Language learning
Structured connectionist models of inference and memory
- SHRUTI:
Shruti demonstrates how a neurally plausible system can encode a large body
of semantic and episodic facts, entities and types, and rule-like mappings,
and yet perform a wide range of inferences within a few hundred milliseconds.
- SMRITI:
SMRITI demonstrates how a transient pattern of activity representing an
event can be rapidly transformed into a robust memory trace
within the hippocampal system as a result of cortico-hippocampal interactions.
