Zhoa, Li, Geng, and Ma recently wrote a poorly written but interesting paper “Artificial Neural Networks Based on Fractal Growth”. The paper describes a neural net architecture that grows in a fractal pattern (Similar to evolutionary artificial neural nets, see e.g. “A review of evolutionary artificial neural networks“ Yao 1993). The input region assigned to each label by the neural net grows in a fractal like pattern to adapt to new data. The growth of the nodes suggest that the fractal neural network classifications are similar to k-Nearest Neighbor with k=1 or an SVM with radial basis functions. They report on application of their method to SEMG (Surface electromyogram signal) classification.
You are currently browsing the monthly archive for November 2015.