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.
This work analyses Polychronous Neuronal Groups (PNGs) and the possibilities of encoding and decoding information from these signals. We considered the use of single neuron coincidence detectors as decoders of PNGs and determined the total number of symbols these detectors could handle. Simulations using the Izhikevich's neuron model yielded several constraints of these systems, from which we obtained...
What are aesthetic emotions and how can they be measured? We discuss that these are emotions related to knowledge and to satisfaction of instinct for knowledge. Arguments from cognitive and mathematical models are presented that aesthetic emotions motivate us to acquire and improve knowledge. Cognitive functions of the emotions of beauty and music are discussed. Can aesthetic emotions be measured?...
We present a new learning rule for intralayer connections in neural networks. The rule is based on Hebbian learning principles and is derived from information theoretic considerations. A simple network trained using the rule is shown to have associative memory like properties. The network acts by building connections between correlated data points, under constraints.
It has been more important to measure daily physical activity for several purposes. There have been a number of methods of measuring physical activity, such as self-reporting, attaching wearable sensors, etc. Since a smartphone has become widespread rapidly, physical activity can be easily measured by accelerometers in the smartphone. Although there were a number of studies for activity recognition...
The mean square convergence of the kernel least mean square (KLMS) algorithm has been studied in a recent paper [B. Chen, S. Zhao, P. Zhu, J. C. Principe, Mean square convergence analysis of the kernel least mean square algorithm, Signal Processing, vol. 92, pp. 2624–2632, 2012]. In this paper, we continue this study and focus mainly on the initial convergence behavior. Two measures of the convergence...
Correntropy, a novel localized similarity measure defined in kernel space, has been successfully used as a cost function in adaptive system training. The adaptive algorithms under the maximum correntropy criterion (MCC) have been shown to be robust to impulsive non-Gaussian noises. However, they may converge slowly especially at a region far from the optimal solution. In this paper, we propose a new...
Driver fatigue problem is one of the important factors of traffic accidents. Recent years, many research had investigated that using EEG signals can effectively detect driver's drowsiness level. However, real-time monitoring system is required to apply these fatigue level detection techniques in the practical application, especially in the real-road driving. Therefore, it required less channels, portable...
Neural network (NN) models have shown good performance on many image recognition benchmarks. Given large image datasets, these models typically have millions or billions of parameters that can easily lead to over-fitting without regularization. Dropout and DropConnect show their effectiveness of regularizing large fully connected layers within neural networks. In Dropout, each neural activation within...
The Izhikevich spiking neuron model is a relatively new mathematical framework which is able to represent many observed spiking neuron behaviors, excitatory or inhibitory, by simply adjusting a set of four model parameters. This model is deterministic in nature and has achieved wide applications in analytical and numerical analysis of biological neurons due largely to its biological plausibility and...
Automatic Term Extraction is an important issue in Natural Language Processing. This paper presents a new approach of terminology extraction combining with machine learning based on cascaded conditional random fields and corpus-based statistical model. In this approach, firstly, the low-layer and high-layer conditional random fields (CRFs) are used to extract the simple and compound terminologies...
In this paper, the KALDI ASR engine adapted to Italian is described and the results obtained so far on some children speech ASR experiments are reported. We give a brief overview of KALDI, we describe in detail its DNN implementation, we introduce the acoustic model (AM) training procedure and we end describing some experiments on Italian children speech together with the final test procedures.
In this work, we used single electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only...
Mining time series data has been revived in the last decade due to the increasing availability of time series datasets. This paper presents an online incremental learning algorithm for time series based on the self-organizing incremental neural network (SOINN) and fast dynamic time warping (FastDTW), referred to as OILFTS. The proposed method OILFTS adopts FastDTW distance as the similarity measure,...
In this paper we introduce the Tensor Deep Stacking Network (T-DSN) Toolkit, an implementation of the T-DSN deep learning architecture. The toolkit consists of a Python library and a set of accompanying helper scripts that allow you to train and evaluate T-DSN models. The toolkit is designed to be portable, modular, efficient and parallelized. Our goal for the toolkit is to promote research on this...
Migraine is a chronic neurological disease characterized by recurrent moderate to severe headaches during a period like one month often in association with symptoms in human brain and autonomic nervous system. Normally, migraine symptoms can be categorized into four different stages: inter-ictal, pre-ictal, ictal, and post-ictal stages. Since migraine patients are difficulty knowing when they will...
In composite event detection systems such as fire alarms, the two foremost goals are speed and accuracy. One way to achieve these goals is by performing data aggregation at central nodes. This helps reduce energy consumption and redundancy. In this paper we present a new hybrid approach that involves the use of k-means algorithm with neural networks, an efficient supervised learning algorithm that...
This paper proposes a cognitive architecture for sensory processing of multimodal data. The cognitive architectures, referred to as Deep Predictive Coding Networks (DPCN) were first used to model video streams. Here we use DPCNs with two input sources, for example: video and speech recordings. We train DPCNs as generative models of both sensors. Since we constrain the network to have a single hidden...
The imbalance problem exists in P300 EEG data sets because P300 potential are collected under the condition of Oddball experimental paradigm. Hence, a P300 detection method, namely RUSBagging SVMs, is proposed in this paper to solve the imbalance problem and make an improvement. This algorithm re-samples the data sets at first to generate a rebalanced training set in one round of iteration and trains...
We design and implement a small neural network, comprised of 52 fixed precision neurons - computationally equivalent to a bounded memory Universal Turing Machine; this design is an order of magnitude smaller than the smallest known universal neural nets. The network is the core of a practical universal neural computer; all neurons have fixed precision and a small set of simple weights. External memory...
Synchronous behavior of neural populations has been related to cognitive processes as attention, learning and has been considered as hallmarks of neurological disorders. The computational models of neural structures, even the simple ones, could give informative results which can improve our understanding of cognitive processes, arising due to collective activity of neurons. Here, a neurocomputational...
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.