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 2103.01118cs.NEcs.AI
收藏

使用分类器系统的深度学习:初步结果

Deep Learning with a Classifier System: Initial Results

University of the West of England(西英格兰大学)

Richard J. Preen, Larry Bull

摘要:

本文介绍了使用能够通过深度神经网络执行自适应计算的学习分类器系统的第一个结果。群体中的个体分类器由两个神经网络组成。第一个充当门控或保护组件,其使得能够在每个实例的基础上对相关联的深度神经网络进行条件计算。在再生时应用自适应变异,在寿命学习期间使用随机梯度下降来改进预测网络。在手写数字识别任务上评估全连接层和卷积层的使用,其中进化适应(i)应用于每个层的梯度下降学习率(ii)每个层内的单元数量,即,全连接神经元的数量和卷积核滤波器的数量(iii)每层的连接性,即,每个权重是否是活动的(iv)权重大小,使得能够从局部最优值逃脱。系统自动减少权重和单位的数量,同时在达到最大预测误差后保持性能。

英文摘要:

This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The first acts as a gating or guarding component, which enables the conditional computation of an associated deep neural network on a per instance basis. Self-adaptive mutation is applied upon reproduction and prediction networks are refined with stochastic gradient descent during lifetime learning. The use of fully-connected and convolutional layers are evaluated on handwritten digit recognition tasks where evolution adapts (i) the gradient descent learning rate applied to each layer (ii) the number of units within each layer, i.e., the number of fully-connected neurons and the number of convolutional kernel filters (iii) the connectivity of each layer, i.e., whether each weight is active (iv) the weight magnitudes, enabling escape from local optima. The system automatically reduces the number of weights and units while maintaining performance after achieving a maximum prediction error.

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。

↑