Learning Deep Parsimonious Representations

2016-12-01 · NeurIPS 2016 12 · Renjie Liao, Alex Schwing, Richard Zemel, Raquel Urtasun

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.

📄 PDF Abstract BibTeX

Code (1)

lrjconan/deep_parsimonious 공식 구현 tf

Tasks

ClusteringFew-Shot Image Classification General Classification Zero-Shot Learning

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-series: Application to manipulator robots

2026-05-27 · Mazen Alamir, Sacha Clavel arxiv

This paper addresses the problem of identifying parsimonious explicit piece-wise polynomial relationships that might involve a relatively large number of raw features. The algorithm leverages a recently proposed identifi…

Anomaly Detection

Parsimonious Semantic Representations with Projection Pointers

2013-03-01 · WS 2013 3 · Noortje J. Venhuizen, Johan Bos, Harm Brouwer

Reward driven discovery of the optimal microstructure representations with invariant variational autoencoders

2025-09-30 · Boris N. Slautin, Kamyar Barakati, Hiroshi Funakubo, Maxim A. Ziatdinov 외 arxiv

Microscopy techniques generate vast amounts of complex image data that in principle can be used to discover simpler, interpretable, and parsimonious forms to reveal the underlying physical structures, such as elementary …

Using Machine Learning to Discover Parsimonious and Physically-Interpretable Representations of Catchment-Scale Rainfall-Runoff Dynamics

2024-12-06 · Yuan-Heng Wang, Hoshin V. Gupta

Despite the excellent real-world predictive performance of modern machine learning (ML) methods, many scientists remain hesitant to discard traditional physical-conceptual (PC) approaches due mainly to their relative int…

Dirichlet Process Parsimonious Mixtures for clustering

2015-01-14 · Faicel Chamroukhi, Marius Bartcus, Hervé Glotin

The parsimonious Gaussian mixture models, which exploit an eigenvalue decomposition of the group covariance matrices of the Gaussian mixture, have shown their success in particular in cluster analysis. Their estimation i…

Clustering Model Selection