2016/05/09 by Chengxi Ye, Chen Zhao, Ye, Chengxi +8
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer architecture #Computer science #Convolutional neural network #Deep learning #Deep neural networks #FOS: Computer and information sciences #MATLAB #Machine Learning (cs.LG) #Machine learning #Multilayer perceptron #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Perceptron #Programming language #Recurrent neural network #Robot #Robotics #cs.CV #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.1605.02766
Accepted to ACM MULTIMEDIA 2016 Open Source Software Competition
openalex publication_date 2016/05/09 · arxiv created 2016/08/02 · arxiv updated 2016/08/03 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28
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.