Geometric Understanding of Deep Learning
arXiv:1805.10451
Abstract
Deep learning is the mainstream technique for many machine learning tasks, including image recognition, machine translation, speech recognition, and so on. It has outperformed conventional methods in various fields and achieved great successes. Unfortunately, the understanding on how it works remains unclear. It has the central importance to lay down the theoretic foundation for deep learning. In this work, we give a geometric view to understand deep learning: we show that the fundamental principle attributing to the success is the manifold structure in data, namely natural high dimensional data concentrates close to a low-dimensional manifold, deep learning learns the manifold and the probability distribution on it. We further introduce the concepts of rectified linear complexity for deep neural network measuring its learning capability, rectified linear complexity of an embedding manifold describing the difficulty to be learned. Then we show for any deep neural network with fixed architecture, there exists a manifold that cannot be learned by the network. Finally, we propose to apply optimal mass transportation theory to control the probability distribution in the latent space.
References in corpus (2)
Cited by in corpus (9)
- Learning Deep Analysis Dictionaries for Image Super-Resolution
- Path homologies of deep feedforward networks
- Optimizing Generative Adversarial Networks for Image Super Resolution via Latent Space Regularization
- Deformable Registration Using Average Geometric Transformations for Brain MR Images
- An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks
- Deep Manifold Embedding for Hyperspectral Image Classification
- Fuzzy Logic Interpretation of Quadratic Networks
- Learning Low-dimensional Manifolds for Scoring of Tissue Microarray Images
- One-Shot Generation of Near-Optimal Topology through Theory-Driven Machine Learning