Collecting Speech and Telemetry Data Privately with Ali Shahim Shamsabadi
15/11/2024
11:00 - 12:00This talk explores how we can collect speech and telemetry data privately.
This talk explores how we can collect speech and telemetry data privately.
This talk explores how our personal devices can evolve into reliable tools for health awareness without compromising privacy or demanding excessive engagement and computational resources.
This talk introduces the Reality-Centric AI agenda, an approach that tackles the complexity and challenges of the real world through machine learning (ML).
This talk will show how to build neural models that are not only guaranteed to be compliant with the given requirements over the output space, but are also able to learn from the background knowledge expressed by the requirements themselves and thus get better performance.
This talk will present the core methodologies and techniques for deep learning with graph-structured data along with some recent advances and open problems.
In this tutorial, we dive into this framework to learn how to: Formalize the DG setting as a robust optimization problem; Describe the training and shifted test distributions with structural causal models (SCMs); Show that causal models work well when the training and test distribution differ; Estimate causal models from training data to achieve DG.
