# Understanding Visual Concepts with Continuation Learning

arXiv: https://arxiv.org/abs/1602.06822 · HTML: https://mlsanity.com/paper/1602.06822/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2016.

## Built on by (most cited first, 4 of 4)

- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions](https://mlsanity.com/paper/2207.11805/) (2022)
- [ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation](https://mlsanity.com/paper/2212.00435/) (2022)
- [How Video Meetings Change Your Expression](https://mlsanity.com/paper/2406.00955/) (2024)

## Abstract (arXiv)

We introduce a neural network architecture and a learning algorithm to produce factorized symbolic representations. We propose to learn these concepts by observing consecutive frames, letting all the components of the hidden representation except a small discrete set (gating units) be predicted from the previous frame, and let the factors of variation in the next frame be represented entirely by these discrete gated units (corresponding to symbolic representations). We demonstrate the efficacy of our approach on datasets of faces undergoing 3D transformations and Atari 2600 games.