Related papers: Tackling Shortcut Learning in Deep Neural Networks…

This paper proposes a new paradigm for learning a set of independent logical rules in disjunctive normal form as an interpretable model for classification. We consider the problem of learning an interpretable decision rule set as training a…

This work introduces a novel interpretable machine learning method called Mixture of Decision Trees (MoDT). It constitutes a special case of the Mixture of Experts ensemble architecture, which utilizes a linear model as gating function and…

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

The standard approach to providing interpretability to deep convolutional neural networks (CNNs) consists of visualizing either their feature maps, or the image regions that contribute the most to the prediction. In this paper, we introduce…

The sample selection approach is very popular in learning with noisy labels. As deep networks learn pattern first, prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean…

Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning…

The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critical domains such as healthcare, finance and autonomous…

Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This…

Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. While a number of previous work has tackled the identification of shortcut reasoning, there are still two major limitations: (i) a…

To meet the growing demand for smarter, faster, and more efficient embodied AI solutions, we introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied autonomous systems.…

The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black box" models, such as deep neural networks and ensemble methods. These models exhibit exceptional predictive performance, making them…

Visual explanation is an approach for visualizing the grounds of judgment by deep learning, and it is possible to visually interpret the grounds of a judgment for a certain input by visualizing an attention map. As for deep-learning models…

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly…

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

One obstacle that so far prevents the introduction of machine learning models primarily in critical areas is the lack of explainability. In this work, a practicable approach of gaining explainability of deep artificial neural networks (NN)…

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world…

Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and…

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity…

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

To plan safe maneuvers and act with foresight, autonomous vehicles must be capable of accurately predicting the uncertain future. In the context of autonomous driving, deep neural networks have been successfully applied to learning…