Representation Learning: A Statistical Perspective
arXiv:1911.11374
Abstract
Learning representations of data is an important problem in statistics and machine learning. While the origin of learning representations can be traced back to factor analysis and multidimensional scaling in statistics, it has become a central theme in deep learning with important applications in computer vision and computational neuroscience. In this article, we review recent advances in learning representations from a statistical perspective. In particular, we review the following two themes: (a) unsupervised learning of vector representations and (b) learning of both vector and matrix representations.
References in corpus (17)
- Efficient Estimation of Word Representations in Vector Space
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Generative Adversarial Text to Image Synthesis
- NICE: Non-linear Independent Components Estimation
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Variational Inference with Normalizing Flows
- Neural Variational Inference and Learning in Belief Networks
- A Theory of Generative ConvNet
- Deep Directed Generative Models with Energy-Based Probability Estimation
- Alternating Back-Propagation for Generator Network
- Introspective Classification with Convolutional Nets
- Learning FRAME Models Using CNN Filters
- Calibrating Energy-based Generative Adversarial Networks
- Learning Grid Cells as Vector Representation of Self-Position Coupled with Matrix Representation of Self-Motion
- Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
- Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model