatory aspect of channel coding in modern wireless communication systems. Among other things, the channel decoder …
Toward High-Performance Implementation of 5G SCMA Algorithms
The recent evolution of mobile communication systems toward a 5G network is associated with the search for new types of non-orthogonal …
Décodage de codes polaires sur des architectures programmables
Les codes polaires constituent une classe de codes correcteurs d’erreurs inventés récemment qui suscite l’intérêt des chercheurs et des …
Transport Triggered Polar Decoders
In this paper, the first transport triggered architecture (TTA) customized for the decoding of polar codes is proposed. A first version …
Custom Low Power Processor for Polar Decoding
Cloud Radio Access Network is foreseen as one of the key features of the future 5G mobile communication standard. In this context, all …
Fast Simulation and Prototyping with AFF3CT
This demonstration intends to present AFF3CT (A Fast Forward 3rror Correction Tool). The main objective of AFF3CT is to provide a …
Improving performance of SCMA MPA decoders using estimation of conditional probabilities
Sparse code multiple access (SCMA) is a new type of non-orthogonal modulation suggested for 5G systems offering lower bit-error rate …