Recherche

Pazos Escudero Nuria

Professeur-e HES ordinaire

Compétences principales

Systèmes communicants intellligents

Systèmes multiprocesseur complexes

Professeur-e HES ordinaire

Téléphone: +41 32 930 22 50

Haute Ecole Arc - Ingénierie
Espace de l'Europe 11, 2000 Neuchâtel, CH

BSc HES-SO en Industrial Design Engineering - Haute Ecole Arc - Ingénierie

Systèmes numériques
Systèmes communicants
Qualité du logiciel

2021

Robustifying the deployment of tinyML models for autonomous mini-vehicles

Scientifique ArODES

Rusci Manuele, Capotondi Alessandro, Donze Romain, Benini Luca, Pazos Escudero Nuria

Sensors, 2021, vol. 21, no. 4

Lien vers la publication

Résumé:

Standard-sized autonomous vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to mini-vehicles poses several challenges due to their limited on-board storage and computing capabilities. Moreover, autonomous systems lack robustness when deployed in dynamic environments where the underlying distribution is different from the distribution learned during training. To address these challenges, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target deployment environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle that learn by imitating a computer vision algorithm, i.e., the expert, in the target environment. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Moreover, we introduce an online predictor that can choose between different tinyCNN models at runtime—trading accuracy and latency—which minimises the inference’s energy consumption by up to 3.2×. Finally, we leverage GAP8, a parallel ultra-low-power RISC-V-based micro-controller unit (MCU), to meet the real-time inference requirements. When running the family of tinyCNNs, our solution running on GAP8 outperforms any other implementation on the STM32L4 and NXP k64f (traditional single-core MCUs), reducing the latency by over 13× and the energy consumption by 92%.

Robustifying the Deployment of tiniML Models for Autonomous mini-vehicles

Scientifique

Nuria Pazos Escudero, Miguel De Prado, Luca Benini,

Special Issue Advances on Smart Vision Chips and Near-Sensor Inference for Edge AI of open access journal Sensors (ISSN 1424-8220; CODEN: SENSC9)., 2021

2020

Automated design space exploration for optimised deployment of DNN on arm cortex-A CPUs

Scientifique ArODES

Mundy Andrew, Saeed Rabia, Denna Maurizio, Pazos Escudero Nuria, Benini Luca

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, To be published

Lien vers la publication

Résumé:

The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). Works have mainly focused on: i) efficient DNN architectures, ii) network optimisation techniques such as pruning and quantisation, iii) optimised algorithms to speed up the execution of the most computational intensive layers and, iv) dedicated hardware to accelerate the data flow and computation. However, there is a lack of research on cross-level optimisation as the space of approaches becomes too large to test and obtain a globally optimised solution. Thus, leading to suboptimal deployment in terms of latency, accuracy, and memory. In this work, we first detail and analyse the methods to improve the deployment of DNNs across the different levels of software optimisation. Building on this knowledge, we present an automated exploration framework to ease the deployment of DNNs. The framework relies on a Reinforcement Learning search that, combined with a deep learning inference framework, automatically explores the design space and learns an optimised solution that speeds up the performance and reduces the memory on embedded CPU platforms. Thus, we present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4× improvement in performance and over 2× reduction in memory with negligible loss in accuracy with respect to the BLAS floating-point implementation.

Bonseyes AI pipeline :

Scientifique ArODES

bringing AI to you

De Prado Miguel, Su Jing, Saeed Rabia, Keller Lorenzo, Vallez Noelia, Anderson Andrew, Gregg David, Benini Luca, Llewellynn Tim, Ouerhani Nabil, Dahyot Rozenn, Pazos Escudero Nuria

ACM Transactions on Internet of Things, 2020, vol. 1, no. 4, article no. 26

Lien vers la publication

Résumé:

Next generation of embedded Information and Communication Technology (ICT) systems are interconnected and collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one of the keys for the next technological revolution: the seamless integration of AI in our daily life. However, training and deployment of custom AI solutions on embedded devices require a fine-grained integration of data, algorithms, and tools to achieve high accuracy and overcome functional and non-functional requirements. Such integration requires a high level of expertise that becomes a real bottleneck for small and medium enterprises wanting to deploy AI solutions on the Edge, which, ultimately, slows down the adoption of AI on applications in our daily life. In this work, we present a modular AI pipeline as an integrating framework to bring data, algorithms, and deployment tools together. By removing the integration barriers and lowering the required expertise, we can interconnect the different stages of particular tools and provide a modular end-to-end development of AI products for embedded devices. Our AI pipeline consists of four modular main steps: (i) data ingestion, (ii) model training, (iii) deployment optimization, and (iv) the IoT hub integration. To show the effectiveness of our pipeline, we provide examples of different AI applications during each of the steps. Besides, we integrate our deployment framework, Low-Power Deep Neural Network (LPDNN), into the AI pipeline and present its lightweight architecture and deployment capabilities for embedded devices. Finally, we demonstrate the results of the AI pipeline by showing the deployment of several AI applications such as keyword spotting, image classification, and object detection on a set of well-known embedded platforms, where LPDNN consistently outperforms all other popular deployment frameworks.

Bonseyes AI Pipeline - Bringing AI to You: End-to-end Integration of Data, Algorithms and Deployment Tools

Scientifique

Nuria Pazos Escudero, Miguel De Prado, Rabia Saeed, Nabil Ouerhani, Tim Llewellyn, Luca Benini

ACM Transactions on Internet of Things, 2020

Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs

Scientifique

Nuria Pazos Escudero, Miguel De Prado, Rabia Saeed, Luca Benini, Andrew Mundy

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020

2021

Hybrid and Flexible Computing Architectures for Deep Learning Systems

Conference

Nabil Ouerhani, Nuria Pazos Escudero, François Tièche, Miguel De Prado, Sara Carola, Lucien Moor, Lukas Bitter

Zoom Innovation on Consumer Electronics (ZINC), 12.04.2021 - 01.06.2017, Novi Sad, Serbia

2019

IoT meets distributed AI :

Conference ArODES

deployment scenarios of Bonseyes AI applications on FIWARE

Nabil Ouerhani, Nuria Pazos Escudero

Proceedings of 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC), 29-31 October 2019, London, United Kingdom

Lien vers la conférence

Résumé:

Bonseyes is an Artificial Intelligence (AI) platform composed of a Data Marketplace, a Deep Learning Toolbox, and Developer Reference Platforms with the aim of facilitating tech and non-tech companies a rapid adoption of AI as an enabler for their business. Bonseyes provides methods and tools to speed up the development and deployment of AI solutions on low power Internet of Things (IoT) devices, embedded computing systems, and data centre servers. In this work, we address the deployment and the integration of Bonseyes AI applications in a wider enterprise application landscape involving different applications and services. We leverage the well-established IoT platform FIWARE to integrate the Bonseyes AI applications into an enterprise ecosystem. This paper presents two AI application deployment and integration scenarios using FIWARE. The first scenario addresses use cases where edge devices have enough compute power to run the AI applications and there is only need to transmit the results to the enterprise ecosystem. The second scenario copes with use cases where an edge device may delegate most of the computation to an external/cloud server. Further, we employ FIWARE IoT Agent generic enabler to manage all edge devices related to Bonseyes AI applications. Both scenarios have been validated on concrete use cases and demonstrators.

WirelessHART-based Sensor Network for Multichannel Measurement of machine-tool Energy Consumption in Production Environments

Conference

Nabil Ouerhani, Arnaud Gay Des Combes, Nuria Pazos Escudero, Patrick Neuenschwander, Patrice Muller

International Conference on Industrial Automation, Robotics and Control Engineering (IARCE 2019), 25.09.2019 - 27.09.2019, Amsterdam, Netherlands

Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems

Conference ArODES

Nuria Pazos Escudero

Proceedings of 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), 25-29 March 2019, Florence, Italy

Lien vers la conférence

Résumé:

Deep Learning is increasingly being adopted by industry for computer vision applications running on embedded devices. While Convolutional Neural Networks' accuracy has achieved a mature and remarkable state, inference latency and throughput are a major concern especially when targeting low-cost and low-power embedded platforms. CNNs' inference latency may become a bottleneck for Deep Learning adoption by industry, as it is a crucial specification for many real-time processes. Furthermore, deployment of CNNs across heterogeneous platforms presents major compatibility issues due to vendor-specific technology and acceleration libraries.In this work, we present QS-DNN, a fully automatic search based on Reinforcement Learning which, combined with an inference engine optimizer, efficiently explores through the design space and empirically finds the optimal combinations of libraries and primitives to speed up the inference of CNNs on heterogeneous embedded devices. We show that, an optimized combination can achieve 45x speedup in inference latency on CPU compared to a dependency-free baseline and 2x on average on GPGPU compared to the best vendor library. Further, we demonstrate that, the quality of results and time "to-solution" is much better than with Random Search and achieves up to 15x better results for a short-time search.

2018

QUENN :

Conference ArODES

QUantization engine for low-power neural networks

Nuria Pazos Escudero

Proceedings of the 15th ACM International Conference on Computing Frontiers, 8-10 May 2018, Ischia, Italy

Lien vers la conférence

Résumé:

Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligence (AI). The high demand of computational resources required by deep neural networks may be alleviated by approximate computing techniques, and most notably reduced-precision arithmetic with coarsely quantized numerical representations. In this context, Bonseyes comes in as an initiative to enable stakeholders to bring AI to low-power and autonomous environments such as: Automotive, Medical Healthcare and Consumer Electronics. To achieve this, we introduce LPDNN, a framework for optimized deployment of Deep Neural Networks on heterogeneous embedded devices. In this work, we detail the quantization engine that is integrated in LPDNN. The engine depends on a fine-grained workflow which enables a Neural Network Design Exploration and a sensitivity analysis of each layer for quantization. We demonstrate the engine with a case study on Alexnet and VGG16 for three different techniques for direct quantization: standard fixed-point, dynamic fixed-point and k-means clustering, and demonstrate the potential of the latter. We argue that using a Gaussian quantizer with k-means clustering can achieve better performance than linear quantizers. Without retraining, we achieve over 55.64% saving for weights' storage and 69.17% for run-time memory accesses with less than 1% drop in top5 accuracy in Imagenet.

2017

BONSEYES :

Conference ArODES

platform for open development of systems of artificial intelligence

Nuria Pazos Escudero

CF'17 Proceedings of the Computing Frontiers Conference

Lien vers la conférence

Résumé:

The Bonseyes EU H2020 collaborative project aims to develop a platform consisting of a Data Marketplace, a Deep Learning Toolbox, and Developer Reference Platforms for organizations wanting to adopt Artificial Intelligence. The project will be focused on using artificial intelligence in low power Internet of Things (IoT) devices ("edge computing"), embedded computing systems, and data center servers ("cloud computing"). It will bring about orders of magnitude improvements in efficiency, performance, reliability, security, and productivity in the design and programming of systems of artificial intelligence that incorporate Smart Cyber-Physical Systems (CPS). In addition, it will solve a causality problem for organizations who lack access to Data and Models. Its open software architecture will facilitate adoption of the whole concept on a wider scale. To evaluate the effectiveness, technical feasibility, and to quantify the real-world improvements in efficiency, security, performance, effort and cost of adding AI to products and services using the Bonseyes platform, four complementary demonstrators will be built. Bonseyes platform capabilities are aimed at being aligned with the European FI-PPP activities and take advantage of its flagship project FIWARE. This paper provides a description of the project motivation, goals and preliminary work.

2016

IoT-based dynamic street light control for smart cities use cases

Conference ArODES

Nabil Ouerhani, Nuria Pazos Escudero

Proceedings of 2016 International Symposium on Networks, Computers and Communications (ISNCC)

Lien vers la conférence

Résumé:

This paper presents a real-world proven solution for dynamic street light control and management which relies on an open and flexible Internet of Things architecture. Substantial contribution is brought at the interoperability level using novel device connection concept based on model-driven communication agents to speed up the integration of sensors and actuators to Internet of Things platforms. The paper shows also results from real-world tests with deployed dynamic street lights in urban spaces. The proposed dynamic light control solution permits an energy saving of about 56% compared to classical static, time-based street light control.

2015

Dynamic street light management :

Conference ArODES

towards a citizen centred approach

Stéphane Gobron, Nabil Ouerhani, Julien Senn, Nuria Pazos Escudero

Proceedings of 2nd Conference "Smart Cities", 30 May 2015, Agadir, Morocco

Lien vers la conférence

Résumé:

This paper presents a novel approach towards dynamic street light control, which combines advanced Information and Communication Technologies (ICT) and citizens' involvement and engagement. Our proposal is based on the citizens' involvement which would strongly increases the efficiency and perfromance of technological solutions in smart city context. We believe that serious Games have the potential to strengthen people motivation in this context.

Réalisations

Recherche

Pazos Escudero Nuria

Professeur-e HES ordinaire

Compétences principales

Systèmes embarqués autonomes

Systèmes communicants intellligents

Systèmes multiprocesseur complexes

Edge AI

On-chip communication

Professeur-e HES ordinaire