|
" Learning from Temporally-Structured Human Activities Data "
Lipton, Zachary Chase
McAuley, Julian;Elkan, Charles
| Document Type
|
:
|
Latin Dissertation
|
| Language of Document
|
:
|
English
|
| Record Number
|
:
|
915064
|
| Doc. No
|
:
|
TL6mw0q3j8
|
| Main Entry
|
:
|
Lipton, Zachary Chase
|
| Title & Author
|
:
|
Learning from Temporally-Structured Human Activities Data\ Lipton, Zachary ChaseMcAuley, Julian;Elkan, Charles
|
| College
|
:
|
UC San Diego
|
| Date
|
:
|
2017
|
| student score
|
:
|
2017
|
| Abstract
|
:
|
Despite the extraordinary success of deep learning on diverse problems, these triumphs are too often confined to large, clean datasets and well-defined objectives. Face recognition systems train on millions of perfectly annotated images. Commercial speech recognition systems train on thousands of hours of painstakingly-annotated data. But for applications addressing human activity, data can be noisy, expensive to collect, and plagued by missing values. In electronic health records, for example, each attribute might be observed on a different time scale. Complicating matters further, deciding precisely what objective warrants optimization requires critical consideration of both algorithms and the application domain. Moreover, deploying human-interacting systems requires careful consideration of societal demands such as safety, interpretability, and fairness.The aim of this thesis is to address the obstacles to mining temporal patterns in human activity data. The primary contributions are: (1) the first application of RNNs to multivariate clinical time series data, with several techniques for bridging long-term dependencies and modeling missing data; (2) a neural network algorithm for forecasting surgery duration while simultaneously modeling heteroscedasticity; (3) an approach to quantitative investing that uses RNNs to forecast company fundamentals; (4) an exploration strategy for deep reinforcement learners that significantly speeds up dialogue policy learning; (5) an algorithm to minimize the number of catastrophic mistakes made by a reinforcement learner; (6) critical works addressing model interpretability and fairness in algorithmic decision-making.
|
| Added Entry
|
:
|
McAuley, Julian;Elkan, Charles
|
| Added Entry
|
:
|
UC San Diego
|
| |