Emotion significantly influences cognition, enhancing memory and learning under certain conditions. Drawing on this principle, emotion-augmented deep learning investigates how affective states can improve neural network architectures and learning paradigms, achieving better generalization than non-emotional models. However, existing methods often rely solely on objective neurophysiological factors, neglecting the role of subjectivity in emotion. To bridge this gap, the present study introduces Emotional Regulation, a novel framework for modeling emotion in deep learning through artificial subjective experience. The method employs pre-training based on affective stimuli, balancing non-emotional and emotionally-influenced responses in downstream task optimization. Extensive experimentation was conducted in image classification, pre-training ResNet and ViT architectures on four emotional datasets, using CIFAR-10 and -100 as target benchmarks. Results reveal improvements over the aforementioned backbones, providing evidence of Emotional Regulation as a promising method for defining emotion-augmented deep learning through artificial subjective experience. Furthermore, the proposed approach overcomes the related work in image classification based on CIFAR, revealing Emotional Regulation as the new state-of-the-art in emotion-augmented deep learning for large-scale vision datasets. The study also enforces evidence of the impact of affective states in improving machine learning tasks' optimization, encouraging further investigation on emotion-inspired architectures.

翻译：情绪显著影响认知，能在特定条件下增强记忆与学习。基于此原理，情绪增强型深度学习研究情感状态如何改善神经网络架构与学习范式，从而获得优于非情绪模型的泛化能力。然而，现有方法往往仅依赖客观神经生理因素，忽视了情绪的主观性。为弥补这一不足，本研究引入情绪调节（Emotional Regulation）这一通过人工主观体验模拟深度学习情感的新框架。该方法采用基于情感刺激的预训练，在下游任务优化中平衡非情绪响应与情绪影响响应。实验在图像分类任务中展开，使用CIFAR-10和CIFAR-100作为目标基准，在四个情感数据集上对ResNet和ViT架构进行预训练。结果表明，上述骨干网络性能得到提升，证明情绪调节作为通过人工主观体验定义情绪增强型深度学习的可行方法。进一步地，所提方法超越了基于CIFAR的图像分类相关研究，揭示了情绪调节在大规模视觉数据集的情绪增强型深度学习中的最新最优性能。本研究还强化了情感状态对改善机器学习任务优化作用的实证证据，鼓励对情感启发架构的进一步探索。