Spiking Neural Networks in Stream Learning scenarios

Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks [1]. In Stream Learning (SL), aka data stream mining or machine learning for data streams, applications (such as mobile phones, sensor networks, industrial process controls and intelligent user interfaces, among others) generate huge amounts of data in the form of fast streams, acquiring special relevance with the advent of the Big Data and IoT era. In these scenarios, algorithms cannot explicitly access all historical data because the storage capacity needed for this purpose becomes unmanageable. Indeed, data streams are fast and large (potentially, infinite), so information must be extracted from them in real-time, being therefore necessary to learn in an online manner [2]. Besides, some of these scenarios produce non-stationary data streams which are becoming increasingly prevalent, and where the process generating the data may change over time, producing changes in the patterns to be modeled (concept drift).