The coming of age of interpretable and explainable machine learning models

Lisboa, Paulo J. G.; Saralajew, Sascha; Vellido, Alfredo; Fernández-Domenech, R.; Villmann, Thomas

doi:10.1016/j.neucom.2023.02.040

Cited by 57 publications

(19 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is key to enable the practical implementations of the models section. 34 We can partially compare our results with those reported by Vilamala et al and Ortega-Martorell et al, 19,21 as the same INTERPRET database was analyzed. In Vilamala et al, 19 the authors evaluated D-C-NMF on the same INTERPRET dataset for the following binary classification tasks: ME versus A2, GL versus A2, GL versus ME, A2 versus NO, ME versus NO, and GL versus NO, at both short and long echo times.…”

Section: Problem 6 (A2 Vs Agg Vs Mm): Can We Distinguish Between Grad...supporting

confidence: 63%

See 1 more Smart Citation

A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

et al. 2023

View full text Add to dashboard Cite

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow‐up. In this study, we investigated the performance of a range of variants of unsupervised matrix factorization methods of the non‐negative matrix underapproximation (NMU) family, namely, sparse NMU, global NMU, and recursive NMU, and compared them with convex non‐negative matrix factorization (C‐NMF), which has previously shown a good performance on brain tumor diagnostic support problems using MRS data. The purpose of the investigation was 2‐fold: first, to ascertain the differences among the sources extracted by these methods; and second, to compare the influence of each method in the diagnostic accuracy of the classification of brain tumors, using them as feature extractors. We discovered that, first, NMU variants found meaningful sources in terms of biological interpretability, but representing parts of the spectrum, in contrast to C‐NMF; and second, that NMU methods achieved better classification accuracy than C‐NMF for the classification tasks when one class was not meningioma.

show abstract

Section: Problem 6 (A2 Vs Agg Vs Mm): Can We Distinguish Between Grad...supporting

confidence: 63%

“…Second, because LDA results are straightforwardly interpretable, which should help the radiologist provide explanations for the diagnostic decisions made by the models. This is key to enable the practical implementations of the models section 34 …”

Section: Discussionmentioning

confidence: 99%

A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

et al. 2023

View full text Add to dashboard Cite

show abstract

“…. , C} such that a data sample x is classified according to c (x) = c w s(x) using the WTA rule [46].Unsupervised learning of the prototypes follows several schemes: The most prominent is standard k-means or its improved variants like k-means++ or neural gas [47,48,49], which use stochastic gradient descent learning (SGDL) or expectation-maximization (EM) optimization. Prototype-based classification learning is based on the famous learning vector quantization (LVQ) approaches originally suggested by Kohonen [50].…”

Section: Standard Vector Quantizationmentioning

confidence: 99%

“…Today it is based on strong mathematical foundations known as generalized LVQ (GLVQ) usually trained by SGDL [51]. NPC guaranties interpretability of vector quantizers for both unsupervised and supervised learning [46]. Further, if the squared Euclidean distance is used for training together with SGDL, prototype adaptations are by simple vector shifts in the data space.…”

Section: Standard Vector Quantizationmentioning

confidence: 99%

Quantum Artificial Intelligence: A tutorial

Martín-Guerrero,

Lamata,

Villmann

2023

ESANN 2023 Proceesdings

View full text Add to dashboard Cite

Artificial Intelligence (AI), a discipline with decades of history, is living its golden era due to striking developments that solve problems that were unthinkable just a few years ago, like generative models of text, images and video. The broad range of AI applications has also arrived to Physics, providing solutions to bottleneck situations, e.g., numerical methods that could not solve certain problems or took an extremely long time, optimization of quantum experimentation, or qubit control. Besides, Quantum Computing has become extremely popular for speeding up AI calculations, especially in the case of data-driven AI, i.e., Machine Learning (ML). The term Quantum ML is already known and deals with learning in quantum computers or quantum annealers, quantum versions of classical ML models and different learning approaches for quantum measurement and control. Quantum AI (QAI) tries to take a step forward in order to come up with disruptive concepts, such as, human-quantum-computer interfaces, sentiment analysis in quantum computers or explainability of quantum computing calculations, to name a few. This special session includes five high-quality papers on relevant topics, like quantum reinforcement learning, parallelization of quantum calculations, quantum feature selection and quantum vector quantization, thus capturing the richness and variability of approaches within QAI.

show abstract

“…Further, the popularity of vector quantization methods arises from their intuitive problem understanding and the resulting interpretable model behavior [ 8 , 10 , 18 , 19 ], which frequently is demanded for acceptance of machine learning methods in technical or biomedical applications [ 20 , 21 , 22 ]. Although these methods are of only lightweight complexity compared to deep networks, frequently sufficient performance is achieved.…”

Section: Introductionmentioning

confidence: 99%

Quantum Computing Approaches for Vector Quantization—Current Perspectives and Developments

Engelsberger

Villmann

2023

Entropy

View full text Add to dashboard Cite

In the field of machine learning, vector quantization is a category of low-complexity approaches that are nonetheless powerful for data representation and clustering or classification tasks. Vector quantization is based on the idea of representing a data or a class distribution using a small set of prototypes, and hence, it belongs to interpretable models in machine learning. Further, the low complexity of vector quantizers makes them interesting for the application of quantum concepts for their implementation. This is especially true for current and upcoming generations of quantum devices, which only allow the execution of simple and restricted algorithms. Motivated by different adaptation and optimization paradigms for vector quantizers, we provide an overview of respective existing quantum algorithms and routines to realize vector quantization concepts, maybe only partially, on quantum devices. Thus, the reader can infer the current state-of-the-art when considering quantum computing approaches for vector quantization.

show abstract

The coming of age of interpretable and explainable machine learning models

Cited by 57 publications

References 95 publications

A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

Quantum Artificial Intelligence: A tutorial

Quantum Computing Approaches for Vector Quantization—Current Perspectives and Developments

Contact Info

Product

Resources

About