A Data Streaming Approach to Pattern Recognition with Evolvable Neural Networks

A major challenge in performing pattern recognition with neural networks is large input data sets; for example, high-resolution static images. There is a direct relationship between the number of inputs and the number of neurons and links required to process those inputs. Specifically, as the number of inputs increases linearly, the complexity of the neural net increases exponentially. We present a new approach to pattern recognition, where input data is “streamed” into a feedback neural net. This is done by distributing the input temporally, such that a portion of the inputs is used for each iteration of the neural net. Therefore, pattern recognition is automatically performed in conveniently sized segments with a single neural net. This reduces the amount of evolution that must be performed to train the neural net.