The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The visual and automatic classification of vehicles plays an important role in the Transport Area. Besides of security issues, the monitoring of the type of traffic in streets and highways, as well the traffic dynamics over time, allows the optimization of use and of resources related to such public infrastructure. In this work we propose a novel method, called 2D-DBM, for robust and efficient automatic...
In this paper, we propose a modified architecture of a Pi-Sigma Neural Network (PSNN) based on two modifications: extension of the activation function and adding delays to neurons in the hidden layer. These new networks are called respectively Activation Function Extended Pi-Sigma (AFEPS) and Delayed Pi-Sigma (DPS) are obtained first by adding an activation function to all hidden neurons and secondly...
Dropout is a very effective way of regularizing neural networks. Stochastically “dropping out” units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregation technique, where an exponential number of smaller networks are averaged in order...
Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to reparameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm,...
New trends in neural computation, now dealing with distributed learning on pervasive sensor networks and multiple sources of big data, make necessary the use of computationally efficient techniques to be implemented on simple and cheap hardware architectures. In this paper, a nonuniform quantization at the input layer of neural networks is introduced, in order to optimize their implementation on hardware...
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition. SHDL framework is constructed with a multi-layer ScatterNet front-end, an unsupervised learning middle, and a supervised learning back-end module. Each layer of the SHDL network is automatically designed as an explicit optimization problem leading...
The increasing amount of data to be processed coming from multiple sources, as in the case of sensor networks, and the need to cope with constraints of security and privacy, make necessary the use of computationally efficient techniques on simple and cheap hardware architectures often distributed in pervasive scenarios. Random Vector Functional-Link is a neural network model usually adopted for processing...
The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed...
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible...
Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced online iterative optimization, enabling nearly real-time stylization. When those stylization networks are applied directly to high-resolution images, however, the style of localized regions often appears less similar to the desired artistic...
Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher Vector encoding with Variational Auto-Encoder (FV-VAE), a novel deep architecture that quantizes the local activations of convolutional layer in a deep generative...
In this paper an Inclined Planes Optimization algorithm, is used to optimize the performance of the multilayer perceptron. Indeed, the performance of the neural network depends on its parameters such as the number of neurons in the hidden layer and the connection weights. So far, most research has been done in the field of training the neural network. In this paper, a new algorithm optimization is...
Various optimal power flow (OPF) algorithms have been utilized in power networks primarily for cost reduction, profit optimization and/or system loss minimization. However, these optimization solvers are either computationally demanding or sensitive to initialization settings and do not guarantee a global optimal. In order to overcome these challenges, this paper proposes an artificial intelligent...
Recent advancements in deep Convolutional Neural Networks (CNNs) have led to impressive progress in computer vision, especially in image classification. CNNs involve numerous hyperparameters that identify the network's structure such as depth of the network, kernel size, number of feature maps, stride, pooling size and pooling regions etc. These hyperparameters have a significant impact on the classification...
Segmentation is a key component of several bio-medical image processing systems. Recently, segmentation methods based on supervised learning such as deep convolutional networks have enjoyed immense success for natural image datasets and biological datasets alike. These methods require large volumes of data to avoid overfitting which limits their applicability. In this work, we present a transfer learning...
Incorporating MPI programming model into data-intensive file system for big data application is significant in performance research for optimization purpose. In this paper we ported an MPI-SVM solver, originally developed for HPC environment to the Hadoop distributed file system (HDFS). We analyzed the performance bottlenecks with which the SVM solver will be confronted on the HDFS. It is known the...
In this paper a Modular Neural Network (MNN) with a granular approach optimization is proposed, where a firefly optimization is proposed to design a optimal MNN architecture. The proposed method can perform the optimization of some parameters such as; number of sub modules, percentage of information for the training phase and number of hidden layers (with their respective number of neurons) for each...
Environmentally friendly and comfortable buildings are a much sought after goal in today's architectural practice. In order to improve energy consumption of buildings without sacrificing indoor comfort, careful consideration of design decisions is needed. Simulation tools provide a solution to one aspect arising from this need, namely the requirement for accurate quantitative results. On the other...
In this paper, a novel change detection method learned from Recurrent Neural Network with transferable ability is proposed. The proposed method, which is based on an improved Long Short Term Memory (LSTM) model, aims at: 1) learning a novel change detection rule to distinguish changed regions with high accuracy; 2) analyzing a new target data with transferable ability from learned change rule; 3)...
As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.