| Title | Locality Guided Neural Networks for Explainable Artificial Intelligence |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Tan, R., Khan, N., Guan, L. |
| Conference Name | 2020 International Joint Conference on Neural Networks (IJCNN) |
| Date Published | jul |
| Keywords | AI methods, CIFAR100 dataset, CNN, convolutional neural nets, convolutional neural networks, current deep network architectures, deep learning architecture, explainable artificial intelligence, learning (artificial intelligence), locality guided neural network, machine learning, Network topology, Neurons, pubcrawl, Resiliency, Scalability, self-organising feature maps, Self-organizing feature maps, Self-Organizing Map, Semantics, Topology, training networks, visualization, xai |
| Abstract | In current deep network architectures, deeper layers in networks tend to contain hundreds of independent neurons which makes it hard for humans to understand how they interact with each other. By organizing the neurons by correlation, humans can observe how clusters of neighbouring neurons interact with each other. In this paper, we propose a novel algorithm for back propagation, called Locality Guided Neural Network (LGNN) for training networks that preserves locality between neighbouring neurons within each layer of a deep network. Heavily motivated by Self-Organizing Map (SOM), the goal is to enforce a local topology on each layer of a deep network such that neighbouring neurons are highly correlated with each other. This method contributes to the domain of Explainable Artificial Intelligence (XAI), which aims to alleviate the black-box nature of current AI methods and make them understandable by humans. Our method aims to achieve XAI in deep learning without changing the structure of current models nor requiring any post processing. This paper focuses on Convolutional Neural Networks (CNNs), but can theoretically be applied to any type of deep learning architecture. In our experiments, we train various VGG and Wide ResNet (WRN) networks for image classification on CIFAR100. In depth analyses presenting both qualitative and quantitative results demonstrate that our method is capable of enforcing a topology on each layer while achieving a small increase in classification accuracy. |
| DOI | 10.1109/IJCNN48605.2020.9207559 |
| Citation Key | tan_locality_2020 |
Locality Guided Neural Networks for Explainable Artificial Intelligence