Salvato in:
Dettagli Bibliografici
Autori principali: Das, Dibyendu, Fontanini, Alfredo, Kogan, Joshua F., Ling, Haibin, Ramakrishnan, C. R., Ramakrishnan, I. V.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.18221
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913561521946624
author Das, Dibyendu
Fontanini, Alfredo
Kogan, Joshua F.
Ling, Haibin
Ramakrishnan, C. R.
Ramakrishnan, I. V.
author_facet Das, Dibyendu
Fontanini, Alfredo
Kogan, Joshua F.
Ling, Haibin
Ramakrishnan, C. R.
Ramakrishnan, I. V.
contents Fully optimized automation of behavioral training protocols for lab animals like rodents has long been a coveted goal for researchers. It is an otherwise labor-intensive and time-consuming process that demands close interaction between the animal and the researcher. In this work, we used a data-driven approach to optimize the way rodents are trained in labs. In pursuit of our goal, we looked at data augmentation, a technique that scales well in data-poor environments. Using data augmentation, we built several artificial rodent models, which in turn would be used to build an efficient and automatic trainer. Then we developed a novel similarity metric based on the action probability distribution to measure the behavioral resemblance of our models to that of real rodents.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18221
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data Augmentation for Automated Adaptive Rodent Training
Das, Dibyendu
Fontanini, Alfredo
Kogan, Joshua F.
Ling, Haibin
Ramakrishnan, C. R.
Ramakrishnan, I. V.
Artificial Intelligence
Fully optimized automation of behavioral training protocols for lab animals like rodents has long been a coveted goal for researchers. It is an otherwise labor-intensive and time-consuming process that demands close interaction between the animal and the researcher. In this work, we used a data-driven approach to optimize the way rodents are trained in labs. In pursuit of our goal, we looked at data augmentation, a technique that scales well in data-poor environments. Using data augmentation, we built several artificial rodent models, which in turn would be used to build an efficient and automatic trainer. Then we developed a novel similarity metric based on the action probability distribution to measure the behavioral resemblance of our models to that of real rodents.
title Data Augmentation for Automated Adaptive Rodent Training
topic Artificial Intelligence
url https://arxiv.org/abs/2410.18221