Disentangled Representations in Neural Models
This work addresses the challenge of interpretability and reusability in neural network representations, which is a problem for researchers and practitioners in machine learning, though it appears incremental as it builds on existing representation learning techniques.
The paper tackles the problem of highly entangled and difficult-to-interpret representations in neural networks by introducing methods for learning disentangled representations in graphics and computation domains, resulting in easy-to-interpret and reusable representations with little or no performance penalty.
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.