arXiv research

The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.

A new method detects interactions in machine learning models.

GRANITE unifies feature-based explanation methods to reduce disagreement.

The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single …

Functional connections in the brain are frequently represented by weighted networks, with nodes representing locations in the brain, and edges representing the strength of connectivity between these locations. One challenge in analyzing such data is that inference at the individual edge level is not particularly biolog…

Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision-making of the agents. In contrast to previous a-posteriori methods for visualizing DeepRL policies, in this work, we …

sBayFDNN bridges deep learning and functional data analysis for complex, structured data.

DAMI uses interpretable regions to select informative samples for deep learning models.

Develops a category-theoretic approach to interpret conformal prediction.

3D CNNs interpret brain MRI differences between men and women.

Proposes a method to quantify the reliability of salient regions in deep learning models using p-values.

Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain. In this work, we focus on weakly supervised localization (WSL) where a model is trained to classify an image and localize regi…

Region-specific linear models are widely used in practical applications because of their non-linear but highly interpretable model representations. One of the key challenges in their use is non-convexity in simultaneous optimization of regions and region-specific models. This paper proposes novel convex region-specific…

SPLICE method disentangles shared and private latent variables from multi-view data.

We use PDPs with confidence bands to explain HPO results.

This work aims to test the Verdoorn Law, with the alternative specifications of (1)Kaldor (1966), for five regions (NUTS II) Portuguese from 1986 to 1994 and for the 28 NUTS III Portuguese in the period 1995 to 1999. Will, therefore, to analyze the existence of increasing returns to scale that characterize the phenomen…

Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…

Art historians and archaeologists have long grappled with the regional classification of ancient Near Eastern ivory carvings. Based on the visual similarity of sculptures, individuals within these fields have proposed object assemblages linked to hypothesized regional production centers. Using quantitative rather than …

JANET improves time series prediction with adaptive uncertainty regions.

Scalable method for regionalizing and extracting temporal patterns from time series data.

IRDs provide local, model-agnostic explanations using hyperboxes.

RAMs improve GAMs' accuracy by fitting components to subregions of feature space.

Bayesian model averaging under predictor redundancy

Dockless bike sharing systems need effective bike flow prediction models.

Unified approach to verify NN properties using ReLU's unique polytope structure.

The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model's behavior. LIME develops multiple interpretable models, each approximat…

In this paper, we consider domino tilings of regions of the form $\mathcal{D} \times [0,n]$, where $\mathcal{D}$ is a simply connected planar region and $n \in \mathbb{N}$. It turns out that, in nontrivial examples, the set of such tilings is not connected by flips, i.e., the local move performed by removing two adjace…

In this thesis, we consider domino tilings of three-dimensional regions, especially those of the form $\mathcal{D} \times [0,N]$. In particular, we investigate the connected components of the space of tilings of such regions by flips, the local move performed by removing two adjacent dominoes and placing them back in t…

The paper forecasts joint electricity demand across 14 British regions using additive models.

Study evaluates deep learning models for solar flare prediction with interpretability analysis.

I studied the convergence of regional house prices to national prices in USA by analyzing time-series of house price indices of 9 Census Divisions. I found the evidence of the convergence in some parts of the country using asymmetric unit root tests. The fact that the evidence of the convergence is not present in large…

si4onnx enables selective inference on deep learning models.

PR-GNN identifies salient brain regions for ASD biomarkers.

A leveraged exchange traded fund (LETF) is an exchange traded fund that uses financial derivatives to amplify the price changes of a basket of goods. In this paper, we consider the robust hedging of European options on a LETF, finding model-free bounds on the price of these options. To obtain an upper bound, we establi…

Pantypes improve prototypical models by capturing diverse input distributions.

Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map gene…

A geometric interpretation is given for certain elliptic-hyperbolic systems in the plane. Among several examples, one which reduces in the elliptic region to the equations for harmonic 1-forms on the projective disc is studied in detail. A boundary-value problem for this example is formulated and is shown to possess we…

Interactive visualization helps understand complex machine learning models.

Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions. However, the state of the art, based on total variation or graph-net, is computationally costly. Here we introduce sparsity in the local neig…

Mapper-GIN simplifies 3D point cloud classification with lightweight structure.

Proposes a novel approach for cluster-aware matching using Laplacian Optimal Transport.

We consider the interpretation in classical geometry of conformal field theories constructed from orbifolds with discrete torsion. In examples we can analyze, these spacetimes contain ``stringy regions'' that from a classical point of view are singularities that are to be neither resolved nor blown up. Some of these mo…

In this work, we develop a technique to produce counterfactual visual explanations. Given a 'query' image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c'$. To do this, we select a 'dis…

New method detects and locates changes in spatio-temporal point processes.

A new method selects regions of interest in GC-MS data without prior target selection.

FiberNet integrates geometry into machine learning for clearer classification.

Framework for confidence estimation in deep CT reconstructions.

Method extracts time-localized clusters to explain deep learning models in ECG analysis.