ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge [PDF]
SensorsThe combination of deep-learning and IoT plays a significant role in modern smart solutions, providing the capability of handling task-specific real-time offline operations with improved accuracy and minimised resource consumption.
Dakshina Ranmal +4 more
doaj +6 more sources
MicroNAS for memory and latency constrained hardware aware neural architecture search in time series classification on microcontrollers [PDF]
Scientific ReportsThe use and research of neural networks on very small processor systems are currently still limited. One of the main reasons is that the design of microcontroller-architecture-aware ML models that take into account user-defined constraints on memory ...
Tobias King +3 more
doaj +3 more sources
IEEE AccessThe growing demand for edge applications calls for efficient and optimized deep neural network models. Neural Architecture Search (NAS) is instrumental in designing such models, but achieving optimal architectures quickly remains a key challenge.
Oscal Tzyh-Chiang Chen +4 more
doaj +4 more sources
Differentiable Neural Architecture, Mixed Precision and Accelerator Co-Search [PDF]
IEEE Access, 2023 Quantization, effective Neural Network architecture, and efficient accelerator hardware are three important design paradigms to maximize accuracy and efficiency.
Krishna Teja Chitty-Venkata +4 more
doaj +3 more sources
Multi-Chaotic HEOA for Hardware-Aware Neural Architecture Search: Brain Tumor Classification on FPGA [PDF]
SensorsAutomated brain tumor classification from MRI scans requires optimized CNN architectures deployable on embedded FPGA platforms. This paper presents an integrated approach combining the Multi-Chaotic Enhanced HEOA (MC-HEOA) for automatic CNN architecture ...
Ismail Mchichou +3 more
doaj +2 more sources
Supernetwork-based efficient mapping of deep learning applications to mixed-precision hardware using model adaptation [PDF]
Nature CommunicationsThe rapid proliferation of Artificial Intelligence applications necessitates scalable solutions that perform efficiently under real-world constraints.
Hadjer Benmeziane +10 more
doaj +2 more sources
HAPQ: A Hardware-Aware Pruning and Quantization Pipeline for Event-Based SNN Detection [PDF]
SensorsAutonomous driving perception demands low latency, high temporal resolution, and stringent hardware efficiency. While event-based spiking neural networks (SNNs) offer bio-inspired sparse computation, their deployment on edge field-programmable gate ...
Zhengyinan Li, Jing Wu
doaj +2 more sources
Neural Architecture Search Benchmarks: Insights and Survey
IEEE Access, 2023 Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset.
Krishna Teja Chitty-Venkata +3 more
doaj +1 more source
APNAS: Accuracy-and-Performance-Aware Neural Architecture Search for Neural Hardware Accelerators
IEEE Access, 2020 Designing resource-efficient deep neural networks (DNNs) is a challenging task due to the enormous diversity of applications as well as their time-consuming design, training, optimization, and evaluation cycles, especially the resource-constrained ...
Paniti Achararit +4 more
doaj +1 more source
Neural Architecture Search and Hardware Accelerator Co-Search: A Survey
IEEE Access, 2021 Deep neural networks (DNN) are now dominating in the most challenging applications of machine learning. As DNNs can have complex architectures with millions of trainable parameters (the so-called weights), their design and training are difficult even for
Lukas Sekanina
doaj +1 more source