← Back to papers
2019 NIPS NeurIPS 2019

Augmented Neural ODEs

Abstract

We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent. To address these limitations, we introduce Augmented Neural ODEs which, in addition to being more expressive models, are empirically more stable, generalize better and have a lower computational cost than Neural ODEs.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
📈 Trend Setter — Neural Networks
🧭 Keyword Pioneer — neural ordinary differential equation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Emilien Dupont , Arnaud Doucet , Yee Whye Teh

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Models > Neural Networks Deep Learning > Learning Types > Representation Learning Machine Learning > Core Methods > Neural Networks

Keywords

representation learning deep learning neural ordinary differential equation topology preservation model expressivity augmented neural ode
Download PDF

Related papers

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test 2019
Metalearned Neural Memory 2019
Model Similarity Mitigates Test Set Overuse 2019
Continual Unsupervised Representation Learning 2019
Reinforcement Learning with Convex Constraints 2019