# Semi-unsupervised Learning of Human Activity using Deep Generative Models

arXiv: https://arxiv.org/abs/1810.12176 · HTML: https://mlsanity.com/paper/1810.12176/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2018.

## Built on by (most cited first, 1 of 1)

- [Semi-unsupervised Learning for Time Series Classification](https://mlsanity.com/paper/2207.03119/) (2022)

## Abstract (arXiv)

We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able to learn from training data of this type are potentially of great use as many real-world datasets are like this. Here we demonstrate a new deep generative model for classification in this regime. Our model, a Gaussian mixture deep generative model, demonstrates superior semi-unsupervised classification performance on MNIST to model M2 from Kingma and Welling (2014). We apply the model to human accelerometer data, performing activity classification and structure discovery on windows of time series data.