A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered…
New method evaluates visual explanations of deep models using adversarial perturbations.
New method to evaluate visual explanations from neural networks.
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional …
In this work, we develop a technique to produce counterfactual visual explanations. Given a 'query' image for which a vision system predicts class , a counterfactual visual explanation identifies how could change such that the system would output a different specified class . To do this, we select a 'dis…
DECE visualizes machine learning decisions with counterfactual explanations.
Method generates visual explanations for similarity models without classification.
We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual chec…
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize…
Paper presents a Rashomon Quartet to show different model explanations.
Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to…
Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary cl…
With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier's decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature val…
Local explanation methods, also known as attribution methods, attribute a deep network's prediction to its input (cf. Baehrens et al. (2010)). We respond to the claim from Adebayo et al. (2018) that local explanation methods lack sensitivity, i.e., DNNs with randomly-initialized weights produce explanations that are bo…
The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning problem. The applications appeal is significant, but this appeal is increasingly cha…
Gradient-based methods improve understanding of deep learning survival models.
We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we provide a globally interpretable model that is as accurate as other neural networks. O…
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a …
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. …
Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent th…
Issues regarding explainable AI involve four components: users, laws & regulations, explanations and algorithms. Together these components provide a context in which explanation methods can be evaluated regarding their adequacy. The goal of this chapter is to bridge the gap between expert users and lay users. Different…
Paper bridges generative models and explainability.
The initial analysis of any large data set can be divided into two phases: (1) the identification of common trends or patterns and (2) the identification of anomalies or outliers that deviate from those trends. We focus on the goal of detecting observations with novel content, which can alert us to artifacts in the dat…
We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure while maintaining comparable prediction performance. The structure representation…
Extends local attributions to Bayesian Neural Networks for improved explanations.
We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image, our method produces a compact support in the image domain that corresponds to a (high-resolution) feature that contributes to the given exp…
Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of…
Explaining the output of a complicated machine learning model like a deep neural network (DNN) is a central challenge in machine learning. Several proposed local explanation methods address this issue by identifying what dimensions of a single input are most responsible for a DNN's output. The goal of this work is to a…
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties are crucial. To address this issue we propose a Bayesian framework th…
Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system's inner-workings. This paper proposes a neu…
Describes explaining neurons in deep representations using compositional logical concepts.
The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-additivity and contex…
StylEx trains a GAN to explain classifier decisions in StyleSpace.
Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of the class score function with respect to the input image. This gradient can be …
Archipelago provides interpretable explanations of feature interactions in machine learning models.
OptiLIME improves LIME explanations by balancing stability and adherence.
Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explaina…
Study proposes a novel local explanation method for deep learning classifiers in process mining.
Interpretability is a key factor in the design of automatic classifiers for medical diagnosis. Deep learning models have been proven to be a very effective classification algorithm when trained in a supervised way with enough data. The main concern is the difficulty of inferring rationale interpretations from them. Dif…
GADGET framework decomposes global feature effects using recursive partitioning.
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initia…
We ask whether the neural network interpretation methods can be fooled via adversarial model manipulation, which is defined as a model fine-tuning step that aims to radically alter the explanations without hurting the accuracy of the original models, e.g., VGG19, ResNet50, and DenseNet121. By incorporating the interpre…
Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach to increase our understanding of these models. In this paper we present an appr…
Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleti…
A new method simplifies feature explanation for complex models.
Study compares DL models for medical image segmentation, finds synergistic ensemble strategies improve performance.