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.
arXiv commentMIT Master's of Engineering thesis
References in corpus (21)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- How transferable are features in deep neural networks?
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- Deep Convolutional Inverse Graphics Network
- Learning to Execute
- Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
- Importance Weighted Autoencoders
- Neural Programmer-Interpreters
- Reinforcement Learning Neural Turing Machines - Revised
- Generative Image Modeling Using Spatial LSTMs
- Disentangling Factors of Variation via Generative Entangling
- Generating Images from Captions with Attention
- Neural Programmer: Inducing Latent Programs with Gradient Descent
- Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs
- Learning the Irreducible Representations of Commutative Lie Groups
- Deep Lambertian Networks
- Learning Simple Algorithms from Examples
- Learning to Generate Chairs, Tables and Cars with Convolutional Networks
- Inverse Graphics with Probabilistic CAD Models
- Variational Particle Approximations