Sampling-based Algorithms for Fast and Deployable AI
We present sampling-based algorithms with provable guarantees to alleviate the increasingly prohibitive costs of training and deploying modern AI systems. At the core of this thesis lies importance sampling, which we use to construct representative subsets of inputs and compress machine learning mod...
Main Author: | Baykal, Cenk |
---|---|
Other Authors: | Rus, Daniela |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/139924 https://orcid.org/0000-0002-6776-9493 |
Similar Items
-
The selective deployment of AI in healthcare: an ethical algorithm for algorithms
by: Vandersluis, R, et al.
Published: (2024) -
Sampling-Based Approximation Algorithms for Reachability Analysis with Provable Guarantees
by: Liebenwein, Lucas, et al.
Published: (2018) -
Algorithms for persistent autonomy and surveillance
by: Baykal, Cenk
Published: (2017) -
Ethics and responsible AI deployment
by: Petar Radanliev, et al.
Published: (2024-03-01) -
Fast Sampling Field Deployable Mud Gas Carbon Isotope Analyzer
by: Sheng Wu, et al.
Published: (2020-09-01)