arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.13633cs.LGcs.NEstat.ML
收藏

静态输入下RNN的平衡支撑匹配量随时间的更新

Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input

Centre de Nanosciences et de Nanotechnologies, Université Paris Sud, Université Paris-Saclay(巴黎萨克雷大学、巴黎南大学纳米科学与纳米技术中心);Unité Mixte de Physique, CNRS, Thales, Université Paris-Sud, Université Paris-Saclay(巴黎萨克雷大学、巴黎南大学、泰雷兹集团、法国国家科学研究中心联合物理研究组);Mila, Université de Montréal(蒙特利尔大学米拉实验室);Canadian Institute for Advanced Research(加拿大高等研究院)

Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier

摘要:

平衡传播(EP)是一种生物启发的学习算法,用于收敛的递归神经网络,即由静态输入x馈送并稳定到稳态的RNN。训练收敛的RNN包括调整权重,直到输出神经元的稳定状态与目标y一致。收敛RNN也可以使用更传统的时间反向传播(BPTT)算法进行训练。在其原始配方EP中描述的实时神经元动力学的情况下,这是计算成本高。在这项工作中,我们介绍了一个离散时间版本的EP简化方程和减少模拟时间,使EP更接近实际的机器学习任务。我们首先从理论上证明,以及数值上的神经和权重更新的EP,向前的时间动态计算,是一步一步地等于BPTT获得的,与梯度计算向后的时间。当动力学的转移函数由原函数导出且稳态保持足够长时,等式是严格的。然后,我们表明,对于更标准的离散时间神经网络动力学,相同的属性是近似尊重,我们随后证明了与BPTT具有等效性能的EP训练。特别是,我们定义了第一个用EP训练的卷积架构,在MNIST上实现了~ 1%的测试误差,这是EP报告的最低误差。这些结果可以指导使用EP训练的深度神经网络的开发。

英文摘要:

Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the weights until the steady state of output neurons coincides with a target y. Convergent RNNs can also be trained with the more conventional Backpropagation Through Time (BPTT) algorithm. In its original formulation EP was described in the case of real-time neuronal dynamics, which is computationally costly. In this work, we introduce a discrete-time version of EP with simplified equations and with reduced simulation time, bringing EP closer to practical machine learning tasks. We first prove theoretically, as well as numerically that the neural and weight updates of EP, computed by forward-time dynamics, are step-by-step equal to the ones obtained by BPTT, with gradients computed backward in time. The equality is strict when the transition function of the dynamics derives from a primitive function and the steady state is maintained long enough. We then show for more standard discrete-time neural network dynamics that the same property is approximately respected and we subsequently demonstrate training with EP with equivalent performance to BPTT. In particular, we define the first convolutional architecture trained with EP achieving ~ 1% test error on MNIST, which is the lowest error reported with EP. These results can guide the development of deep neural networks trained with EP.

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。

↑