Article

Probing machine-learning classifiers using noise, bubbles, and reverse correlation

2020-06-23

Abstract excerpt

<h4>Background</h4> Many scientific fields now use machine-learning tools to assist with complex classification tasks. In neuroscience, automatic classifiers may be useful to diagnose medical images, monitor electrophysiological signals, or decode perceptual and cognitive states from neural signals. However, such tools often remain black-boxes: they lack interpretability. A lack of interpretability has obvious et...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: bedbce17-5837-515e-96ea-14ec7a00c7fe
DOI: 10.1101/2020.06.22.165688

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Probing machine-learning classifiers using noise, bubbles, and reverse correlationDOI 10.1101/2020.06.22.165688Read

Machine Learning Interpretability Methods to Characterize Brain Network Dynamics in EpilepsySemantic proximity Read

From Neurons to Networks: A Holistic Review of Electroencephalography (EEG) from Neurophysiological Foundations to Advanced DecodingSemantic proximity Read

Continental generalization of an AI system for clinical seizure recognitionSemantic proximity Read

Multimodal sleep stage classification and label-free abnormality scoring in mid-to-older adultsSemantic proximity Read

Uncertainty in Deep Learning for EEG under Dataset ShiftsSemantic proximity Read

A Fused Power Spectrum based Feature Selection to Identify Schizophrenia from EEG Signals using Deep Learning Models - An Experimental StudySemantic proximity Read

EEG Classification for Neurological Disorders Using Frequency Band DecilesSemantic proximity Read

Toward Generating Physiologically Plausible Artificial Electroencephalography Data: Effects of Convolution-based Upsampling Methods on Data QualitySemantic proximity Read

Classifying REM Sleep Behavior Disorder through CNNs with Image-Based Representations of EEGsSemantic proximity Read

A machine learning toolbox for the analysis of sharp-wave ripples reveal common features across speciesSemantic proximity Read

An Explainable and Robust Deep Learning Approach for Automated Electroencephalography-based Schizophrenia DiagnosisSemantic proximity Read

Towards Causal Interpretability in Deep Learning for Parkinson’s Detection from Voice DataSemantic proximity Read