Ensemble Neural Networks (ENN): A gradient-free stochastic method

by   Yuntian Chen, et al.

In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are calculated by the ensemble randomized maximum likelihood algorithm (EnRML), which is an inverse modeling method. The ENN is able to simultaneously provide estimations and perform uncertainty quantification since it is built under the Bayesian framework. The ENN is also robust to small training data size because the ensemble of stochastic realizations essentially enlarges the training dataset. This constitutes a desirable characteristic, especially for real-world engineering applications. In addition, the ENN does not require the calculation of gradients, which enables the use of complicated neuron models and loss functions in neural networks. We experimentally demonstrate benefits of the proposed model, in particular showing that the ENN performs much better than the traditional Bayesian neural networks (BNN). The EnRML in ENN is a substitution of gradient-based optimization algorithms, which means that it can be directly combined with the feed-forward process in other existing (deep) neural networks, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), broadening future applications of the ENN.



There are no comments yet.


page 13


Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

Recurrent neural networks (RNNs) have shown promising performance for la...

A Novel Neural Network Training Framework with Data Assimilation

In recent years, the prosperity of deep learning has revolutionized the ...

Channel-Directed Gradients for Optimization of Convolutional Neural Networks

We introduce optimization methods for convolutional neural networks that...

Adapting Resilient Propagation for Deep Learning

The Resilient Propagation (Rprop) algorithm has been very popular for ba...

Convolutional neural networks with fractional order gradient method

This paper proposes a fractional order gradient method for the backward ...

Partitioned integrators for thermodynamic parameterization of neural networks

Stochastic Gradient Langevin Dynamics, the "unadjusted Langevin algorith...

Decoupled Neural Interfaces using Synthetic Gradients

Training directed neural networks typically requires forward-propagating...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.