相关论文: When Explanations Lie: Why Many Modified BP Attrib…

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…

Local Binary Pattern (LBP) is a traditional descriptor for texture analysis that gained attention in the last decade. Being robust to several properties such as invariance to illumination translation and scaling, LBPs achieved…

Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the credit assignment problem in artificial neural networks.…

Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological implausibility, hinder the concurrent updating of layers and do…

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved. In this chapter, we explore…

Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are "class-dependent" methods in that they generate a feature…

There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of…

Explainable AI (XAI) methods help identify which image regions influence a model's prediction, but often face a trade-off between detail and interpretability. Layer-wise Relevance Propagation (LRP) offers a model-aware alternative. However,…

Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network.…

A recent study by De et al. (2022) has reported that large-scale representation learning through pre-training on a public dataset significantly enhances differentially private (DP) learning in downstream tasks, despite the high…

Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation. But this allows gradients to be distributed equally among all paths. The proposed approach guides the…

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge representations hidden in middle conv-layers of the CNN.…

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

Transformer architectures are complex and their use in NLP, while it has engendered many successes, makes their interpretability or explainability challenging. Recent debates have shown that attention maps and attribution methods are…

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both…

As the use of deep neural networks continues to grow, understanding their behaviour has become more crucial than ever. Post-hoc explainability methods are a potential solution, but their reliability is being called into question. Our…

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing…

Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes…