paper-with-me

Papers

Explaining and Interpreting LSTMs

2019-09-25 · Leila Arras, Jose A. Arjona-Medina, Michael Widrich, Grégoire Montavon, Michael Gillhofer, Klaus-Robert Müller, Sepp Hochreiter, Wojciech Samek

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the variety of tasks to be solved. In this chapter, we explore how to adapt the Layer-wise Relevance Propagation (LRP) technique used for explaining the predictions of feed-forward networks to the LSTM architecture used for sequential data modeling and forecasting. The special accumulators and gated interactions present in the LSTM require both a new propagation scheme and an extension of the underlying theoretical framework to deliver faithful explanations.

📄 PDF Abstract BibTeX arXiv:1909.12114

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

NeuralHydrology -- Interpreting LSTMs in Hydrology

2019-03-19 · Frederik Kratzert, Mathew Herrnegger, Daniel Klotz, Sepp Hochreiter 외

Despite the huge success of Long Short-Term Memory networks, their applications in environmental sciences are scarce. We argue that one reason is the difficulty to interpret the internals of trained networks. In this stu…

Methods for Interpreting and Understanding Deep Neural Networks

2017-06-24 · Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed technique…

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

2022-04-04 · Christoph Wehner, Francis Powlesland, Bashar Altakrouri, Ute Schmid

Artificial Intelligence and Digital Twins play an integral role in driving innovation in the domain of intelligent driving. Long short-term memory (LSTM) is a leading driver in the field of lane change prediction for man…

Decision Making

Hard Masking for Explaining Graph Neural Networks

2021-01-01 · Thorben Funke, Megha Khosla, Avishek Anand

Graph Neural Networks (GNNs) are a flexible and powerful family of models that build nodes' representations on irregular graph-structured data. This paper focuses on explaining or interpreting the rationale underlying a …

Data CompressionDecision MakingNode ClassificationPrediction

Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models

2017-08-28 · Wojciech Samek, Thomas Wiegand, Klaus-Robert Müller

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impress…

Deep LearningExplainable artificial intelligenceGeneral Classificationimage-classification+2