Rule extraction from neural network trained using deep belief network and back propagation

Chakraborty, Manomita; Biswas, Saroj Kumar; Purkayastha, Biswajit

doi:10.1007/s10115-020-01473-0

Cited by 17 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 2015 ) Global interpretability (technical) Global interpretability is provided when interpretability analysis is performed to explain the system behavior for a set of inputs corresponding to an entire class or multiple classes Post-hoc interpretability methods may provide global interpretability, such as distillation techniques Frosst and Hinton ( 2017 ) and the extraction of rule lists (Chakraborty et al. ( 2020 ) Explainability (global) Explainable AI, also denoted as XAI, defines the branch of AI research that focuses on generating explanations for complex AI systems The six families of post-hoc interpretability methods known as feature attribution, feature visualization, concept attribution, surrogate, case-based and textual explanations are addressed as explainable AI. Transparency (global) Transparency is used in AI to characterize those systems for which the role of internal components, paradigms and overall behaviour is known and can be simulated The family of linear regression models and decision trees in low dimension are transparent and can be simulated Brackets specify the domain in which each definition applies.…”

Section: Resultsmentioning

confidence: 99%

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

et al. 2022

View full text Add to dashboard Cite

Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are “weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI.

show abstract

Section: Resultsmentioning

confidence: 99%

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The table shows that the average testing accuracies of the NNEs are higher than the average testing accuracies of FFNNs in all the datasets. [7], and Eclectic Rule Extraction from Neural Network with Multi-Hidden Layer (ERENN_MHL) [32] algorithms.…”

Section: Resultsmentioning

confidence: 99%

Rule extraction using ensemble of neural network ensembles

Chakraborty¹,

Biswas²,

Purkayastha³

2022

Cognitive Systems Research

View full text Add to dashboard Cite

“…The table shows that the average testing accuracies of the NNEs are higher than the average testing accuracies of FFNNs in all the datasets. Layer (ERENN_MHL) [32] algorithms.…”

Section: Resultsmentioning

confidence: 99%

Explainable Neural Network Ensembles

Chakraborty¹,

Biswas²,

Purkayastha³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural networks are known for providing impressive classification performance, and the ensemble learning technique is further acting as a catalyst to enhance this performance by integrating multiple networks. But like neural networks, neural network ensembles are also considered as a black-box because they cannot explain their decision making process. So, despite having high classification performance, neural networks and their ensembles are not suited for some applications which require explainable decisions. However, the rule extraction technique can overcome this drawback by representing the knowledge learned by a neural network in the guise of interpretable decision rules. A rule extraction algorithm provides neural networks with the power to justify their classification responses through explainable classification rules. Several rule extraction algorithms exist to extract classification rules from neural networks, but only a few of them generates rules using neural network ensembles. So this paper proposes an algorithm named Rule Extraction using Ensemble of Neural Network Ensembles (RE-E-NNES) to demonstrate the high performance of neural network ensembles through rule extraction. RE-E-NNES extracts classification rules by ensembling several neural network ensembles. Results show the efficacy of the proposed RE-E-NNES algorithm compared to different existing rule extraction algorithms.

show abstract

Rule extraction from neural network trained using deep belief network and back propagation

Cited by 17 publications

References 26 publications

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

Rule extraction using ensemble of neural network ensembles

Explainable Neural Network Ensembles

Contact Info

Product

Resources

About