To isolate brain activity that may reflect effective cognitive processes during the study phase of a memory task, cognitive neuroscientists commonly contrast brain activity during study of later-remembered versus later-forgotten items. This "subsequent memory effect" method has been described as identifying brain activity "predictive" of memory outcome. However, the modern field of machine learning distinguishes between descriptive analysis, subject to overfitting, and true prediction, that can classify untrained data. First, we tested whether classic event-related potential signals were, in fact, predictive of later old/new recognition memory (N=62, 225 items/participant); this produced significant, but small predictive success. Next, pattern classification of the multivariate spatio-temporal features of the single-trial EEG waveform also succeeded in predicting memory. However, the prediction was still small in magnitude. In addition, topographic maps suggested individual differences in sources of predictive activity. These findings suggest that on average, brain activity, measured by EEG, during the study phase is only marginally "predictive" of subsequent memory. It is possible that this predictive approach will succeed better when other experimental factors known to influence memory outcome are also integrated into the models.

中文翻译：

---

从研究相关的大脑活动预测记忆

为了在记忆任务的研究阶段隔离可能反映有效认知过程的大脑活动，认知神经科学家通常在研究后来记住的和后来忘记的项目期间对比大脑活动。这种“随后的记忆效应”方法被描述为识别记忆结果的“预测性”大脑活动。然而，现代机器学习领域区分了描述性分析（受过度拟合）和真实预测（可以对未经训练的数据进行分类）。首先，我们测试了经典事件相关的潜在信号是否实际上可以预测后来的旧/新识别记忆（N = 62，225 个项目/参与者）；这产生了显着但很小的预测成功。下一个，单次试验 EEG 波形的多元时空特征的模式分类也成功地预测了记忆。然而，预测的幅度仍然很小。此外，地形图表明预测活动来源的个体差异。这些发现表明，平均而言，在研究阶段，通过脑电图测量的大脑活动对后续记忆的“预测性”只是微不足道的。当已知影响记忆结果的其他实验因素也被整合到模型中时，这种预测方法可能会更好地成功。在研究阶段，通过脑电图测量的大脑活动对随后的记忆只有轻微的“预测”。当已知影响记忆结果的其他实验因素也被整合到模型中时，这种预测方法可能会更好地成功。在研究阶段，通过脑电图测量的大脑活动对随后的记忆只有轻微的“预测”。当已知影响记忆结果的其他实验因素也被整合到模型中时，这种预测方法可能会更好地成功。