Cognitive modeling and learning with sparse binary hypervectors
This work addresses cognitive modeling and NLP tasks by introducing a novel method for sparse binary hypervectors, but it appears incremental as it builds on existing VSA frameworks.
The authors tackled the problem of cognitive modeling and learning by proposing a model using sparse binary hypervectors within the Vector Symbolic Architecture framework, resulting in improved transparency and efficiency for online training and inference. They revisited word-level embeddings and explored NLP applications, though no concrete numbers were provided.
Following the general theoretical framework of VSA (Vector Symbolic Architecture), a cognitive model with the use of sparse binary hypervectors is proposed. In addition, learning algorithms are introduced to bootstrap the model from incoming data stream, with much improved transparency and efficiency. Mimicking human cognitive process, the training can be performed online while inference is in session. Word-level embedding is re-visited with such hypervectors, and further applications in the field of NLP (Natural Language Processing) are explored.