Analog Artificial Neural Networks (ANNs) could be the core of an “intelligent” signal processor, with the today used digital processing replaced by a raw “data driven” methodology. Characteristic of this approach is: analog input/output: signals do not need A/D and D/A converters; speed: an analog system can be faster than a digital or a mixed-mode one; effectiveness: ANNs already demonstrated their power in many applications; low power: analog circuits can save power. NEPS2 is a NEural Signal Processor, which offers the above characteristics and is based on a traditional, available and not expensive double poly-silicon double metal commercial VLSI process.