Manifold Regularized Discriminative Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Discriminative Sparse Coding on Multi-Manifold for Data Representation and Classification
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 ClassificationGraph based manifold regularized deep neural networks for automatic speech recognition
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 RecognitionA Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning
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 LearningSCE: A manifold regularized set-covering method for data partitioning
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…
ClusteringA Manifold Regularized Multi-Task Learning Model for IQ Prediction from Multiple fMRI Paradigms
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