Gradient boosted decision trees reveal nuances of auditory discrimination behavior
Gradient boosted decision trees reveal nuances of auditory discrimination behavior
复制标题
DOI：
10.1101/2023.06.16.545302
复制
发表时间：
2024-02
影响因子：
4.3
通讯作者：
Carla Griffiths;Jules Lebert;J. Sollini;J. Bizley
中科院分区：
文献类型：
--
作者：
Carla Griffiths;Jules Lebert;J. Sollini;J. Bizley
动物心理物理学可以生成丰富的行为数据集，通常由单个受试者的数千次试验组成。被动增强模型是分析此类数据的一种很有前途的机器学习方法，部分原因是这些工具允许用户深入了解模型如何进行预测。我们训练雪貂报告一个目标词的存在，时间和偏侧化内连续提出的非目标词流。为了评估动物在音高上概括的能力，我们在试验中操纵了语音刺激的基频（F0），为了评估音高对流的贡献，我们将F0从单词标记到标记。然后，我们对试验结果和反应时间数据实施了梯度推进回归和决策树，以了解雪貂决策背后的行为因素。我们通过实现SHAP特征重要性和部分依赖图来可视化模型贡献。虽然雪貂可以在所有音高变化的条件下准确地执行任务，但我们的模型揭示了F0变化对性能的微妙影响，试验内音高变化会增加误报并延长反应时间。我们的模型识别了动物通常会误报的非目标词的子集。后续分析表明，目标和非目标词的频谱时间相似性，而不是在持续时间或幅度波形的相似性是最强的假报警的可能性的预测。最后，我们将结果与传统的混合效应模型进行了比较，揭示了梯度提升模型在这些方法上的等效或更好的性能。大多数基于实验室的听觉范式，特别是那些测试动物模型的听觉范式，很少能捕捉到现实世界听众所面临的各种听力挑战。然而，许多实验室正试图利用更现实的实验，更复杂的行为范式需要更复杂的方法来分析结果数据。在这里，我们使用了一种新的行为范式来测试雪貂听众识别目标语音的能力，并评估他们在音高变化中的概括能力。为了理解结果数据集，我们使用机器学习算法来了解受过训练的雪貂如何执行这项任务。直觉式回归和决策树是成熟的机器学习方法，不需要用户预先确定交互效果，并且伴随着可视化方法，可以深入了解多个因素最终如何塑造行为。我们比较使用梯度提升模型更标准的回归方法，并通过应用这些方法，我们证明了雪貂的性能在这项任务上的关键特征。我们的研究结果表明，这种机器学习方法是分析动物模型中行为数据的理想方法。
Animal psychophysics can generate rich behavioral datasets, often comprised of many 1000s of trials for an individual subject. Gradient-boosted models are a promising machine learning approach for analyzing such data, partly due to the tools that allow users to gain insight into how the model makes predictions. We trained ferrets to report a target word’s presence, timing, and lateralization within a stream of consecutively presented non-target words. To assess the animals’ ability to generalize across pitch, we manipulated the fundamental frequency (F0) of the speech stimuli across trials, and to assess the contribution of pitch to streaming, we roved the F0 from word token-to-token. We then implemented gradient-boosted regression and decision trees on the trial outcome and reaction time data to understand the behavioral factors behind the ferrets’ decision-making. We visualized model contributions by implementing SHAPs feature importance and partial dependency plots. While ferrets could accurately perform the task across all pitch-shifted conditions, our models reveal subtle effects of shifting F0 on performance, with within-trial pitch shifting elevating false alarms and extending reaction times. Our models identified a subset of non-target words that animals commonly false alarmed to. Follow-up analysis demonstrated that the spectrotemporal similarity of target and non-target words rather than similarity in duration or amplitude waveform was the strongest predictor of the likelihood of false alarming. Finally, we compared the results with those obtained with traditional mixed effects models, revealing equivalent or better performance for the gradient-boosted models over these approaches. AUTHOR SUMMARY The sorts of listening challenges faced by real-world listeners are rarely captured by most laboratory-based auditory paradigms, particularly those testing animal models. However, many labs are attempting to utilize more realistic experiments, and more complicated behavioral paradigms require more sophisticated approaches to analyzing the resulting data. Here, we used a new behavioral paradigm to test the ability of ferret listeners to identify target speech sounds and assess their ability to generalize across changes in pitch. To make sense of the resulting dataset, we used machine learning algorithms to understand how trained ferrets perform this task. Gradient-boosted regression and decision trees are well-established machine learning methods that do not require users to predetermine interaction effects and are accompanied by visualization methods that allow insights to be gained into how multiple factors ultimately shape behavior. We compare the use of gradient-boosted models to more standard regression approaches and, by applying these methods, we demonstrate key features of ferrets’ performance on this task. Our results suggest that this machine learning approach is ideal for analyzing behavioral data in animal models.