- Location
- Virtual over Zoom
- Series/Type
- Biostatistics Seminar, DLSPH Event
- Dates
- November 16, 2021 from 3:00pm to 4:00pm
Links
The Biostatistics Seminar Series presents:
“Deep Learning Models for Time Series Prediction and their Application to Longitudinal Microbiome Data” by Dr. Divya Sharma, University Health Network
Abstract:
Microbiome inherently is dynamic in nature, attributing to the presence of interactions among microbes, microbes and the host, and with the environment. Researchers have shown that the microbiome can be altered over time, either transiently or long term, by infections or medical interventions such as antibiotics. In this presentation, I will discuss about some of the popular deep learning models for time series prediction tasks and their application in disease prediction using longitudinal microbiome data. I will shed light on how advanced neural networks such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) can be used for feature extraction and temporal dependency analysis in longitudinal microbiome data. We will also discuss about the challenges and future scope in this area, along with the performance comparison with conventional machine learning models.
For Dr. Sharma’s biosketch, please see http://individual.utoronto.ca/DivyaSharma/