Reproducibility of importance extraction methods in neural network based fMRI classification

Gotsopoulos, Athanasios; Saarimäki, Heini; Glerean, Enrico; Jä̈askëlainen, Iiro P.; Sams, Mikko; Nummenmaa, Lauri; Lampinen, Jouko

doi:10.1101/197277

Cited by 3 publications

(2 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prior consideration -that individual variables might not be particularly predictive, but can still contribute to an informative set-is still an important factor when interpreting the results of the ablation approach. Gotsopoulos and colleagues (2018) discuss these and other approaches for the classification of fMRI data (Gotsopoulos et al, 2018).…”

Section: Outputs and Interpretationmentioning

confidence: 99%

Machine Learning for Clinical Psychology and Clinical Neuroscience

Coutanche¹,

Hallion²

2019

Preprint

View full text Add to dashboard Cite

A rapid growth in computational power and an increasing availability of large, publicly- accessible, multimodal datasets present new opportunities for psychology and neuroscience researchers to ask novel questions, and to approach old questions in novel ways. Studies of the personal characteristics, situation-specific factors, and sociocultural contexts that result in the onset, development, maintenance, and remission of psychopathology, are particularly well-suited to benefit from machine learning methods. However, introductory textbooks for machine learning rarely tailor their guidance to the needs of psychology and neuroscience researchers. Similarly, the traditional statistical training of clinical scientists often does not incorporate these approaches. This chapter acts as an introduction to machine learning for researchers in the fields of clinical psychology and clinical neuroscience. We discuss these methods, illustrated through real and hypothetical applications in the fields of clinical psychology and clinical neuroscience. We touch on study design, selecting appropriate techniques, how (and how not) to interpret results, and more, to aid researchers who are interested in applying machine learning methods to clinical science data.

show abstract

Section: Outputs and Interpretationmentioning

confidence: 99%

Machine Learning for Clinical Psychology and Clinical Neuroscience

Coutanche¹,

Hallion²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Neural network (NN) structures have been used for knowledge representation [1], modelling [2][3][4], prediction [5,6], design automation [7], classification [8,9], identification [10], and nonlinear control [11] applications in many domains. All these applications mainly used the monolithic structure for NN.…”

Section: Introductionmentioning

confidence: 99%

A dynamic ensemble learning algorithm for neural networks

Alam

Siddique

Adeli

2019

Neural Comput & Applic

338

167

View full text Add to dashboard Cite

This paper presents a novel dynamic ensemble learning (DEL) algorithm for designing ensemble of neural networks (NNs). DEL algorithm determines the size of ensemble, the number of individual NNs employing a constructive strategy, the number of hidden nodes of individual NNs employing a constructive-pruning strategy, and different training samples for individual NN's learning. For diversity, negative correlation learning has been introduced and also variation of training samples has been made for individual NNs that provide better learning from the whole training samples. The major benefits of the proposed DEL compared to existing ensemble algorithms are (1) automatic design of ensemble; (2) maintaining accuracy and diversity of NNs at the same time; and (3) minimum number of parameters to be defined by user. DEL algorithm is applied to a set of real-world classification problems such as the cancer, diabetes, heart disease, thyroid, credit card, glass, gene, horse, letter recognition, mushroom, and soybean datasets. It has been confirmed by experimental results that DEL produces dynamic NN ensembles of appropriate architecture and diversity that demonstrate good generalization ability.

show abstract

Gradient self-weighting linear collaborative discriminant regression classification for human cognitive states classification

Gupta

Chatur

2020

Machine Vision and Applications

View full text Add to dashboard Cite

Reproducibility of importance extraction methods in neural network based fMRI classification

Cited by 3 publications

References 59 publications

Machine Learning for Clinical Psychology and Clinical Neuroscience

Machine Learning for Clinical Psychology and Clinical Neuroscience

A dynamic ensemble learning algorithm for neural networks

Gradient self-weighting linear collaborative discriminant regression classification for human cognitive states classification

Contact Info

Product

Resources

About