Name
Abstract | ||
|---|---|---|
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generation and filtering of useful random projections has better biological justification, is faster, easier to train and may in practice solve non-separable problems of higher complexity than typical feedforward neural networks. Estimation of confidence in network decisions is done by visualization of the number of nodes that agree with the final decision. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-04274-4_81 | ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I |
Keywords | Field | DocType |
biological justification,biological perspective,complex logic,final decision,higher complexity,network decision,non-separable problem,simpler algorithm,typical feedforward neural network,useful random projection,Almost Random Projection Machine | Random projection,Feedforward neural network,Computer science,Stochastic neural network,Probabilistic neural network,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Backpropagation,Machine learning | Conference |
Volume | ISSN | Citations |
5768 | 0302-9743 | 4 |
PageRank | References | Authors |
0.44 | 5 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| wlodzislaw duch | 1 | 780 | 91.91 |
| tomasz maszczyk | 2 | 42 | 5.29 |