[论文解读] Identifying Learning Rules From Neural Network Observables

Aran Nayebi, Sanjana Srivastava+2 more|arXiv (Cornell University)|Oct 22, 2020

Neural Networks and Applications参考文献 44被引用 7

一句话总结

本文提出一种虚拟实验框架，通过权重、激活和逐层活动变化的聚合统计量来识别神经网络中的学习规则。通过在人工网络上模拟神经科学实验，结果表明，仅依赖激活模式的简单分类器即可有效区分不同学习规则，且对测量噪声和单元采样不足具有鲁棒性，提示在生物系统中，对约100–500个神经元的电生理记录可能已足够用于学习规则的识别。

ABSTRACT

The brain modifies its synaptic strengths during learning in order to better adapt to its environment. However, the underlying plasticity rules that govern learning are unknown. Many proposals have been suggested, including Hebbian mechanisms, explicit error backpropagation, and a variety of alternatives. It is an open question as to what specific experimental measurements would need to be made to determine whether any given learning rule is operative in a real biological system. In this work, we take a "virtual experimental" approach to this problem. Simulating idealized neuroscience experiments with artificial neural networks, we generate a large-scale dataset of learning trajectories of aggregate statistics measured in a variety of neural network architectures, loss functions, learning rule hyperparameters, and parameter initializations. We then take a discriminative approach, training linear and simple non-linear classifiers to identify learning rules from features based on these observables. We show that different classes of learning rules can be separated solely on the basis of aggregate statistics of the weights, activations, or instantaneous layer-wise activity changes, and that these results generalize to limited access to the trajectory and held-out architectures and learning curricula. We identify the statistics of each observable that are most relevant for rule identification, finding that statistics from network activities across training are more robust to unit undersampling and measurement noise than those obtained from the synaptic strengths. Our results suggest that activation patterns, available from electrophysiological recordings of post-synaptic activities on the order of several hundred units, frequently measured at wider intervals over the course of learning, may provide a good basis on which to identify learning rules.

研究动机与目标

• 确定是否可以在不了解网络架构或损失函数的前提下，仅从神经可观测量的聚合统计量中识别出神经网络中的学习规则。
• 评估不同类型的神经测量——权重、激活或活动变化——在学习规则区分中的有效性。
• 在真实实验约束条件下（如轨迹采样不足和测量噪声）评估这些识别方法的鲁棒性。
• 识别哪些可观测统计量最有助于区分生物上合理的不同学习规则。
• 为系统神经科学中的未来在体实验设计提供计算框架支持。

提出的方法

• 在多样化神经网络架构、损失函数、学习规则超参数和权重初始化条件下，模拟大规模学习轨迹数据集。
• 从三种可观测量中提取聚合统计量：突触权重、神经激活和瞬时的逐层活动变化。
• 训练线性和非线性分类器（包括随机森林），仅基于这些可观测量预测底层学习规则。
• 通过子采样神经元和限制对学习轨迹上时间点的访问，引入实验真实性。
• 通过在训练过程中未见过的架构和训练课程上进行测试，评估模型的泛化能力。
• 通过受控扰动，比较不同可观测量在测量噪声和采样不足下的鲁棒性。

实验结果

研究问题

• RQ1 是否可以在不了解网络架构或损失函数的前提下，仅从神经可观测量的聚合统计量中可靠识别学习规则？
• RQ2 在真实测量约束下，哪种可观测量——权重、激活或活动变化——能为学习规则识别提供最鲁棒的信号？
• RQ3 在轨迹采样不足的情况下，测量的时间间隔如何影响学习规则识别的准确性？
• RQ4 测量噪声和单元采样不足在多大程度上会降低学习规则识别的性能？
• RQ5 基于激活的统计量是否能在未见过的网络架构和训练课程上实现泛化？

主要发现

• 即使不了解底层架构或损失函数，仅使用权重、激活或逐层活动变化的聚合统计量，也能可靠地区分不同类别的学习规则。
• 简单的非线性分类器（随机森林）在所有三种可观测量类型上均表现出相当的性能，表明每种可观测量均提供了足够的判别信息。
• 基于激活的统计量在应对单元采样不足和测量噪声方面显著优于基于权重的统计量，后者在极低噪声水平下即迅速退化。
• 在更宽的时间间隔下采集的测量结果比连续测量更具鲁棒性，尤其在激活模式方面。
• 该方法在未见的架构和训练课程上仍具泛化能力，表明其未过度拟合特定网络结构或任务。
• 在学习过程中以较宽时间间隔采样约100–500个神经元的突触后活动电生理记录，可能为生物系统中学习规则的识别提供切实可行的基础。