We present a computational neural network model of recognition memory based on the biological structures of the hippocampus and medial temporal lobe cortex (MTLC), which perform complementary learning functions. The hippocampal component of the model contributes to recognition by recalling specific studied details. MTLC can not support recall, but it is possible to extract a scalar familiarity signal from MTLC that tracks how well the test item matches studied items. We present simulations that establish key qualitative differences in the operating characteristics of the hippocampal recall and MTLC familiarity signals, and we identify several manipulations (e.g., target-lure similarity, interference) that differentially affect the two signals. We also use the model to address the stochastic relationship between recall and familiarity (i.e., are they independent), and the effects of partial vs. complete hippocampal

Abstract not found

We readily acquire memories of events and situations in our daily lives. There is a broad consensus that the hippocampal system (HS) plays a critical role in the encoding and retrieval of such "episodic" memories. But how the HS subserves this mnemonic function is not fully understood. This article presents a computational model, SMRITI,that demonstrates how a transient pattern of activity representing an event can be transformed rapidly into a persistent and robust memory trace as a result of long-term potentiation within structures whose architecture and circuitry resemble those of the HS. Predictions and implications of the model are discussed. LONG ABSTRACT We readily remember events and situations in our daily lives and rapidly acquire memories of specific events by watching a telecast or reading a newspaper. There is a broad consensus that the hippocampal system (HS), consisting of the hippocampal formation and neighboring cortical areas, plays a critical role in the encoding and retrieval of such "episodic" memories. But how the HS subserves this mnemonic function is not fully understood. This article presents a computational model, SMRITI, that demonstrates how a cortically expressed transient pattern of activity representing an event can be transformed rapidly into a persistent and robust memory trace as a result of long-term potentiation within structures whose architecture and circuitry resemble those of the HS. Memory traces formed by the model respond to partial cues, and at the same time, reject similar but erroneous cues. During retrieval these memory traces, acting in concert with cortical circuits encoding semantic, causal, and procedural knowledge, can recreate activation-based representations of memorized events. The model explicates the representa...

We present an overview of our computational approach towards understanding the different contributions of the neocortex and hippocampus in learning and memory. The approach is based on a set of principles derived from converging biological, psychological, and computational constraints. The most central principles are that the neocortex employs a slow learning rate and overlapping distributed representations to extract the general statistical structure of the environment, while the hippocampus learns rapidly using separated representations to encode the details of specific events while suffering minimal interference. Additional principles concern the nature of learning (error-driven and Hebbian), and recall of information via pattern completion. We summarize the results of applying these principles to a wide range of phenomena in conditioning, habituation, contextual learning, recognition memory, recall, and retrograde amnesia, and point to directions of current development. 2 Computat...

for events and their spatial context:

Learning in animals is modular (though not encapsulated), and there is growing interest in modular, non-homogeneous models of learning within the neural networks community. Behavior-based artificial intelligence, with its emphasis on modular components, seems an ideal platform for implementing such systems in autonomous agents. However, historically this community has shunned representation issues, and there is no established system for combining modular control and modular adaptivity. This paper describes a behavior based architecture and development approach designed to enable research in modular adaptivity.

Although computational considerations suggest that a resource-limited memory system may have to trade off capacity for generalization ability, such a trade-off has not been demonstrated in the past. We describe a simple model of memory that exhibits this trade-off and describe its performance in a variety of tasks.

Abstract not found