Interactive slice visualization for exploring machine learning models
- URL: http://arxiv.org/abs/2101.06986v1
- Date: Mon, 18 Jan 2021 10:47:53 GMT
- Title: Interactive slice visualization for exploring machine learning models
- Authors: Catherine B. Hurley, Mark O'Connell, Katarina Domijan
- Abstract summary: We use interactive visualization of slices of predictor space to address the interpretability deficit.
In effect, we open up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Machine learning models fit complex algorithms to arbitrarily large datasets.
These algorithms are well-known to be high on performance and low on
interpretability. We use interactive visualization of slices of predictor space
to address the interpretability deficit; in effect opening up the black-box of
machine learning algorithms, for the purpose of interrogating, explaining,
validating and comparing model fits. Slices are specified directly through
interaction, or using various touring algorithms designed to visit
high-occupancy sections or regions where the model fits have interesting
properties. The methods presented here are implemented in the R package
\pkg{condvis2}.
Related papers
- An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training.
Previous research has focused on aligning sequences' visual and semantic spatial distributions.
We introduce a new loss function sampling method to obtain a tight and robust representation.
arXiv Detail & Related papers (2024-06-02T06:53:01Z) - Provably Efficient Representation Learning with Tractable Planning in
Low-Rank POMDP [81.00800920928621]
We study representation learning in partially observable Markov Decision Processes (POMDPs)
We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU)
We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
arXiv Detail & Related papers (2023-06-21T16:04:03Z) - Interpreting Black-box Machine Learning Models for High Dimensional
Datasets [40.09157165704895]
We train a black-box model on a high-dimensional dataset to learn the embeddings on which the classification is performed.
We then approximate the behavior of the black-box model by means of an interpretable surrogate model on the top-k feature space.
Our approach outperforms state-of-the-art methods like TabNet and XGboost when tested on different datasets.
arXiv Detail & Related papers (2022-08-29T07:36:17Z) - Emblaze: Illuminating Machine Learning Representations through
Interactive Comparison of Embedding Spaces [9.849191565291855]
Emblaze is a system that integrates embedding space comparison within a computational notebook environment.
It uses an animated, interactive scatter plot with a novel Star Trail augmentation to enable visual comparison.
It also employs novel neighborhood analysis and clustering procedures to dynamically suggest groups of points with interesting changes between spaces.
arXiv Detail & Related papers (2022-02-05T21:01:49Z) - Model-agnostic multi-objective approach for the evolutionary discovery
of mathematical models [55.41644538483948]
In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results.
We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
arXiv Detail & Related papers (2021-07-07T11:17:09Z) - Transforming Feature Space to Interpret Machine Learning Models [91.62936410696409]
This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations.
It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools.
A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach.
arXiv Detail & Related papers (2021-04-09T10:48:11Z) - Model-agnostic interpretation by visualization of feature perturbations [0.0]
We propose a model-agnostic interpretation approach that uses visualization of feature perturbations induced by the particle swarm optimization algorithm.
We validate our approach both qualitatively and quantitatively on publicly available datasets.
arXiv Detail & Related papers (2021-01-26T00:53:29Z) - Learning outside the Black-Box: The pursuit of interpretable models [78.32475359554395]
This paper proposes an algorithm that produces a continuous global interpretation of any given continuous black-box function.
Our interpretation represents a leap forward from the previous state of the art.
arXiv Detail & Related papers (2020-11-17T12:39:44Z) - A Trainable Optimal Transport Embedding for Feature Aggregation and its
Relationship to Attention [96.77554122595578]
We introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference.
Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost.
arXiv Detail & Related papers (2020-06-22T08:35:58Z) - FDive: Learning Relevance Models using Pattern-based Similarity Measures [27.136998442865217]
We present FDive, a visual active learning system that helps to create visually explorable relevance models.
Based on the best-ranked similarity measure, the system calculates an interactive Self-Organizing Map-based relevance model.
It also automatically prompts further relevance feedback to improve its accuracy.
arXiv Detail & Related papers (2019-07-29T15:37:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.