Counterfactuals, or modified inputs that lead to a different outcome, are an important tool for understanding the logic used by machine learning classifiers and how to change an undesirable classification. Even if a c...
详细信息
Counterfactuals, or modified inputs that lead to a different outcome, are an important tool for understanding the logic used by machine learning classifiers and how to change an undesirable classification. Even if a counterfactual changes a classifier's decision, however, it may not affect the true underlying class probabilities, i.e. the counterfactual may act like an adversarial attack and "fool" the classifier. We propose a new framework for creating modified inputs that change the true underlying probabilities in a beneficial way which we call Trustworthy Actionable Perturbations (TAP). This includes a novel verification procedure to ensure that TAP change the true class probabilities instead of acting adversarially. Our framework also includes new cost, reward, and goal definitions that are better suited to effectuating change in the real world. We present PAC-learnability results for our verification procedure and theoretically analyze our new method for measuring reward. We also develop a methodology for creating TAP and compare our results to those achieved by previous counterfactual methods. Copyright 2024 by the author(s)
Recent advances in artificial intelligence have prompted the use of machine learning methods in network security. In this paper, we address the issue of imbalanced data that is often present in network security datase...
详细信息
Convolutional neural networks are used to classify dermoscopic skin lesion images. The high accuracy of deep learning models is well documented;however, those models do not perform very well on testing (unseen data) s...
详细信息
This paper explores the utilization of a novel transformer-based architecture for end-to-end learning in predicting steering angles in self-driving scenarios while leveraging a novel robust image processing pipeline t...
详细信息
In this paper,observability is studied for periodically switched Boolean control networks(PSBCNs),which are managed with periodic switching signal and consist of some Boolean control ***,via semi-tensor product of mat...
详细信息
In this paper,observability is studied for periodically switched Boolean control networks(PSBCNs),which are managed with periodic switching signal and consist of some Boolean control ***,via semi-tensor product of matrices,PSBCNs are expressed as algebraic ***,a parallel system is constructed by combining two same PSBCNs,based on which,the observability problem of the original PSBCN can be transformed into the set reachability problem of this parallel ***,two necessary and sufficient conditions are obtained to detect reachability of parallel systems and observability of *** addition,the proposed conditions are extended to the case of state ***,a practical example and a numerical example are provided to illustrate the results.
A new predictor-corrector method (NPCM) was developed by Daftardar-Gejji and Sukale et al. (Appl Math Comput 244: 158-182, 2014) to solve fractional order differential equations. In the present article, we develop a n...
详细信息
The article deals with the analysis of the fractional COVID-19 epidemic model (FCEM) with a convex incidence rate. Keeping in view the fading memory and crossover behavior found in many biological phenomena, we study ...
详细信息
The present study aims to investigate a trend of long-term changes in drought proneness in Iran. For this purpose, we first evaluate the reliability, resilience, and vulnerability (RRV) based on the gridded data of so...
详细信息
Let R be prime ring with characteristic different from 2, C denotes the extended centroid, L a Lie ideal of R and Qr the right Martindale quotient of the ring R. Let Δ1 and Δ2 represents two generalized skew derivat...
详细信息
Graph Neural Networks (GNNs) have emerged as a widely used and effective method across various domains for learning from graph data. Despite the abundance of GNN variants, many struggle with effectively propagating me...
详细信息
暂无评论