UCI AI/ML Seminar Series
Maja Rudolph
Senior Research Scientist
Bosch Center for AI
Modeling Irregular Time Series with Continuous Recurrent Units
Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Standard RNNs assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) – a neural architecture that can naturally handle irregular intervals between observations. The CRU assumes a hidden state which evolves according to a linear stochastic differential equation and is integrated into an encoder-decoder framework. The recursive computations of the CRU can be derived using the continuous-discrete Kalman filter and are in closed form. The resulting recurrent architecture has temporal continuity between hidden states and a gating mechanism that
5 views
34
5
5 years ago 01:01:31 10
AI/ML Seminar Series: Stephan Mandt (10/19/2020)
3 years ago 01:01:46 5
AI/ML Seminar Series: Maja Rudolph (2/07/2022)
3 years ago 00:59:35 5
AI/ML Seminar Series: Roy Fox (1/10/2022)
3 years ago 00:55:41 16
AI/ML Seminar Series: Ruiqi Gao (2/14/2022)
3 years ago 00:49:41 9
AI/ML Seminar Series: Dylan Slack (1/31/2022)
1 year ago 01:00:50 0
[I’ML] ML System Design
4 years ago 01:33:54 6
RS School ML Pandas Data Manipulations
6 years ago 01:51:08 3
V-Sense Seminar: Deep Learning
8 years ago 02:21:03 2
3. СУБД в HighLoad. Семинар MySQL и шардинг | Технострим
8 years ago 01:53:08 0
Семинар «Deep Learning в решении задач сентимент анализа» | Технострим
8 years ago 03:00:06 6
4. СУБД в HighLoad. Семинар MongoDB | Технострим
4 years ago 00:57:35 2
AI Seminar 2021: Geoffrey Shmigelsky, “Commercialization & Using AI in Livestock ID and Monitoring“
5 years ago 01:29:44 9
Прикладное машинное обучение. Семинар 5. BERT for text classification
4 years ago 01:19:29 40
4. Машинное обучение ПМИ: преобразование данных
4 years ago 01:04:36 8
“Boring” Problems in Distributed ML feat. Richard Liaw | Stanford MLSys Seminar Episode 28
5 years ago 00:13:22 21
Новости из мира ML | Семинар #1 лаборатории машинного обучения ИТМО
3 years ago 01:09:48 8
22. Машинное обучение ПМИ: интерпретируемый ML
4 years ago 01:25:46 29
6. Машинное обучение ПМИ: что мне спрогнозировал алгоритм и калибровка вероятностей
2 years ago 00:00:00 1
Прогнозирование цен на электроэнергию с помощью ML/AI.
5 years ago 00:06:47 7
Новости из мира ML | Семинар #2 лаборатории машинного обучения ИТМО