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.
Heart disease is a deadly disease that large population of people around the world suffers from. When considering death rates and large number of people who suffers from heart disease, it is revealed how important early diagnosis of heart disease. Traditional way of diagnosis is not sufficient for such an illness. Developing a medical diagnosis system based on machine learning for prediction of heart...
This work presents improvements to a neuroevolution algorithm called Evolutionary eXploration of Augmenting Convolutional Topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). While EXACT has multithreaded and parallel implementations, it has also been implemented as part of a volunteer computing project at the Citizen Science Grid to provide truly...
With the benefit of convolutional operation, the convolutional neural networks (CNN) has been successfully applied in classification, regression and time series modeling. For neural modeling of dynamic systems, CNN also should have many advantages over other neural models, such as avoiding local minima and the noises and outliers affections. In this paper, the dynamic system identification is addressed...
Dropout is a technique widely used for preventing overfitting while training deep neural networks. However, applying dropout to a neural network typically increases the training time. This paper proposes a different dropout approach called controlled dropout that improves training speed by dropping units in a column-wise or row-wise manner on the matrices. In controlled dropout, a network is trained...
With the extensive application of machine learning algorithms in bioinformatics, more and more computer researchers are beginning to focus on this field. Polyadenylation of messenger RNA (mRNA) is one of the key steps of gene expression in eukaryotes, polyadenylation site marks the end of transcription, it is of great significance to explore prediction of the site of gene sequences encoding gene....
Motor function rehabilitation is very urgent for patients. Motor imagery is an efficient way for rehabilitation. To achieve the supervision of multiple rehabilitation targets simultaneously, the promotion of multi-class motor imagery classification accuracy is critical. In this paper, a multi-class classification method is proposed by utilizing singular value decomposition and deep boltzmann machine...
We study unsupervised learning by developing a generative model built from progressively learned deep convolutional neural networks. The resulting generator is additionally a discriminator, capable of "introspection" in a sense — being able to self-evaluate the difference between its generated samples and the given training data. Through repeated discriminative learning, desirable properties...
In this paper, we present a model for rainfall rate prediction 30 seconds ahead of time using an artificial neural network. The resultant predicted rainfall rate can then be used in determining an appropriate fade counter-measure, for instance, digital modulation scheme ahead of time, to keep the bit error rate (BER) on the link within acceptable levels to allow constant flow of data on the link during...
Neural networks have demonstrated promising results for a wide range of applications. The proposed techniques employ different architectures and objective functions to adapt to the application while enabling a feasible implementation. Commonly used objective functions for network optimization are based on the cross entropy between the empirical distribution of the training data and the model distribution...
This paper describes a pipelined stochastic gradient descent (SGD) algorithm and its hardware architecture with a memory distributed structure. In the proposed architecture, a pipeline stage takes charge of multiple layers: a “layer block.” The layer-block-wise pipeline has much less weight parameters for network training than conventional multithreading because weight memory is distributed to workers...
Deep structured of Convolutional Neural Networks (CNN) has recently gained intense attention in development due to its good performance in object recognition. One of the crucial components in CNN is the learning mechanism of weight parameters through backpropagation. In this paper, stochastic diagonal Approximate Greatest Descent (SDAGD) is proposed to train weight parameters in CNN. SDAGD adopts...
State-of-the-art convolutional neural networks are enormously costly in both compute and memory, demanding massively parallel GPUs for execution. Such networks strain the computational capabilities and energy available to embedded and mobile processing platforms, restricting their use in many important applications. In this paper, we propose BCNN with Separable Filters (BCNNw/SF), which applies Singular...
Scaling CMOS integrated circuit technology leads to decrease the chip price and increase processing performance in complex applications with re-configurability. Thus, VLSI architecture is a promising candidate in implementing neural network models nowadays. Backpropagation algorithm is used for training multilayer perceptron with high degree of parallel processing. Parallel computing implementation...
Histopathological characterization of colorectal polyps is an important principle for determining the risk of colorectal cancer and future rates of surveillance for patients. The process of characterization is time-intensive and requires years of specialized medical training. In this work, we propose a deep-learning-based image analysis approach that not only can accurately classify different types...
Analog resistive memories promise to reduce the energy of neural networks by orders of magnitude. However, the write variability and write nonlinearity of current devices prevent neural networks from training to high accuracy. We present a novel periodic carry method that uses a positional number system to overcome this while maintaining the benefit of parallel analog matrix operations. We demonstrate...
With the increase in the availability of information regarding energy use, there is an increase of forecasting software on the energy market, that can forecast on the short, medium and long term. In the paper, there is presented a software solution for load forecasting using Artificial Neural Networks (ANN) method. In the case study, we have written an application for a consumer which is engaged in...
Artificial neural networks (ANN) have become a powerful tool for machine learning. Resistive memory devices can be used for the realization of a non-von Neumann computational platform for ANN training in an area-efficient way. For instance, the conductance values of phase-change memory (PCM) devices can be used to represent synaptic weights and can be updated in-situ according to learning rules. However,...
The system security has turned into an extremely critical worry as system assaults have been extending with the ascent of hacking devices, inconvenience of systems and interruptions in number and brutality. This paper is centered around interruption identification by utilizing Multilayer Perceptron (MLP) with various calculation of backpropagation neural network. In this paper, performance of various...
An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. The gradient descent back-propagation rule is a powerful algorithm that is ubiquitous in deep learning, but it relies on the immediate availability of network-wide information stored with high-precision...
This paper reports how to train a Deep Belief Network (DBN) using only 8-bit fixed-point parameters. We propose a dynamic-point stochastic rounding algorithm that provides enhanced results compared to the existing stochastic rounding. We show that by using a variable scaling factor, the fixed-point parameter updates are enhanced. To be more hardware amenable, the use of common scaling factor at each...
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.