LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
Strong inhibitory signaling underlies stable temporal dynamics and working memory in spiking neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
A timing-based backpropagation algorithm for multi-spike SNNs achieves ANN-comparable accuracy and identifies an optimal time constant for spike counts not seen in single-spike models.
citing papers explorer
-
Hypothesis generation and updating in large language models
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
-
Timing-Based Backpropagation in Spiking Neural Networks Without Single-Spike Restrictions
A timing-based backpropagation algorithm for multi-spike SNNs achieves ANN-comparable accuracy and identifies an optimal time constant for spike counts not seen in single-spike models.