通过物理网络中的非干扰反馈化学信号进行学习
Learning by non-interfering feedback chemical signaling in physical networks
摘要:
非神经和神经生物系统都可以学习。因此,与其关注纯粹的类脑学习,人们正在努力研究物理系统中的学习。这些努力包括平衡传播(EP)和耦合学习(CL),这需要在学习过程中存储两个不同的状态-自由状态和扰动状态,以保留有关梯度的信息。受黏菌的启发,我们提出了一种新的学习算法,它植根于化学信号,不需要存储两个不同的状态。相反,输出误差信息被编码在化学信号中,该化学信号以与激活/前馈信号类似的方式扩散到网络中。稳态反馈化学品浓度与激活信号一起在本地存储所需的梯度信息。我们使用物理线性流网络应用我们的算法,并使用Iris数据集进行测试,准确率为93%。我们还证明了我们的算法执行梯度下降。最后,除了将我们的算法直接与EP和CL进行比较之外,我们还讨论了算法的生物相容性。
英文摘要:
Both non-neural and neural biological systems can learn. So rather than focusing on purely brain-like learning, efforts are underway to study learning in physical systems. Such efforts include equilibrium propagation (EP) and coupled learning (CL), which require storage of two different states-the free state and the perturbed state-during the learning process to retain information about gradients. Inspired by slime mold, we propose a new learning algorithm rooted in chemical signaling that does not require storage of two different states. Rather, the output error information is encoded in a chemical signal that diffuses into the network in a similar way as the activation/feedforward signal. The steady state feedback chemical concentration, along with the activation signal, stores the required gradient information locally. We apply our algorithm using a physical, linear flow network and test it using the Iris data set with 93% accuracy. We also prove that our algorithm performs gradient descent. Finally, in addition to comparing our algorithm directly with EP and CL, we address the biological plausibility of the algorithm.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。