Multi-fidelity deep neural networks for adaptive inference in the internet of multimedia things
| Autor: | Sam Leroux, Pieter Van Molle, Steven Bohez, Pieter Simoens, Bart Dhoedt, Bert Vankeirsbilck, Elias De Coninck, Tim Verbelen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
IoT
Computer Networks and Communications Computer science media_common.quotation_subject Fidelity Inference 02 engineering and technology computer.software_genre Deep neural networks 0202 electrical engineering electronic engineering information engineering Resource efficient inference media_common Sequence Artificial neural network Multimedia business.industry 020206 networking & telecommunications Variety (cybernetics) Hardware and Architecture Benchmark (computing) 020201 artificial intelligence & image processing The Internet business computer Software Energy (signal processing) |
| Zdroj: | FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE |
| ISSN: | 0167-739X 1872-7115 |
| Popis: | Internet of Things (IoT) infrastructures are more and more relying on multimedia sensors to provide information about the environment. Deep neural networks (DNNs) could extract knowledge from this audiovisual data but they typically require large amounts of resources (processing power, memory and energy). If all limitations of the execution environment are known beforehand, we can design neural networks under these constraints. An IoT setting however is a very heterogeneous environment where the constraints can change rapidly. We propose a technique allowing us to deploy a variety of different networks at runtime, each with a specific complexity-accuracy trade-off but without having to store each network independently. We train a sequence of networks of increasing size and constrain each network to contain the parameters of all smaller networks in the sequence. We only need to store the largest network to be able to deploy each of the smaller networks. We experimentally validate our approach on different benchmark datasets for image recognition and conclude that we can build networks that support multiple trade-offs between accuracy and computational cost. (C) 2019 Elsevier B.V. All rights reserved. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect