Recurrent Neural Networks with Interpretable Cells Predict and Classify Worm Behaviour

File Description SizeFormat 
WNIP_2017_paper_kezhi.pdfPublished version5.85 MBAdobe PDFView/Open
Title: Recurrent Neural Networks with Interpretable Cells Predict and Classify Worm Behaviour
Authors: Li, K
Javer, A
Keaveny, E
Brown, AE
Item Type: Conference Paper
Abstract: An important goal in behaviour analytics is to connect disease state or genome variation with observable differences in behaviour. Despite advances in sensor technology and imaging, informative behaviour quantification remains challenging. The nematode worm C. elegans provides a unique opportunity to test analysis approaches because of its small size, compact nervous system, and the availability of large databases of videos of freely behaving animals with known genetic differences. Despite its relative simplicity, there are still no reports of generative models that can capture essential differences between even well-described mutant strains. Here we show that a multilayer recurrent neural network (RNN) can produce diverse behaviours that are difficult to distinguish from real worms’ behaviour and that some of the artificial neurons in the RNN are interpretable and correlate with observable features such as body curvature, speed, and reversals. Although the RNN is not trained to perform classification, we find that artificial neuron responses provide features that perform well in worm strain classification.
Issue Date: 4-Dec-2017
Date of Acceptance: 22-Nov-2017
Journal / Book Title:
Copyright Statement: © The Authors
Conference Name: Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS)
Start Date: 2017-12-04
Finish Date: 2017-12-07
Conference Place: Long Beach, California, USA
Appears in Collections:Clinical Sciences
Molecular Sciences
Faculty of Medicine

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx