Open AccessProceedings Article
VISUALIZATION OF NONLINEAR CLASSIFICATION MODELS IN NEUROIMAGING - Signed Sensitivity Maps
Peter Mondrup Rasmussen,Tanya Schmah,Kristoffer Hougaard Madsen,Torben Ellegaard Lund,Grigori Yourganov,Stephen C. Strother,Lars Kai Hansen +6 more
- 01 Jan 2012
- pp 254-263
23
TL;DR: This work focuses on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain, unlike earlier related methods.
read more
Abstract: Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model visualization. Specifically we focus on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain. Each of the maps includes sign information, unlike earlier related methods. The sign information allows the researcher to assess in which direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.
Sebastian Bach,Alexander Binder,Grégoire Montavon,Frederick Klauschen,Klaus-Robert Müller,Wojciech Samek +5 more
TL;DR: This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers by introducing a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks.
Evaluating the Visualization of What a Deep Neural Network Has Learned
TL;DR: In this article, a general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps is presented, and the authors compare heatmaps computed by three different methods on the SUN397, ILSVRC2012, and MIT Places data sets.
•Posted Content
Evaluating the visualization of what a Deep Neural Network has learned
TL;DR: A general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps and shows that the recently proposed layer-wise relevance propagation algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method.
431
•Posted Content
Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
Mariusz Bojarski,Philip Yeres,Anna Choromanska,Krzysztof Choromanski,Bernhard Firner,Lawrence D. Jackel,Urs A. Muller +6 more
TL;DR: A method for determining which elements in the road image most influence PilotNet's steering decision is developed, and results show that PilotNet indeed learns to recognize relevant objects on the road.
402
Multivariate lesion-symptom mapping using support vector regression.
TL;DR: The purpose of this artilce was to develop an MLSM using a machine learning‐based multivariate regression algorithm: support vector regression (SVR), and found that SVR‐LSM showed much higher sensitivity and specificity for detecting the synthetic lesion‐behavior relations than VLSM.
289
References
•Book
Kernel Methods for Pattern Analysis
John Shawe-Taylor,Nello Cristianini +1 more
- 01 Jan 2004
TL;DR: This book provides an easy introduction for students and researchers to the growing field of kernel-based pattern analysis, demonstrating with examples how to handcraft an algorithm or a kernel for a new specific application, and covering all the necessary conceptual and mathematical tools to do so.
Regularized Discriminant Analysis
TL;DR: Alternatives to the usual maximum likelihood estimates for the covariance matrices are proposed, characterized by two parameters, the values of which are customized to individual situations by jointly minimizing a sample-based estimate of future misclassification risk.
2.5K
Decoding mental states from brain activity in humans
John-Dylan Haynes,Geraint Rees +1 more
TL;DR: This work has shown that it is possible to accurately decode a person's conscious experience based only on non-invasive measurements of their brain activity, and can also be extended to other types of mental state, such as covert attitudes and lie detection.
1.9K
Machine learning classifiers and fMRI: a tutorial overview
TL;DR: This tutorial overview shows how, in addition to answering the question of 'is there information about a variable of interest' ( pattern discrimination), classifiers can be used to tackle other classes of question, namely 'where is the information' and 'how is that information encoded' (pattern characterization).
1.8K
Functional magnetic resonance imaging (fMRI) "brain reading": detecting and classifying distributed patterns of fMRI activity in human visual cortex.
David D. Cox,Robert L. Savoy +1 more
TL;DR: In the present study, multivariate statistical pattern recognition methods were used to classify patterns of fMRI activation evoked by the visual presentation of various categories of objects, demonstrating that fMRI data contain far more information than is typically appreciated.
1.2K