P2ExNet: Patch-Based Prototype Explanation Network

Mercier, Dominique; Dengel, Andreas; Ahmed, Sheraz

doi:10.1007/978-3-030-63836-8_27

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novelty compared to previous work is using a constrained similarity measure, rather than the commonly used L2 distance, to compare the encodings with the learned prototypes. Mercier et al [102] train an autoencoder to generate embeddings for an input time series in their approach P2ExNet. The embedding representation is then fed into a prototype network in which multiple subsequence prototypes of the whole input time series, instead of a single prototype, are used.…”

Section: Definition 8 (Multivariate Shapelet) Given a Tsc Datasetmentioning

confidence: 99%

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

et al. 2022

View full text Add to dashboard Cite

Time series data is increasingly used in a wide range of fields, and it is often relied on in crucial applications and high-stakes decision-making. For instance, sensors generate time series data to recognize different types of anomalies through automatic decision-making systems. Typically, these systems are realized with machine learning models that achieve top-tier performance on time series classification tasks. Unfortunately, the logic behind their prediction is opaque and hard to understand from a human standpoint. Recently, we observed a consistent increase in the development of explanation methods for time series classification justifying the need to structure and review the field. In this work, we (a) present the first extensive literature review on Explainable AI (XAI) for time series classification, (b) categorize the research field through a taxonomy subdividing the methods into time points-based, subsequences-based and instance-based, and (c) identify open research directions research directions regarding the type of explanations and the evaluation of explanations and interpretability.

show abstract

Section: Definition 8 (Multivariate Shapelet) Given a Tsc Datasetmentioning

confidence: 99%

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Therefore we need another computational inexpensive simulation scheme (that is, from our motivation, a non Finite-Element-based method) for the generation of a sufficiently large training set for the DNN in order to obtain a predictive surrogate model. For an overview of general requirements to achieve surrogate models within a data based approach using large training sets in a deep learning framework see [6], and [7][8][9][10] as examples of applications of trained DNNs as surrogate models in mechanics. Furthermore, e.g.…”

Section: Introductionmentioning

confidence: 99%

A surrogate model for the prediction of permeabilities and flow through porous media

Niekamp

Niemann

Schröder

2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

In this contribution we present an approach to generate a data driven surrogate model for the prediction of permeabilities and flow through two dimensional random micro-heterogeneous materials. The laminar flow is well described by Darcy's law. In order to achieve an efficient computational tool for the generation of the database (up to 10 3 realizations), needed for the training of the neural networks, we apply a stochastic model based on the Brownian motion. The stationary state of the resulting stochastic model solves the Darcy equation and can be iteratively solved by a Monte Carlo approach applied to a particle simulation. Improved numerical efficiency can be yield by usage of the related transition matrix.

show abstract

PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

Mercier

Dengel

Ahmed

2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neural models are only exploited in a few areas. Traditional methods are still used very often compared to deep neural models. These methods get preferred in safety-critical, financial, or medical fields because of their interpretable results. However, their performance and scale-ability are limited, and finding suitable explanations for time-series classification tasks is challenging due to the concepts hidden in the numerical time-series data. Visualizing complete time-series results in a cognitive overload concerning our perception and leads to confusion. Therefore, we believe that patch-wise processing of the data results in a more interpretable representation. We propose a novel hybrid approach that utilizes deep neural networks and traditional machine learning algorithms to introduce an interpretable and scale-able time-series classification approach. Our method first performs a fine-grained classification for the patches followed by sample level classification.

show abstract

P2ExNet: Patch-Based Prototype Explanation Network

Cited by 3 publications

References 16 publications

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

A surrogate model for the prediction of permeabilities and flow through porous media

PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

Contact Info

Product

Resources

About