Studies in Deep Belief Networks
نویسندگان
چکیده
Deep networks are able to learn good representations of unlabelled data via a greedy layer-wise approach to training. One challenge arises in choosing the layer types to use, whether it is an autoencoder, restricted boltzmann machine, with and without sparsity regularization. The layer choice directly affects the type of representations learned. In this paper, we examine sparse autoencoders and characterize their behavior under different parameterizations. We also present preliminary results on quadratic layers with slowness.
منابع مشابه
An adaptive estimation method to predict thermal comfort indices man using car classification neural deep belief
Human thermal comfort and discomfort of many experimental and theoretical indices are calculated using the input data the indicator of climatic elements are such as wind speed, temperature, humidity, solar radiation, etc. The daily data of temperature، wind speed، relative humidity، and cloudiness between the years 1382-1392 were used. In the First step، Tmrt parameter was calculated in the Ray...
متن کاملModelling Retinal Feature Detection With Deep Belief Networks In A Simulated Environment
Recent research has demonstrated the great capability of deep belief networks for solving a variety of visual recognition tasks. However, primary focus has been on modelling higher level visual features and later stages of visual processing found in the brain. Lower level processes such as those found in the retina have gone ignored. In this paper, we address this issue and demonstrate how the ...
متن کاملDeep Belief Networks and Biomedical Text Categorisation
We evaluate the use of Deep Belief Networks as classifiers in a text categorisation task (assigning category labels to documents) in the biomedical domain. Our preliminary results indicate that compared to Support Vector Machines, Deep Belief Networks are superior when a large set of training examples is available, showing an F-score increase of up to 5%. In addition, the training times for DBN...
متن کاملDevelopment and Application of Deep Belief Networks for Predicting Railway Operation
In this paper, we propose to apply deep belief networks (DBN) to predict potential operational disruptions caused by rail vehicle door systems. DBN are a powerful algorithm that is able to detect and extract complex patterns and features in data and has demonstrated superior performance on several benchmark studies. A case study is shown whereby the DBN are trained and applied on real case stud...
متن کاملUnsupervised feature learning for audio classification using convolutional deep belief networks
In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks...
متن کاملA Deep Learning Approach to Machine Transliteration
In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show ...
متن کامل