Controlling explanatory heatmap resolution and semantics via decomposition depth

Bach, Sebastian; Binder, Alexander; Müller, Klaus‐Robert; Samek, Wojciech

doi:10.1109/icip.2016.7532763

Cited by 17 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rule-based learner: [82,83,147,148,251,252,253,254,255,256] Decision Tree: [21,56,79,81,97,135,257,258,259] Others: [80] Feature relevance explanation Importance/Contribution: [60,61,110,260,261] Sensitivity / Saliency: [260] [262] Local explanation Decision Tree / Sensitivity: [233] [263] Explanation by Example Activation clusters: [264,144] Text explanation Caption generation: [111] [150] Visual explanation Saliency / Weights: [265] Architecture modification Others: [264] [266] [267] Convolutional Neural Networks Explanation by simplification Decision Tree: [78] Feature relevance explanation Activations: [72,268] [46] Feature Extraction: [72,268] Visual explanation Filter / Activation: [63,136,137,...…”

Section: Explanation By Simplificationmentioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

show abstract

Section: Explanation By Simplificationmentioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The relevance decompositions for the SVM predictor layer are computed using the "simple" ( = 0) rule (cf. [34] and [140] for further technical details). Since the fine-tuned DNN model structure is composed of a repeating sequence of convolutional or fully connected layers interleaved with pooling and ReLU activation layers, we uniformly apply the αβ-rule with α = 2, β = −1 throughout the network, which complements the ReLU-activated inputs fed into hidden layers especially well for explanation.…”

Section: E3 Comparing Fisher Vector and Deep Network Prediction Stramentioning

confidence: 99%

Unmasking Clever Hans predictors and assessing what machines really learn

et al. 2019

Self Cite

View full text Add to dashboard Cite

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly intelligent behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner.

show abstract

“…For happiness and disgust, images from the Actorstudy dataset were used. The classification results for the subimages in Figure 5 showing emotion (from (1) to (4)) and the subimage (5) showing pain are correct. A misclassification can be seen in subfigure (6).…”

Section: Resultsmentioning

confidence: 90%

“…Using the preset approach, the relevance scores for all neurons of the lowest (first) layer are uniformly distributed to the input neuron instead of using the α and β values [13]. To control the resolution of the heatmaps generated by LRP, Bach et al [5] describes an approach for 'mapping influence cut-off point'. This point describes the moment from which the forward mapping function of the classifier no longer influences relevance propagation, since only the receptive field of the classifier is relevant.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep-learned faces of pain and emotions: Elucidating the differences of facial expressions with the help of explainable AI methods

Weitz

Hassan

Schmid

et al. 2019

Tm - Technisches Messen

View full text Add to dashboard Cite

Deep neural networks are successfully used for object and face recognition in images and videos. In order to be able to apply such networks in practice, for example in hospitals as a pain recognition tool, the current procedures are only suitable to a limited extent. The advantage of deep neural methods is that they can learn complex non-linear relationships between raw data and target classes without limiting themselves to a set of hand-crafted features provided by humans. However, the disadvantage is that due to the complexity of these networks, it is not possible to interpret the knowledge that is stored inside the network. It is a black-box learning procedure. Explainable Artificial Intelligence (AI) approaches mitigate this problem by extracting explanations for decisions and representing them in a human-interpretable form. The aim of this paper is to investigate the explainable AI methods Layer-wise Relevance Propagation (LRP) and Local Interpretable Model-agnostic Explanations (LIME). These approaches are applied to explain how a deep neural network distinguishes facial expressions of pain from facial expressions of emotions such as happiness and disgust.

show abstract

Controlling explanatory heatmap resolution and semantics via decomposition depth

Cited by 17 publications

References 15 publications

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Unmasking Clever Hans predictors and assessing what machines really learn

Deep-learned faces of pain and emotions: Elucidating the differences of facial expressions with the help of explainable AI methods

Contact Info

Product

Resources

About