Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
نویسندگان
چکیده
We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark.
منابع مشابه
Deep Neural Networks for Iris Recognition System Based on Video: Stacked Sparse Auto Encoders (ssae) and Bi-propagation Neural Network Models
Iris recognition technique is now regarded among the most trustworthy biometrics tactics. This is basically ascribed to its extraordinary consistency in identifying individuals. Moreover, this technique is highly efficient because of iris’ distinctive characteristics and due to its ability to protect the iris against environmental and aging effects. The Problem statement of this work is that th...
متن کاملStacked What-Where Auto-encoders
We present a novel architecture, the “stacked what-where auto-encoders” (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised and unsupervised learning without relying on sampling during training. An instantiation of SWWAE uses a convolutional net (Convnet) (LeCun et al. (1998)) to encode the input, and employs a deconvol...
متن کاملTransfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data
Tremendous progress has been made in object recognition with deep convolutional neural networks (CNNs), thanks to the availability of large-scale annotated dataset. With the ability of learning highly hierarchical image feature extractors, deep CNNs are also expected to solve the Synthetic Aperture Radar (SAR) target classification problems. However, the limited labeled SAR target data becomes ...
متن کاملStacked Sparse Auto-Encoders (SSAE) Based Electronic Nose for Chinese Liquors Classification
This paper presents a stacked sparse auto-encoder (SSAE) based deep learning method for an electronic nose (e-nose) system to classify different brands of Chinese liquors. It is well known that preprocessing; feature extraction (generation and reduction) are necessary steps in traditional data-processing methods for e-noses. However, these steps are complicated and empirical because there is no...
متن کاملTraining Auto-encoders Effectively via Eliminating Task-irrelevant Input Variables
Auto-encoders are often used as building blocks of deep network classifier to learn feature extractors, but task-irrelevant information in the input data may lead to bad extractors and result in poor generalization performance of the network. In this paper,via dropping the task-irrelevant input variables the performance of auto-encoders can be obviously improved .Specifically, an importance-bas...
متن کامل