Ann1DnBackpropagation Artificial Neural Network in C++ | |
Download |
Ann1Dn Ranking & Summary
Advertisement
- License:
- GPL
- Publisher Name:
- Chesnokov Yuriy
- Publisher web site:
- http://www.codeproject.com/Members/Chesnokov-Yuriy
- Operating Systems:
- Windows All
- File Size:
- 97 KB
Ann1Dn Tags
- Performance Report Performance neural network estimation neural network simulator neural artificial neural network architectures neural network model neural network framework artificial neural network neural network library neural network platform artificial intellige use neural network neural network trainer train neural network simulate neural network neural network analyzer map neural network generate neural network neural network creator neural network engine use artificial neural network create neural network neural network function neural network implementation neural network class view neural network simulation neural network simulation analyze neural network neural network analysis study neural network test neural network neural network usage experiment neural network performance estimation design neural network create artificial synaps artificial synaps generator Self Artificial Learning Neural Network evolution spike neural network neural network simluation neural network generator Kohonen neural network develop neural network neural network development neural network forecasting Neural Network Forecast Multi-Layer Neural Network Neural Network example learn Neural Network neural data backpropagation
Ann1Dn Description
Ann1Dn was developed to be a backpropagation artificial neural network console application with validation and test sets for performance estimation using uneven distribution metrics. A console based implementation of the backpropogation neural network C++ library I developed and used during my research in medical data classification and the CV library for face detection.The console supports training data random separation to train, validation, and test sets before backpropagation training. Random separation allows to obtain a representative train set comparing performance on validation and test parts. A validation set is useful for preventing over-fitting by estimating the performance on that set. At the end of the backpropagation session, I save both network configurations, the one with the best performance on the validation set and the last training epoch configuration. For performance estimation, I use sensitivity, specificity, positive predictivity, negative predictivity, and accuracy metrics. The console implementation is easier to use, you avoid a lot of mouse clicking in GUI applications, and may automate the process with batch files for choosing the right network topology, the best performance on the validation and test sets, and so on.
Ann1Dn Related Software