MixUp as Locally Linear Out-of-Manifold Regularization
نویسندگان
چکیده
منابع مشابه
Growing Locally Linear Embedding for Manifold Learning
Locally linear embedding is an effective nonlinear dimensionality reduction method for exploring the intrinsic characteristics of high dimensional data. This paper proposes a new manifold learning method, which is based on locally linear embedding and growing neural gas and is termed growing locally linear embedding (GLLE). GLLE overcomes the major limitations of the original locally linear emb...
متن کاملLearning with Locally Linear Feature Regularization
Machine learning models are successfully being used for problems in language, vision, and biology that have millions or tens of millions of features. A common approach to alleviating the complexity of high dimensional feature spaces is to penalize the L1 or L2 norm of the parameter vector. We may be able to design more effective regularizers, though, if we possess external information about whi...
متن کاملLinear Manifold Regularization for Large Scale Semi-supervised Learning
The enormous wealth of unlabeled data in many applications of machine learning is beginning to pose challenges to the designers of semi-supervised learning methods. We are interested in developing linear classification algorithms to efficiently learn from massive partially labeled datasets. In this paper, we propose Linear Laplacian Support Vector Machines and Linear Laplacian Regularized Least...
متن کاملRegularization on Image Patches: a linear reconstruction from manifold embedding
We propose an image representation scheme combining the local and nonlocal characterization of patches in an image. Our representation scheme can be shown to be equivalent to a tight frame constructed from convolving local bases (e.g. wavelet frames, discrete cosine transforms, etc.) with nonlocal bases (e.g. spectral basis induced by nonlinear dimension reduction on patches), and we call the r...
متن کاملVector-valued Manifold Regularization
We consider the general problem of learning an unknown functional dependency, f : X !→ Y, between a structured input space X and a structured output space Y, from labeled and unlabeled examples. We formulate this problem in terms of data-dependent regularization in Vector-valued Reproducing Kernel Hilbert Spaces (Micchelli & Pontil, 2005) which elegantly extend familiar scalarvalued kernel meth...
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: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33013714