A5055042432- Neural dynamics and brain function
- Zebrafish Biomedical Research Applications
- Neurological disorders and treatments
- Human Pose and Action Recognition
- Neuroscience and Neuropharmacology Research
- Reinforcement Learning in Robotics
- Neonatal and fetal brain pathology
- Genetic Neurodegenerative Diseases
- Context-Aware Activity Recognition Systems
- Parkinson's Disease Mechanisms and Treatments
- Generative Adversarial Networks and Image Synthesis
- Mitochondrial Function and Pathology
- Robot Manipulation and Learning
- Memory and Neural Mechanisms
University of Florida
2022-2023
Large volumes of used electronics are often collected in remanufacturing plants, which requires disassembly before harvesting parts for reuse. Disassembly is mainly conducted manually with low productivity. Recently, human–robot collaboration has been considered as a solution. To assist effectively, robots should observe work environments and recognize human actions accurately. Rich activity video recording supervised learning can be to extract insights; however, does not allow...
Effectively modeling and quantifying behavior is essential for our understanding of the brain. Modeling in naturalistic settings social multi-subject tasks remains a significant challenge. different subjects performing same task requires partitioning behavioral data into features that are common across subjects, others distinct to each subject. interactions between multiple individuals freely-moving setting disentangling effects due individual as compared investigations. To achieve flexible...
Abstract Effectively modeling and quantifying behavior is essential for our understanding of the brain. Modeling in naturalistic settings social multi-subject tasks remains a significant challenge. different subjects performing same task requires partitioning behavioral data into features that are common across subjects, others distinct to each subject. interactions between multiple individuals freely-moving setting disentangling effects due individual as compared investigations. To achieve...
While the neural commonalities as subjects perform similar task-related behaviors has been previously examined, it is very difficult to ascertain for spontaneous, task-unrelated such grooming. As our ability record high-dimensional naturalistic behavioral and corresponding data increases, we can now try understand relationship between different performing spontaneous that occur rarely in time. Here, first apply novel machine learning techniques video from four head-fixed mice they a...
Effectively modeling and quantifying behavior is essential for our understanding of the brain. Modeling in naturalistic settings social multi-subject tasks remains a significant challenge. different subjects performing same task requires partitioning behavioral data into features that are common across subjects, others distinct to each subject. interactions between multiple individuals freely-moving setting disentangling effects due individual as compared investigations. To achieve flexible...
DYT1 or DYT-TOR1A dystonia is early-onset generalized caused by a trinucleotide deletion of GAG in the TOR1A gene leads to loss glutamic acid residue resulting torsinA protein. A mouse model with overt unique importance better understand pathophysiology and evaluate preclinical drug efficacy. likely network disorder involving multiple brain regions, particularly basal ganglia. Dyt1 conditional knockout striatum cerebral cortex motor deficits, suggesting corticostriatal connection...
Effectively modeling and quantifying behavior is essential for our understanding of the brain. Modeling across different subjects in a unified manner remains significant challenge field behavioral quantification, which necessitates partitioning data into features that are common subjects, others distinct to each subject. We build on semi-supervised approach partition subspace adequately known as Partitioned Subspace Variational AutoEncoder (PS-VAE), propose novel regularization based...