相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Yuqiao Liu et al.
Summary: Deep neural networks have achieved great success in many applications, but their architectures require labor-intensive and expert-designed processes. Neural architecture search (NAS) technology enables automatic design of architectures, with evolutionary computation (EC) methods gaining attention and success. However, there is currently no comprehensive summary of EC-based NAS algorithms.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Fouad Sakr et al.
Summary: This paper presents a tiny Convolution Neural Network (CNN) architecture suitable for electronic skin systems, which is optimized through strategies like layer fusion and buffer re-use for efficient inference on commercial microcontrollers. Experimental results demonstrate that the proposed system achieves high real-time processing capability and reduces the model size significantly.
ADVANCES IN SYSTEM-INTEGRATED INTELLIGENCE, SYSINT 2022
(2023)
Article
Engineering, Electrical & Electronic
Christian Gianoglio et al.
Summary: This paper proposes a learning strategy based on the out-of-samples technique to find the configurations of the elaboration unit and the parameters of the predictor that best balance the generalization accuracy and the computational cost. The study conducted on touch modalities classification problem shows that SLFNNs achieve the best solution in terms of accuracy, outperforming existing algorithms, while also considering the trade-off between generalization performance and computational cost.
IEEE SENSORS JOURNAL
(2022)
Review
Computer Science, Artificial Intelligence
Dilyara Baymurzina et al.
Summary: This paper reviews the recent works on Neural Architecture Search (NAS) and highlights several crucial concepts and problems in this field.
Article
Automation & Control Systems
Zhengkun Yi et al.
Summary: This article proposes a kernel-based approach to address the challenges in touch modality identification, including high dimensionality, complex morphology, and misalignment issues, by reducing feature dimension, preserving spatial information, and employing global alignment techniques. The effectiveness of the proposed approach is verified through a comprehensive comparison with competing methods on a public touch modality dataset.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Hamoud Younes et al.
Summary: This paper presents the first FPGA implementation of an approximate tensorial Support Vector Machine classifier using High-Level Synthesis, with a touch modality classification framework to validate its effectiveness. Compared to exact implementations, the proposed approach achieves up to 49% reduction in power consumption, 3.2x speedup, 40% reduction in hardware resources, and 82% less energy consumption while maintaining an accuracy loss of less than 5% when classifying input touch data.
Article
Computer Science, Artificial Intelligence
Tailin Liang et al.
Summary: Deep neural networks have been widely used in computer vision applications, but their complex architectures pose challenges in real-time deployment due to high computation resources and energy costs. Network compression techniques such as pruning and quantization can help overcome these challenges by reducing redundant computations. Both techniques can be used independently or together to improve the efficiency and performance of deep neural networks.
Article
Engineering, Electrical & Electronic
Mohamad Alameh et al.
Summary: This paper explores the time series characteristics of RNNs for touch modality classification, proposing efficient models to capture long-term dependencies in data and presenting hardware-friendly approaches that reduce computational and memory requirements. The implemented models show higher classification accuracy and scalability, with reduced hardware complexity and improved performance compared to state-of-the-art solutions on the same benchmark dataset.
IEEE SENSORS JOURNAL
(2021)
Article
Computer Science, Theory & Methods
Pengzhen Ren et al.
Summary: Neural Architecture Search (NAS) is a revolutionary algorithm aimed at reducing human intervention and allowing algorithms to automatically design neural architectures. The related research work is complex and rich, requiring a comprehensive and systematic survey.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Artificial Intelligence
Haotong Qin et al.
PATTERN RECOGNITION
(2020)
Article
Computer Science, Information Systems
Yuhan Hu et al.
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Mohamad Alameh et al.
2019 15TH CONFERENCE ON PHD RESEARCH IN MICROELECTRONICS AND ELECTRONICS (PRIME)
(2019)
Article
Computer Science, Artificial Intelligence
Merel M. Jung et al.
JOURNAL ON MULTIMODAL USER INTERFACES
(2017)
Article
Robotics
Mohsen Kaboli et al.
Article
Chemistry, Analytical
Paolo Gastaldo et al.
Article
Robotics
David Silvera Tawil et al.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2012)