Explainable classification by learning human-readable sentences in feature subsets

Krishnamurthy, P.; Sarmadi, Alireza; Khorrami, Farshad

doi:10.1016/j.ins.2021.02.031

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…interpretability and descriptive accuracy. Krishnamurthy et al (2021) offered a socalled sentences in feature subsets (SiFS) in order to implement a genetic-based algorithm to choose a subset of distinctive features that affect the prediction process. The obtained features were then converted into compact decision rules and held Boolean logic sentences that humans can easily comprehend.…”

Section: Feature Relevancementioning

confidence: 99%

Explainable artificial intelligence: a comprehensive review

et al. 2021

View full text Add to dashboard Cite

Thanks to the exponential growth in computing power and vast amounts of data, artificial intelligence (AI) has witnessed remarkable developments in recent years, enabling it to be ubiquitously adopted in our daily lives. Even though AI-powered systems have brought competitive advantages, the black-box nature makes them lack transparency and prevents them from explaining their decisions. This issue has motivated the introduction of explainable artificial intelligence (XAI), which promotes AI algorithms that can show their internal process and explain how they made decisions. The number of XAI research has increased significantly in recent years, but there lacks a unified and comprehensive review of the latest XAI progress. This review aims to bridge the gap by discovering the critical perspectives of the rapidly growing body of research associated with XAI. After offering the readers a solid XAI background, we analyze and review various XAI methods, which are grouped into (i) pre-modeling explainability, (ii) interpretable model, and (iii) post-modeling explainability. We also pay attention to the current methods that dedicate to interpret and analyze deep learning methods. In addition, we systematically discuss various XAI challenges, such as the trade-off between the performance and the explainability, evaluation methods, security, and policy. Finally, we show the standard approaches that are leveraged to deal with the mentioned challenges.

show abstract

Section: Feature Relevancementioning

confidence: 99%

Explainable artificial intelligence: a comprehensive review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For each label, based on the subset of relevant features identified as discussed above, a set of humanreadable sentences (with each sentence comprised of an AND-combination of a set of linear inequality based conditions, each of which is called a "word" in the sentence) is learned using a combination of stochastic gradient descent and genetic algorithms (Krishnamurthy et al [2021]). This component of ppMTL is enabled only when ppMTL is run in "full" mode and is not enabled in the "light-weight" mode in which the feature down-selection discussed above provides the required identification of the subset of features.…”

Section: Learning Of Human-readable Sentencesmentioning

confidence: 99%

ESAFE: Enterprise Security and Forensics at Scale

McShea¹,

Wright²,

Lam³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffused and may be located across network and endpoint devices.Further, cyberrelevant data routinely exceeds total available storage, bandwidth, and analysis capability, often by several orders of magnitude. Real-time detection of threats within or across very large enterprise networks is not simply an issue of scale, but also a challenge due to the variable nature of malicious activities and their presentations. The system seeks to develop a hierarchy of cyber reasoning layers to detect malicious behavior, characterize novel attack vectors and present an analyst with a contextualized human-readable output from a series of machine learning models. We developed machine learning algorithms for scalable throughput and improved recall for our Multi-Resolution Joint Optimization for Enterprise Security and Forensics (ESAFE) solution.

show abstract

Fuzzy similarity phrases for interpretable data classification

Vasilakakis

Iakovidis

2023

Information Sciences

View full text Add to dashboard Cite

Explainable classification by learning human-readable sentences in feature subsets

Cited by 5 publications

References 28 publications

Explainable artificial intelligence: a comprehensive review

Explainable artificial intelligence: a comprehensive review

ESAFE: Enterprise Security and Forensics at Scale

Fuzzy similarity phrases for interpretable data classification

Contact Info

Product

Resources

About