Disentangled Representations in Neural Models
arXiv:1602.02383
Abstract
Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to reuse and interpret, and they do a poor job of capturing the sparsity which is present in real- world transformations. In this paper, I describe methods for learning disentangled representations in the two domains of graphics and computation. These methods allow neural methods to learn representations which are easy to interpret and reuse, yet they incur little or no penalty to performance. In the Graphics section, I demonstrate the ability of these methods to infer the generating parameters of images and rerender those images under novel conditions. In the Computation section, I describe a model which is able to factorize a multitask learning problem into subtasks and which experiences no catastrophic forgetting. Together these techniques provide the tools to design a wide range of models that learn disentangled representations and better model the factors of variation in the real world.
MIT Master's of Engineering thesis
References in corpus (9)
- How transferable are features in deep neural networks?
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Deep Convolutional Inverse Graphics Network
- Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
- Disentangling Factors of Variation via Generative Entangling
- Neural Programmer: Inducing Latent Programs with Gradient Descent
- Deep Lambertian Networks
- Learning Simple Algorithms from Examples
- Inverse Graphics with Probabilistic CAD Models