Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information $I_R$. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well trained, targeted to approximate a specific function. Despite a general belief that a composite neural network may perform better than a single component, the overall performance characteristics are not clear. In this work, we construct the framework of a composite network, and prove that a composite neural network performs better than any of its pre-trained components with a high probability bound. In addition, if an extra pre-trained component is added to a composite network, with high probability, the overall performance will not be degraded. In the study, we explore a complicated application---PM2.5 prediction---to illustrate the correctness of the proposed composite network theory. In the empirical evaluations of PM2.5 prediction, the constructed composite neural network models support the proposed theory and perform better than other machine learning models, demonstrate the advantages of the proposed framework.

A composite neural network is a rooted directed acyclic graph combining a set of pre-trained and non-instantiated neural network models. A pre-trained neural network model is well-crafted for a specific task and with instantiated weights. is generally well trained, targeted to approximate a specific function. Despite a general belief that a composite neural network may perform better than a single component, the overall performance characteristics are not clear. In this work, we prove that there exist parameters such that a composite neural network performs better than any of its pre-trained components with a high probability bound.