We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency — as though these inferences are a reflex response of our cognitive apparatus. This remarkable human ability poses a challenge for cognitive science and computational neuroscience: How can a network of slow neuron-like elements represent a large body of systematic knowledge and perform a wide range of inferences with such speed? The connectionist model Shruti attempts to address this challenge by demonstrating how a neurally plausible network can encode a large body of semantic and episodic facts, systematic rules, and knowledge about entities and types, and yet perform a wide range of explanatory and predictive inferences within a few hundred milliseconds. Relational structures (frames, schemas) are represented in Shruti by clusters of cells, and inference in Shruti corresponds to a transient propagation of rhythmic activity over such cell-clusters wherein dynamic bindings are represented by the synchronous firing of appropriate cells. Shruti encodes mappings across relational structures using high-efficacy links that enable the propagation of rhythmic activity, and it encodes items in long-term memory as coincidence and conincidence-error detector circuits that become active in response to the occurrence (or non-occurrence) of appropriate coincidences in the on going flux of rhythmic activity.

Biological networks are capable of gradual learning based on observing a large number of exemplars over time as well as of rapidly memorizing specific events as a result of a single exposure. The focus of research in neural networks has been on gradual learning, and the modeling of one-shot memorization has received relatively little attention. Nevertheless, the development of biologically plausible computational models of rapid memorization is of considerable value, since such models would enhance our understanding of the neural processes underlying episodic memory formation. A few researchers have attempted the computational modeling of rapid (one-shot) learning within a framework described variably as recruitment learning and vicinal algorithms. Here it is shown that recruitment learning and vicinal algorithms can be grounded in the biological phenomena of long-term potentiation and longterm depression. Toward this end, a computational abstraction of LTP and LTD is presented, and an "algorithm" for the recruitment of binding-detector (or coincidence-detector) cells is described and evaluated using biologically realistic data.

this report. Kautz [79] modeled plan recognition logically in a manner that allowed goals and plans to be described at various levels of abstraction. Etzioni et al. [94, 95, 92, 93] developed a version space algorithm for plan recognition that is provably sound and polynomial time [94, 93]. Weld et al. developed goal recognition algorithms using inductive logic programming [90] and version-space algebra [89, 168, 88] in the context of programming by demonstration

Our ability to remember events and situations in our daily life demonstrates our ability to rapidly acquire new memories. There is a broad consensus that the hippocampal system (HS) plays a critical role in the formation and retrieval of such memories. A computational model is described that demonstrates how the HSmay rapidly transform a transient pattern of activity representing an event or a situation into a persistent structural encoding via long-term potentiation and long-term depression. Introduction Our ability to remember events and situations in our daily life and acquire facts after reading a newspaper demonstrates our ability to rapidly acquire new memories. This form of memory has been the focus of considerable research in psychology and cognitive neuroscience and has been characterized variably as declarative, locale, and explicit. There is a broad consensus that this form of memory is distinct, both in its functional properties and its neural basis, from other for...

The memorization of events and situations (episodic memory) requires the rapid formation of neural circuits for detecting bindings and binding-errors. The formation of binding-error detectors, however, is problematic given their paradoxical behavior. A computational model is described that demonstrates how a transient pattern of activity representing an episode can lead to the rapid formation of circuits for detecting bindings and bindings-errors as a result of long-term potentiation within structures whose architecture and circuitry match those of the hippocampal formation, a neural structure known to be critical to episodic memory formation.

The memorization of events and situations (episodic memory) requires the rapid formation of a memory trace consisting of several functional components. A computational model is described that demonstrates how a transient pattern of activity representing an episode can lead to the rapid recruitment of appropriate circuits as a result of long-term potentiation within structures whose architecture and circuitry match those of the hippocampal formation, a neural structure known to play a critical role in the formation of such memories.

shruti is a connectionist model that demonstrates how a network of neuron-like elements can encode a large body of semantic, episodic, and causal knowledge, and rapidly make decisions and perform explanatory and predictive reasoning. To further ground this model in the functioning of the brain it must be shown that components of the model can be learned in a neurally plausible manner. Previous work has already demonstrated the rapid learning of episodic facts via cortico-hippocampal interactions.

It is argued that the memorization of events and situations (episodic memory) requires the rapid formation of neural circuits responsive to binding errors and binding matches. While the formation of circuits responsive to binding matches can be modeled by associative learning mechanisms, the rapid formation of circuits responsive to binding errors is difficult to explain given their seemingly paradoxical behavior; such a circuit must be formed in response to the occurrence of a binding (i.e., a particular pattern in the input), but subsequent to its formation, it must not fire anymore in response to the occurrence of the very binding (i.e., pattern) that led to its formation. A plausible account of the formation of such circuits has not been offered. A computational model is described that demonstrates how a transient pattern of activity representing an event can lead to the rapid formation of circuits for detecting bindings and binding errors as a result of long-term potentiation with...

Abstract not found