Digital Repository

Towards mechanistically constrained Recurrent Neural Network models of population dynamics

Show simple item record

dc.contributor.advisor Barak, Omri en_US
dc.contributor.author DABHOLKAR, KABIR VINAY en_US
dc.date.accessioned 2021-07-15T04:31:50Z
dc.date.available 2021-07-15T04:31:50Z
dc.date.issued 2021-06
dc.identifier.citation 47 en_US
dc.identifier.uri http://dr.iiserpune.ac.in:8080/xmlui/handle/123456789/6076
dc.description.abstract Recurrent Neural Networks (RNNs) trained on neuroscience tasks are promising models of population dynamics of their biological counterparts [1, 2, 3, 4]. In this approach, RNNs are only constrained by task definition, and can potentially find many solutions to the same task. This is because training RNNs (or any highly parameterized function) by input-output examples can suffer from underspecification, as different algorithms or mechanisms can solve the same input-output examples. In light of this, how do we ensure that our RNN models are faithful to the biological computation being modelled? To systematically approach this question, we need a ground truth model. We therefore use a student-teacher framework in which both the teacher and the student are RNNs. In particular, a teacher RNN is trained to solve a task – much like an animal in laboratory – and the student is constrained to match either the behavior or the neural data of the teacher. We then compare mechanistic similarity by invoking the concept of stress tests – inputs not from the task related training distribution. We recognise that both behavioral and neural constraints have weaknesses in this regard and that in order to find some kind of guarantee, information about the teacher’s response to perturbations to the inputs is crucial for the student. Motivated by the abundance of behavioral data, we propose a novel method of training RNNs that we call ‘Jacobian constraint’ , wherein we constrain not only the RNNs input-output behavior but also the sensitivity – the behavioral response to infinitesimal stress tests. We find that RNNs obtained by this method replicate stress test behavior better than those obtained by constraining RNNs to neural data.[5, 6] en_US
dc.language.iso en en_US
dc.subject Recurrent neural networks en_US
dc.subject Computational neuroscience en_US
dc.subject Neural population dynamics en_US
dc.title Towards mechanistically constrained Recurrent Neural Network models of population dynamics en_US
dc.type Thesis en_US
dc.type.degree BS-MS en_US
dc.contributor.department Dept. of Biology en_US
dc.contributor.registration 20161121 en_US


Files in this item

This item appears in the following Collection(s)

  • MS THESES [1705]
    Thesis submitted to IISER Pune in partial fulfilment of the requirements for the BS-MS Dual Degree Programme/MSc. Programme/MS-Exit Programme

Show simple item record

Search Repository


Advanced Search

Browse

My Account