From ANN to Biomimetic Information Processing

摘要: Artificial neural networks (ANN) are useful components in today’s data analysis toolbox. They were initially inspired by the brain but today accepted to be quite different from it. ANN typically lack scalability and mostly rely on supervised learning, both of which biologically implausible features. Here we describe evaluate a novel cortex-inspired hybrid algorithm. It is found perform par with Support Vector Machine (SVM) classification activation patterns rat olfactory bulb. On-line unsupervised learning shown provide significant tolerance sensor drift, an important property algorithms used analyze chemo-sensor data. Scalability approach illustrated MNIST dataset handwritten digits.