Title | ||
---|---|---|
No-Prop-fast - A High-Speed Multilayer Neural Network Learning Algorithm: MNIST Benchmark and Eye-Tracking Data Classification. |
Abstract | ||
---|---|---|
While the No-Prop (no back propagation) algorithm uses the delta rule to train the output layer of a feed-forward network, No-Prop-fast employs fast linear regression learning using the Hopf-Wiener solution. Ten times faster learning speeds can be achieved on large datasets like the MNIST benchmark, compared to one of the fastest backpropagation algorithm known. Additionally, the plain feed-forward network No-prop-fast can distinguish gaze movements on cartoons with and without text, as well as age-specific attention shifts between text and picture areas with minimal pre-processing. Continuously learning mobile robots and adaptive intelligent systems require such fast learning algorithms. Almost real-time learning speeds enable lower turn-around cycles in product development and data analysis. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-41013-0_46 | Communications in Computer and Information Science |
Field | DocType | Volume |
Delta rule,Semi-supervised learning,MNIST database,Computer science,Wake-sleep algorithm,Algorithm,Eye tracking,Echo state network,Data classification,Backpropagation | Conference | 383 |
ISSN | Citations | PageRank |
1865-0929 | 0 | 0.34 |
References | Authors | |
11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
André F. Krause | 1 | 43 | 7.27 |
KAI ESSIG | 2 | 33 | 4.49 |
Martina Piefke | 3 | 33 | 4.55 |
Thomas Schack | 4 | 33 | 7.51 |