Название: Embedded Artificial Intelligence: Devices, Embedded Systems, and Industrial Applications
Автор: Ovidiu Vermesan, Mario Diaz Nava, Bjorn Debaillie
Издательство: River Publishers
Год: 2023
Страниц: 143
Язык: английский
Формат: pdf (true)
Размер: 18.9 MB

Recent technological developments in sensors, edge computing, connectivity, and Artificial Intelligence (AI) technologies have accelerated the integration of data analysis based on embedded AI capabilities into resource-constrained, energy-efficient hardware devices for processing information at the network edge.

Embedded AI combines embedded Machine Learning (ML) and Deep Learning (DL) based on neural networks (NN) architectures such as convolutional NN (CNN), or spiking neural network (SNN) and algorithms on edge devices and implements edge computing capabilities that enable data processing and analysis without optimised connectivity and integration, allowing users to access data from various sources.

Embedded AI efficiently implements edge computing and AI processes on resource-constrained devices to mitigate downtime and service latency, and it successfully merges AI processes as a pivotal component in edge computing and embedded system devices. Embedded AI also enables users to reduce costs, communication, and processing time by assembling data and by supporting user requirements without the need for continuous interaction with physical locations.

This book provides an overview of the latest research results and activities in industrial embedded AI technologies and applications, based on close cooperation between three large-scale ECSEL JU projects, AI4DI, ANDANTE, and TEMPO.

Embedded edge Artificial Intelligence (AI) reduces latency, increases the speed of processing tasks, and reduces bandwidth requirements by reducing the among of data transmitted, and costs by introducing cost-effective and efficient low power hardware solutions allowing processing data locally. New embedded AI techniques offer high data security, decreasing the risks to sensitive and confidential data and increasing the dependability of autonomous technologies.

Embedded edge devices are becoming more and more complex, heterogeneous, and powerful as they incorporate a combination of hardware components like central processing units (CPUs), microcontroller processing units (MCUs), graphics processing units (GPUs), digital signal processors (DSPs), image signal processors (ISPs), neural processing units (NPUs), field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs) and other accelerators to perform multiple forms of machine learning (ML), deep learning (DL) and spiking neural network (SNN) algorithms. Embedded edge devices with dedicated accelerators can perform matrix multiplication significantly faster than CPUs, and ML/DL algorithms implemented in AI frameworks and edge AI platforms can efficiently exploit these hardware components.

Processing pipelines, toolchains, and flexible edge AI software architectures can provide specific system-on-a-chip (SoC), system-on­ module (SoM) and application types for optimised run-time support. These tools can facilitate the full exploitation of heterogeneous SoC/SoM capabilities for ML/DL and maximise component reuse at the edge.

The book’s content targets researchers, designers, developers, academics, post-graduate students and practitioners seeking recent research on embedded AI. It combines the latest developments in embedded AI, addressing methodologies, tools, and techniques to offer insight into technological trends and their use across different industries.