Elder James R, Zheng Jie, Shimelis Lydia B, Rutishauser Ueli, Lin Milo M
Green Center for Systems Biology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
Lyda Hill Dept. of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.
bioRxiv. 2025 Feb 4:2025.01.30.635821. doi: 10.1101/2025.01.30.635821.
Neural circuits must balance plasticity and stability to enable continual learning without catastrophic forgetting, a pervasive feature of artificial neural networks trained using end-to-end learning (e.g. backpropagation). Here, we apply an alternative, hierarchical learning algorithm to the cognitive task of boundary detection in video clips. In contrast to backpropagation, hierarchical training converges to a network executing a fixed schema and generates firing statistics consistent with single-neuron recordings from human subjects performing the same task. The hierarchically trained network's schema circuit remains invariant following training on sparse data, with additional data serving to refine the upstream representation.
神经回路必须平衡可塑性和稳定性，以实现持续学习而不会出现灾难性遗忘，这是使用端到端学习（例如反向传播）训练的人工神经网络的一个普遍特征。在这里，我们将一种替代的分层学习算法应用于视频剪辑中的边界检测认知任务。与反向传播不同，分层训练收敛到执行固定模式的网络，并生成与执行相同任务的人类受试者的单神经元记录一致的放电统计数据。在稀疏数据上进行训练后，分层训练网络的模式电路保持不变，额外的数据用于细化上游表示。
