Neural Expectation Maximization
arXiv:1708.03498
Abstract
Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (sequential) perceptual grouping task and find that it is able to accurately recover the constituent objects. We demonstrate that the learned representations are useful for next-step prediction.
Accepted to NIPS 2017
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- SfM-Net: Learning of Structure and Motion from Video
- Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
- Deep Learning of Representations: Looking Forward
- Learning visual groups from co-occurrences in space and time
- Neuronal Synchrony in Complex-Valued Deep Networks
- Binding via Reconstruction Clustering
- Tagger: Deep Unsupervised Perceptual Grouping
Cited by in corpus (4)
- Investigating Object Compositionality in Generative Adversarial Networks
- Attentive Normalization for Conditional Image Generation
- GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture
- Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation