Detecting Information Relays in Deep Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
EEGElectroencephalogram (EEG)ERPSimilar Papers 제목 키워드 기반
RelaySum for Decentralized Deep Learning on Heterogeneous Data
In decentralized machine learning, workers compute model updates on their local data. Because the workers only communicate with few neighbors without central coordination, these updates propagate progressively over the n…
Deep LearningA Machine Learning-Based Method for Identifying Critical Distance Relays for Transient Stability Studies
Modeling protective relays is crucial for performing accurate stability studies as they play a critical role in defining the dynamic responses of power systems during disturbances. Nevertheless, due to the current limita…
LOS Coverage Area in Vehicular Networks with Cox distributed Roadside Units and Relays
We develop an analytical framework to examine the line-of-sight (LOS) coverage area in vehicular networks with roadside units (RSU) and vehicle relays. In practical deployment scenarios, RSUs and vehicle relays are spati…
Point ProcessesAverage AoI Minimization for Energy Harvesting Relay-aided Status Update Network Using Deep Reinforcement Learning
A dual-hop status update system aided by energy harvesting (EH) relays with finite data and energy buffers is studied in this work. To achieve timely status updates, the best relays should be selected to minimize the ave…
Deep Reinforcement LearningAge of Information in Multi-Relay Networks with Maximum Age Scheduling
We propose and evaluate age of information (AoI)-aware multiple access mechanisms for the Internet of Things (IoT) in multi-relay two-hop networks. The network considered comprises end devices (EDs) communicating with a …
Scheduling