知镜 Cognispect · 医学文献与研究工作台

Synthetic dreaming for state-conditioned epistemic exploration in neural networks

Lachiany M.
Neural Netw · 2026-09-19 · PMID 42785214

文献摘要

Artificial intelligence (AI) systems typically learn from externally provided data, which constrains their generalization, robustness under distributional shift, and creative capacity. Inspired by biological dreaming, we propose a learning framework termed synthetic dreaming, in which a neural network generates internally imagined training samples conditioned on its evolving latent representations and integrates them into the optimization process. This work formalizes synthetic dreaming within a probabilistic framework using a hybrid training objective that combines empirical data with internally generated samples through a regulated dream-weight coefficient λ and a high-level latent variable h. The framework is instantiated using a Transformer-based language model coupled with a conditional variational dream generator. Empirical results show consistent performance improvements or trends over strong baselines. In particular, synthetic dreaming reduces test perplexity by up to  ∼ 15% and out-of-distribution perplexity by  ∼ 19%, while increasing lexical diversity (measured by n-gram entropy) and improving robustness under input corruption (reducing degradation from  ∼ 41% to  ∼ 19% under 10% masking). These results indicate that state-conditioned internal sample generation can improve generalization and robustness by expanding and regularizing the learned representation space. The proposed framework provides a concrete and computationally efficient mechanism for integrating internal simulation into neural network training.

在知镜精读原文来源DOI 原文

知镜提供医学文献检索、阅读笔记、人体图谱、统计绘图与研究复现工具。