Abstract
Spiking neural networks are a popular area of current research in both artificial intelligence and neuroscience. Unlike second generation networks like the multilayer perceptron (MLP), they simulate rather than emulate neuronal interactions. Spiking networks have been shown to be theoretically more powerful than earlier generation networks, and have repeatedly been suggested as ideal for realtime problems due to their time-basis. Because of their sparse nature, real neural networks are also extremely power-efficient, a pressing concern in computing today. This raises the possibility of applying sparse spiking networks for power-saving. To investigate these ideas, we wish to apply a spiking network to realtime data classification. As a first step, we use a feedforward network with the SpikeProp algorithm to classify offline skeleton data derived from a depth camera. Classifier networks were successfully trained, but we found SpikeProp considerably more complex to apply than backpropagation. There is considerable potential for optimization and power efficiency, and we hope to compare the performance of our system with more established learning techniques in a realtime setting.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN) |
| Place of Publication | United States |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 1-8 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781467314909 |
| DOIs | |
| Publication status | Published - 2012 |
| Event | IEEE International Joint Conference on Neural Networks: IJCNN 2012 - Brisbane Convention Centre, Brisbane, Australia Duration: 10 Jun 2012 → 15 Jun 2012 https://web.archive.org/web/20120510232940/http://www.ieee-wcci2012.org/ (Conference website) |
Conference
| Conference | IEEE International Joint Conference on Neural Networks |
|---|---|
| Country/Territory | Australia |
| City | Brisbane |
| Period | 10/06/12 → 15/06/12 |
| Other | The 2012 IEEE World Congress on Computational Intelligence (IEEE WCCI 2012) is the largest technical event in the field of computational intelligence. It will host three conferences: the 2012 International Joint Conference on Neural Networks (IJCNN 2012), the 2012 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2012), and the 2012 IEEE Congress on Evolutionary Computation (IEEE CEC 2012). IEEE WCCI 2012 will be held in Brisbane, a awe-inspiring city situated along the Brisbane River and the eastern coast line of Australia. The congress will provide a stimulating forum for scientists, engineers, educators, and students from all over the world to discuss and present their research findings on computational intelligence. |
| Internet address |
|