LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning
Chengxi Ye, Chen Zhao, Yezhou Yang, Cornelia Fermuller, Yiannis Aloimonos
- Year
- 2016
- Access
- Open access
Abstract
LightNet is a lightweight, versatile and purely Matlab-based deep learning framework. The idea underlying its design is to provide an easy-to-understand, easy-to-use and efficient computational platform for deep learning research. The implemented framework supports major deep learning architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The framework also supports both CPU and GPU computation, and the switch between them is straightforward. Different applications in computer vision, natural language processing and robotics are demonstrated as experiments.
Keywords
Related papers
How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments
Ji-Hoon Hwang, Daeyoung Kim, Hyung-Suk Yoon +2 more
2026
Uncertainty-guided evolvable recognition framework for industrial robots via prototype-based fuzzy inference and evidence fusion
Yanrun Zhou, Zihao Lei, Guangrui Wen +4 more
Robotics and Computer-Integrated Manufacturing · 2026
Point cloud registration for non-destructive, high-resolution coating thickness measurement from 3D scans
Simon Duenser, Ivo Aschwanden, Raamadaas Krishnadas +2 more
Robotics and Computer-Integrated Manufacturing · 2026
Toward the intelligent robotics era: Multimodal flexible haptic sensors for advanced perception systems
Sili Ding, Feng Xu, Jie Chen +3 more
Progress in Materials Science · 2026