Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on layer-wise Relevance Propagation (LRP), a technique used in explainable artificial intelligence (XAI) to attribute neural network outputs to input features through backpropagated relevance scores. Existing LRP methods often struggle with precision in evaluating individual neuron contributions. To overcome this limitation, we present a novel approach that improves the parsing of selected neurons during LRP backward propagation, using the Visual Geometry Group 16 (VGG16) architecture as a case study. Our method creates neural network graphs to highlight critical paths and visualizes these paths with heatmaps, optimizing neuron selection through accuracy metrics like Mean Squared Error (MSE) and Symmetric Mean Absolute Percentage Error (SMAPE). Additionally, we utilize a deconvolutional visualization technique to reconstruct feature maps, offering a comprehensive view of the network's inner workings. Extensive experiments demonstrate that our approach enhances interpretability and supports the development of more transparent artificial intelligence (AI) systems for computer vision applications. This advancement has the potential to improve the trustworthiness of AI models in real-world machine vision applications, thereby increasing their reliability and effectiveness.
In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks.
Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not look inside the model, inhibiting human trust in the model and explanations. Motivated by the ability of neurons to detect high-level semantic concepts in vision models, we perform a novel analysis on the behaviour of individual GNN neurons to answer questions about GNN interpretability, and propose new metrics for evaluating the interpretability of GNN neuron…
The internal states of most deep neural networks are difficult to interpret, which makes diagnosis and debugging during training challenging. Activation maximization methods are widely used, but lead to multiple optima and are hard to interpret (appear noise-like) for complex neurons. Image-based methods use maximally-activating image regions which are easier to interpret, but do not provide pixel-level insight into why the neuron responds to them. In this work we introduce an MCMC method: Langevin Dynamics Activation Maximization (LDAM), which is designed for diagnostic visualization. LDAM pr…
NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions
Institute for AI Innovation and Societal Impact (AI4LIFE), Hanoi University of Science and Technology（河内国家大学下属科学与技术大学人工智能创新与社会影响研究所）；University of Florida（佛罗里达大学）；VinUniversity（VinUniversity（越南 VinUniversity 大学））
Auburn University（奥本大学）；Uber AI Labs（优步人工智能实验室）；University of Wyoming（怀俄明大学）
A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as Activation Maximization (AM) or Feature Visualization via Optimization. In this chapter, we (1) review existing AM techniques in the literature; (2) discuss a probabilistic interpretation for AM; and (3) review the applications of AM in debugging and …
The Chinese University of Hong Kong（香港中文大学）；Southeast University（东南大学）；Cornell University（康奈尔大学）
Throughout history, the development of artificial intelligence, particularly artificial neural networks, has been open to and constantly inspired by the increasingly deepened understanding of the brain, such as the inspiration of neocognitron, which is the pioneering work of convolutional neural networks. Per the motives of the emerging field: NeuroAI, a great amount of neuroscience knowledge can help catalyze the next generation of AI by endowing a network with more powerful capabilities. As we know, the human brain has numerous morphologically and functionally different neurons, while artifi…
University of Wyoming（怀俄明大学）；Cornell University（康奈尔大学）
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. To do so, researchers have created Deep Visualization techniques including activation maximization, which synthetically generates inputs (e.g. images) that maximally activate each neuron. A limitation of current techniques is that they assume each neuron detects only one type of feature, but we know that neurons can be multifaceted, in that they fire in response to many different types of features: for example, a grocery store class neuron must activate either for rows of p…
Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to facilitate visualization). Neurons in the output space are connected with each other but this structure remains fixed throughout training and learning is achieved through the updating of neuron reference vectors in feature space. Despite the fact that growing variants of SOM overcome the fixed structure limitation they increase computational cost and also do …
We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network. By accounting for interactions across neurons, Neuron Shapley is more effective in identifying important filters compared to common approaches based on activation patterns. Interestingly, removing just 30 filters with the highest Shapley scores effectively destroys the prediction accuracy of Inception-v3 on ImageNet. Visualization of these few critical filters provides insights into how the network functions. Neuron Shapley is a flexible framework…
Over past several years, deep learning has achieved huge successes in various applications. However, such a data-driven approach is often criticized for lack of interpretability. Recently, we proposed artificial quadratic neural networks consisting of second-order neurons in potentially many layers. In each second-order neuron, a quadratic function is used in the place of the inner product in a traditional neuron, and then undergoes a nonlinear activation. With a single second-order neuron, any fuzzy logic operation, such as XOR, can be implemented. In this sense, any deep network constructed …
Yale Department of Computer Science（耶鲁大学计算机科学系）；Yale Department of Genetics（耶鲁大学遗传学系）；Université de Montréal, Dept. of Math. & Stat.（蒙特利尔大学数学与统计系）；Mila（米拉研究院）
While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on the primary task. Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer. This penalty encourages activations to be smooth either on a predetermined gra…
We introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions. To simulate properties of biological systems we add the costs penalizing long connections and the proximity of neurons in a two-dimensional space. Our experiments show that in the case where the network performs two different tasks, the neurons naturally split into clusters, where each cluster is responsible for processing a different task. This behavior not only corresponds to the biological systems, but also allows for further insight into interpretability or c…
