Image recognition based on lightweight convolutional neural network: Recent advances
Y Liu, J Xue, D Li, W Zhang, TK Chiew, Z Xu - Image and Vision Computing, 2024 - Elsevier
Image recognition is an important task in computer vision with broad applications. In recent
years, with the advent of deep learning, lightweight convolutional neural network (CNN) has …
years, with the advent of deep learning, lightweight convolutional neural network (CNN) has …
Efficient and lightweight convolutional neural network architecture search methods for object classification
Determining the architecture of deep learning models is a complex task. Several automated
search techniques have been proposed, but these methods typically require high …
search techniques have been proposed, but these methods typically require high …
A lightweight real-time detection method of small objects for home service robots
T Zhang, F Zhao, Y Zou, J Zheng - Machine Vision and Applications, 2024 - Springer
Home service robots face a challenge in accurately and promptly detecting small objects in
unstructured scenarios when the target is far from the robot vision system. Therefore, a …
unstructured scenarios when the target is far from the robot vision system. Therefore, a …
Metaheuristics and machine learning: an approach with reinforcement learning assisting neural architecture search
Methaheuristics (MHs) are techniques widely used for solving complex optimization
problems. In recent years, the interest in combining MH and machine learning (ML) has …
problems. In recent years, the interest in combining MH and machine learning (ML) has …
Real-time Adaptive Partition and Resource Allocation for Multi-user End-cloud Inference Collaboration in Mobile Environment
Y Li, Z Liu, Z Kou, Y Wang, G Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The deployment of Deep Neural Networks (DNNs) requires significant computational and
storage resources, which is challenging for resource-constrained end devices. To this end …
storage resources, which is challenging for resource-constrained end devices. To this end …
A Lightweight Neural Architecture Search Model for Medical Image Classification
Accurate classification of medical images is essential for modern diagnostics. Deep learning
advancements led clinicians to increasingly use sophisticated models to make faster and …
advancements led clinicians to increasingly use sophisticated models to make faster and …
Dynamic Neural Architecture Search for Image Classification
M Gerber, N Pillay - Proceedings of the Genetic and Evolutionary …, 2024 - dl.acm.org
Neural architecture search (NAS) has proven to be effective at automating the design of
neural network architectures and hyperparameters. The design produced by NAS is …
neural network architectures and hyperparameters. The design produced by NAS is …
Robust identification of users by convolutional neural network in MATLAB and Raspberry Pi.
PU Murillo, R Jiménez-Moreno… - … Journal of Electrical …, 2024 - search.ebscohost.com
The following article presents the development of an algorithm embedded in a Raspberry Pi
3B board, where a user identification was made, using the convolutional neural network …
3B board, where a user identification was made, using the convolutional neural network …
Too-Hot-to-Handle: Insights into Temperature and Noise Hyperparameters for Differentiable Neural-Architecture-Searches
J Conrad, S Wilhelmstätter, R Asthana… - 2024 IEEE 6th …, 2024 - ieeexplore.ieee.org
The deployment of neural networks on resource-constrained hardware requires architecture
optimization algorithms that respect accuracy and computational cost. One emerging way for …
optimization algorithms that respect accuracy and computational cost. One emerging way for …
A Novel Automatic Generation Method for Neural Network by Using Iterative Function System
M Wang, L Zuo, Y Gong, Y Song, Q Zhao… - … Conference on Neural …, 2024 - Springer
This paper proposes an innovative approach for generating the topology of artificial neural
networks. The proposed method utilizes an iterative function system (IFS) to produce …
networks. The proposed method utilizes an iterative function system (IFS) to produce …