一种改进的在线自适应模块化神经网络

针对在线模块化神经网络难以实时有效划分样本空间,提出一种改进的在线自适应模块化神经网络.首先,基于距离与密度实时更新样本局部密度及RBF神经元中心,实现样本空间在线划分;然后,将子网络模块数根据划分样本空间的个数进行自适应增减,每个子网络模块对属于对应样本空间的样本进行学习;最后,集成模块对子网络模块的输出结果进行集成,输出最终结果.针对在线梯度下降法要求样本有足够的随机性问题,提出一种具有固定记忆的在线梯度下降法对网络进行在线学习.通过对典型非线性时变系统及污水处理过程中出水氨氮浓度进行预测,验证了该模块化神经网络能够实时有效地更新RBF神经元中心,并减少学习过程中子网络模块不必要的增减,且网络结构更加简洁,能够准确预测不同的时变系统.

An improved online adaptive modular neural network

An improved online adaptive modular neural network is proposed for the online modular neural network which is difficult to effectively divide sample space in real time. Firstly, the proposed network performs on-line task decomposition by real-time updating local sample density and RBF neuron center based on distance and density. Then the number of sub-network modules is adaptively increased or decreased according to the number of divided sample spaces, and each sub-network module learns the corresponding sample. Finally, integration module integrates the output of sub-network modules and outputs the final result. For the problem of the online gradient descent method requiring the sample with enough randomness, an online gradient descent method with fixed memory is proposed. Based on the prediction of the typical nonlinear time varying systems and the effluent ammonia nitrogen values from waste water treatment processes, the experimental results show that, the proposed network can effectively update the RBF neuron center in real time, which reduces unnecessary increase or decrease of sub-network modules during the learning process, has more concise structure and can accurately predict the time-varying systems.