"Ustract-We sbow tbe reaslblllty or usiog a distribuled assoclatln melllOry as the recoaaltloo componeat ror a bla-pkkiq system. Tbe system displays IDvariaD« to geometric distol1loas and a robust ,.. spout Ia the pteseace or DOise, oc:clusloas. aad memory raults. AJ­ tboulla our system Is primarily cooceraed witb two-dimensiOonal object reeoillitioa we suUest bow our metlaod can be extended tO...

The immune system offers to be a rich source of metaphors to guide the exploration of the notion of an adaptive system. We might define a class of systems which are inspired by, but diverge from, descriptions of the immune system, and refer to them as immune-bused systems. The research reported here is motivated by a desire to explore the possibilities of such systems. Specifically, we attempt ...

Searching for an object in a cluttered environment takes advantage of different cues, explicit attentional cues, such as arrows, and visual cues, such as saliency, but also memory. Behavioral studies manipulating the spatial relationships between context and target in visual search suggest that the memory of context-target associations could be retrieved quickly and act at an early perceptual s...

Searching for an object in a cluttered environment takes advantage of different cues, explicit attentional cues, such as arrows, and visual cues, such as saliency, but also memory. Behavioral studies manipulating the spatial relationships between context and target in visual search suggest that the memory of context-target associations could be retrieved quickly and act at an early perceptual s...

Content Addressable Memories or CAMs are popular parallel matching circuits. They provide the capability, in hardware, to search a table of data for a matching entry. This functionality is a high performance alternative to popular software-based searching schemes. CAMs are typically found in embedded circuitry where fast matching is essential. This paper presents a novel approach to CAM impleme...

Motivated by the findings of modular structure in the association cortex, we study a multi-modular model of associative memory that can successfully store memory patterns with different levels of activity. We show that the segregation of synaptic conductances into intra-modular linear and inter-modular nonlinear ones considerably enhances the network's memory retrieval performance. Compared wit...