ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures

Abstracl--A model to implement parallel search of compressed or distributed pattern recognition codes in a neural network hierarchy is introduced. The search process functions well with either Jast learning or slow h'arning, and can robustly cope with sequences of asynchronous input patterns in real-time. The search process emerges" when computational properties of the chemical synapse, such as transmitter accumulation, release, inactivation, and modulation, are embedded within an Adaptive' Resonance Theory architecture called A R T 3. Formal analogs of ions such as Naand Ca'control nonlinear feedback interactions that enable presynaptic transmitter dynamics to model the postsynaptic short-term memory representation of a pattern recognition code. Reinforcement feedback can modulate the search process by altering the A R T 3 vigilance parameter or directly engaging the search mechanism. The search process is a ,[orm qfl hypothesis testing capabh' of discovering appropriate representations of a nonstationa O, input environment.