Few-shot time series segmentation using prototype-defined infinite hidden Markov models
arXiv:2102.03885
Abstract
We propose a robust framework for interpretable, few-shot analysis of non-stationary sequential data based on flexible graphical models to express the structured distribution of sequential events, using prototype radial basis function (RBF) neural network emissions. A motivational link is demonstrated between prototypical neural network architectures for few-shot learning and the proposed RBF network infinite hidden Markov model (RBF-iHMM). We show that RBF networks can be efficiently specified via prototypes allowing us to express complex nonstationary patterns, while hidden Markov models are used to infer principled high-level Markov dynamics. The utility of the framework is demonstrated on biomedical signal processing applications such as automated seizure detection from EEG data where RBF networks achieve state-of-the-art performance using a fraction of the data needed to train long-short-term memory variational autoencoders.
References in corpus (8)
- Prototypical Networks for Few-shot Learning
- NICE: Non-linear Independent Components Estimation
- Understanding deep learning requires rethinking generalization
- General state space Markov chains and MCMC algorithms
- Normalizing Flows for Probabilistic Modeling and Inference
- A simple example of Dirichlet process mixture inconsistency for the number of components
- Stationary Activations for Uncertainty Calibration in Deep Learning
- Learning higher-order sequential structure with cloned HMMs