paper-with-me

홈 › Papers

Manifold Regularized Discriminative Neural Networks

2015-11-19 · Shuangfei Zhai, Zhongfei Zhang

Unregularized deep neural networks (DNNs) can be easily overfit with a limited sample size. We argue that this is mostly due to the disriminative nature of DNNs which directly model the conditional probability (or score) of labels given the input. The ignorance of input distribution makes DNNs difficult to generalize to unseen data. Recent advances in regularization techniques, such as pretraining and dropout, indicate that modeling input data distribution (either explicitly or implicitly) greatly improves the generalization ability of a DNN. In this work, we explore the manifold hypothesis which assumes that instances within the same class lie in a smooth manifold. We accordingly propose two simple regularizers to a standard discriminative DNN. The first one, named Label-Aware Manifold Regularization, assumes the availability of labels and penalizes large norms of the loss function w.r.t. data points. The second one, named Label-Independent Manifold Regularization, does not use label information and instead penalizes the Frobenius norm of the Jacobian matrix of prediction scores w.r.t. data points, which makes semi-supervised learning possible. We perform extensive control experiments on fully supervised and semi-supervised tasks using the MNIST, CIFAR10 and SVHN datasets and achieve excellent results.

📄 PDF Abstract BibTeX arXiv:1511.06328

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Discriminative Sparse Coding on Multi-Manifold for Data Representation and Classification

2012-08-19 · Jing-Yan Wang

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics, etc. However, the conventional sparse coding algorith…

General Classification

Graph based manifold regularized deep neural networks for automatic speech recognition

2016-06-19 · Vikrant Singh Tomar, Richard C. Rose

Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning

2017-07-01 · CVPR 2017 7 · Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang 외

Deep Auto-Encoder (DAE) has shown its promising power in high-level representation learning. From the perspective of manifold learning, we propose a graph regularized deep neural network (GR-DNN) to endue traditional DAE…

Representation Learning

SCE: A manifold regularized set-covering method for data partitioning

2019-04-17 · Xuelong. Li, Quanmao Lu, Yongsheng Dong, DaCheng Tao

Cluster analysis plays a very important role in data analysis. In these years, cluster ensemble, as a cluster analysis tool, has drawn much attention for its robustness, stability, and accuracy. Many efforts have been do…

Clustering

A Manifold Regularized Multi-Task Learning Model for IQ Prediction from Multiple fMRI Paradigms

2019-01-17

Multi-modal brain functional connectivity (FC) data have shown great potential for providing insights into individual variations in behavioral and cognitive traits. The joint learning of multi-modal imaging data can util…

Functional ConnectivityMulti-Task Learning