Learning visual representations with projection pursuit
نویسندگان
چکیده
منابع مشابه
Implementing projection pursuit learning
This paper examines the implementation of projection pursuit regression (PPR) in the context of machine learning and neural networks. We propose a parametric PPR with direct training which achieves improved training speed and accuracy when compared with nonparametric PPR. Analysis and simulations are done for heuristics to choose good initial projection directions. A comparison of a projection ...
متن کاملLearning Visual Representations using Images with Captions
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples is small. When labeled data is scarce it may be beneficial to use unlabeled data to learn an image representation that is low-dimensional, but nevertheless captures the information required to discriminate between ima...
متن کاملCombining Exploratory Projection Pursuit and Projection Pursuit Regression with Application to Neural Networks
Parameter estimation becomes difficult in high-dimensional spaces due to the increasing sparseness of the data. Therefore, when a low-dimensional representation is embedded in the data, dimensionality reduction methods become useful. One such method-projection pursuit regression (Friedman and Stuetzle 1981 (PPR)-is capable of performing dimensionality reduction by composition, namely, it constr...
متن کاملFunctional Projection Pursuit
This article describes the adaption of exploratory projection pursuit for use with functional data. The aim is to nd \interesting" projections of functional data: e.g. to separate curves into meaningful clusters. Functional data are projected onto low-dimensional subspaces determined by a projection function using a suitable inner product. Such a projection is rapidly computed by representing d...
متن کاملOblique Projection Matching Pursuit
Recent theory of compressed sensing (CS) tells us that sparse signals can be reconstructed from a small number of random samples. In reconstruction of sparse signals, greedy algorithms, such as the orthogonal matching pursuit (OMP), have been shown to be computationally efficient. In this paper, the performance of OMP is shown to be dependent on how well information of the underlying signals is...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Vision
سال: 2010
ISSN: 1534-7362
DOI: 10.1167/5.8.373