2016
NIPS
NeurIPS 2016
Learning Deep Parsimonious Representations
Abstract
In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations. Towards this goal, we propose a clustering based regularization that encourages parsimonious representations. Our k-means style objective is easy to optimize and flexible supporting various forms of clustering, including sample and spatial clustering as well as co-clustering. We demonstrate the effectiveness of our approach on the tasks of unsupervised learning, classification, fine grained categorization and zero-shot learning.
🌉
Interdisciplinary Bridge
— Deep Learning and Machine Learning
🧭
Keyword Pioneer
— clustering-based regularization
🐣
Hot Topic Early Bird
— zero-shot learning
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Core Methods > Clustering
Machine Learning > Core Methods > Representation Learning
Machine Learning > Learning Types > Unsupervised Learning
Machine Learning > Learning Types > Zero-Shot Learning
Deep Learning > Learning Types > Representation Learning
Deep Learning > Learning Types > Unsupervised Learning