TY - GEN
T1 - LightNet
T2 - 24th ACM Multimedia Conference, MM 2016
AU - Ye, Chengxi
AU - Zhao, Chen
AU - Yang, Yezhou
AU - Fermüller, Cornelia
AU - Aloimonos, Yiannis
N1 - Funding Information:
This work was funded by the support of the National Science Foundation under grant SMA 1540917 and grant CNS 1544797, and by DARPA through U.S. Army grant W911NF-14-1-0384.
Publisher Copyright:
© 2016 Copyright held by the owner/author(s).
PY - 2016/10/1
Y1 - 2016/10/1
N2 - LightNet is a lightweight, versatile, 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 learn-ing architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recur-rent 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 demon-strated as experiments. Availability: the source code and data is available at: https://github.com/yechengxi/LightNet.
AB - LightNet is a lightweight, versatile, 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 learn-ing architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recur-rent 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 demon-strated as experiments. Availability: the source code and data is available at: https://github.com/yechengxi/LightNet.
KW - Computer vision
KW - Convolutional neural networks
KW - Deep learning
KW - Image understanding
KW - Machine learning
KW - Multilayer perceptrons
KW - Natural language processing
KW - Recurrent neural networks
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=84994633817&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994633817&partnerID=8YFLogxK
U2 - 10.1145/2964284.2973791
DO - 10.1145/2964284.2973791
M3 - Conference contribution
AN - SCOPUS:84994633817
T3 - MM 2016 - Proceedings of the 2016 ACM Multimedia Conference
SP - 1156
EP - 1159
BT - MM 2016 - Proceedings of the 2016 ACM Multimedia Conference
PB - Association for Computing Machinery, Inc
Y2 - 15 October 2016 through 19 October 2016
ER -