REVIEW 2 cited by
Learning Associative Inference Using Fast Weight Memory
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM model with an associative memory, dubbed Fast Weight Memory (FWM). Through differentiable operations at every step of a given input sequence, the LSTM updates and maintains compositional associations stored in the rapidly changing FWM weights. Our model is trained end-to-end by gradient descent and yields excellent performance on compositional language reasoning problems, meta-reinforcement-learning for POMDPs, and small-scale word-level language modelling.
Forward citations
Cited by 2 Pith papers
-
Re:Frame -- Retrieving Experience From Associative Memory
A plug-in that retrieves expert actions from a small associative memory buffer improves offline Decision Transformer performance on three of four D4RL MuJoCo tasks, with gains up to 10.7 points.
-
Generative Retrieval for Book search
GBS applies generative retrieval to book search by augmenting training data with hierarchical book identifiers and pseudo-queries, and encoding books with outline-based bi-level positions and retentive attention, repo...
Discussion (0). Continue with ORCID to comment.