Read by QxMD icon Read

recurrent neural network

Lin Xiao, Yongsheng Zhang, Bolin Liao, Zhijun Zhang, Lei Ding, Long Jin
A dual-robot system is a robotic device composed of two robot arms. To eliminate the joint-angle drift and prevent the occurrence of high joint velocity, a velocity-level bi-criteria optimization scheme, which includes two criteria (i.e., the minimum velocity norm and the repetitive motion), is proposed and investigated for coordinated path tracking of dual robot manipulators. Specifically, to realize the coordinated path tracking of dual robot manipulators, two subschemes are first presented for the left and right robot manipulators...
2017: Frontiers in Neurorobotics
Emmanuel Mandonnet, Luc Taillandier, Hugues Duffau
Diffuse low-grade gliomas (DLGG) are cerebral tumors occurring in young adults, with an inescapable progression to higher grade of malignancy, resulting in functional impairment and death. DLGG evolve in several phases: an asymptomatic period despite a slow radiological growth; a period in which inaugural symptoms occur, usually epilepsy with possible mild cognitive disorders; then a phase with malignant transformation generating disabling neurological deficits; and ultimately the terminal stage. Early maximal surgical resection significantly increases overall survival while preserving quality of life...
September 15, 2017: La Presse Médicale
Haiou Li, Jie Hou, Badri Adhikari, Qiang Lyu, Jianlin Cheng
BACKGROUND: Deep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins...
September 18, 2017: BMC Bioinformatics
Tolga Ergen, Suleyman Serdar Kozat
We investigate online nonlinear regression and introduce novel regression structures based on the long short term memory (LSTM) networks. For the introduced structures, we also provide highly efficient and effective online training methods. To train these novel LSTM-based structures, we put the underlying architecture in a state space form and introduce highly efficient and effective particle filtering (PF)-based updates. We also provide stochastic gradient descent and extended Kalman filter-based updates. Our PF-based training method guarantees convergence to the optimal parameter estimation in the mean square error sense provided that we have a sufficient number of particles and satisfy certain technical conditions...
September 13, 2017: IEEE Transactions on Neural Networks and Learning Systems
Lei Ding, Lin Xiao, Bolin Liao, Rongbo Lu, Hua Peng
To obtain the online solution of complex-valued systems of linear equation in complex domain with higher precision and higher convergence rate, a new neural network based on Zhang neural network (ZNN) is investigated in this paper. First, this new neural network for complex-valued systems of linear equation in complex domain is proposed and theoretically proved to be convergent within finite time. Then, the illustrative results show that the new neural network model has the higher precision and the higher convergence rate, as compared with the gradient neural network (GNN) model and the ZNN model...
2017: Frontiers in Neurorobotics
Claudius Strub, Gregor Schöner, Florentin Wörgötter, Yulia Sandamirskaya
Dynamic neural fields (DNFs) are dynamical systems models that approximate the activity of large, homogeneous, and recurrently connected neural networks based on a mean field approach. Within dynamic field theory, the DNFs have been used as building blocks in architectures to model sensorimotor embedding of cognitive processes. Typically, the parameters of a DNF in an architecture are manually tuned in order to achieve a specific dynamic behavior (e.g., decision making, selection, or working memory) for a given input pattern...
2017: Frontiers in Computational Neuroscience
Lituan Wang, Lei Zhang, Zhang Yi
Motion models have been proved to be a crucial part in the visual tracking process. In recent trackers, particle filter and sliding windows-based motion models have been widely used. Treating motion models as a sequence prediction problem, we can estimate the motion of objects using their trajectories. Moreover, it is possible to transfer the learned knowledge from annotated trajectories to new objects. Inspired by recent advance in deep learning for visual feature extraction and sequence prediction, we propose a trajectory predictor to learn prior knowledge from annotated trajectories and transfer it to predict the motion of target objects...
October 2017: IEEE Transactions on Cybernetics
Eder Santana, Matthew S Emigh, Pablo Zegers, Jose C Principe
We propose a convolutional recurrent neural network (ConvRNNs), with winner-take-all (WTA) dropout for high-dimensional unsupervised feature learning in multidimensional time series. We apply the proposed method for object recognition using temporal context in videos and obtain better results than comparable methods in the literature, including the deep predictive coding networks (DPCNs) previously proposed by Chalasani and Principe. Our contributions can be summarized as a scalable reinterpretation of the DPCNs trained end-to-end with backpropagation through time, an extension of the previously proposed WTA autoencoders to sequences in time, and a new technique for initializing and regularizing ConvRNNs...
September 1, 2017: IEEE Transactions on Neural Networks and Learning Systems
Zhibin Yu, Dennis S Moirangthem, Minho Lee
Understanding of human intention by observing a series of human actions has been a challenging task. In order to do so, we need to analyze longer sequences of human actions related with intentions and extract the context from the dynamic features. The multiple timescales recurrent neural network (MTRNN) model, which is believed to be a kind of solution, is a useful tool for recording and regenerating a continuous signal for dynamic tasks. However, the conventional MTRNN suffers from the vanishing gradient problem which renders it impossible to be used for longer sequence understanding...
2017: Frontiers in Neurorobotics
Jose A Gonzalez, Lam A Cheah, Phil D Green, James M Gilbert, Stephen R Ell, Roger K Moore, Ed Holdsworth
By speech articulator movement and training a transformation to audio we can restore the power of speech to someone who has lost their larynx. We sense changes in magnetic field caused by movements of small magnets attached to the lips and tongue. The sensor transformation uses recurrent neural networks.
2017: Studies in Health Technology and Informatics
Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister, Alexander M Rush
Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also significant noise. In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics...
August 29, 2017: IEEE Transactions on Visualization and Computer Graphics
Gabriel Koch Ocker, Yu Hu, Michael A Buice, Brent Doiron, Krešimir Josić, Robert Rosenbaum, Eric Shea-Brown
An essential step toward understanding neural circuits is linking their structure and their dynamics. In general, this relationship can be almost arbitrarily complex. Recent theoretical work has, however, begun to identify some broad principles underlying collective spiking activity in neural circuits. The first is that local features of network connectivity can be surprisingly effective in predicting global statistics of activity across a network. The second is that, for the important case of large networks with excitatory-inhibitory balance, correlated spiking persists or vanishes depending on the spatial scales of recurrent and feedforward connectivity...
August 29, 2017: Current Opinion in Neurobiology
Garrett E Katz, James A Reggia
We introduce mathematical objects that we call ``directional fibers,'' and show how they enable a new strategy for systematically locating fixed points in recurrent neural networks. We analyze this approach mathematically and use computer experiments to show that it consistently locates many fixed points in many networks with arbitrary sizes and unconstrained connection weights. Comparison with a traditional method shows that our strategy is competitive and complementary, often finding larger and distinct sets of fixed points...
August 24, 2017: IEEE Transactions on Neural Networks and Learning Systems
Anna Kutschireiter, Simone Carlo Surace, Henning Sprekeler, Jean-Pascal Pfister
The robust estimation of dynamical hidden features, such as the position of prey, based on sensory inputs is one of the hallmarks of perception. This dynamical estimation can be rigorously formulated by nonlinear Bayesian filtering theory. Recent experimental and behavioral studies have shown that animals' performance in many tasks is consistent with such a Bayesian statistical interpretation. However, it is presently unclear how a nonlinear Bayesian filter can be efficiently implemented in a network of neurons that satisfies some minimum constraints of biological plausibility...
August 18, 2017: Scientific Reports
Anjali Chawla, Zachary A Cordner, Gretha Boersma, Timothy H Moran
Binge eating disorder (BED) is defined as recurrent, distressing over-consumption of palatable food (PF) in a short time period. Clinical studies suggest that individuals with BED may have impairments in cognitive processes, executive functioning, impulse control, and decision-making, which may play a role in sustaining binge eating behavior. These clinical reports, however, are limited and often conflicting. In this study, we used a limited access rat model of binge-like behavior in order to further explore the effects of binge eating on cognition...
October 15, 2017: Physiology & Behavior
Yahya Karimipanah, Zhengyu Ma, Ralf Wessel
A rigorous understanding of brain dynamics and function requires a conceptual bridge between multiple levels of organization, including neural spiking and network-level population activity. Mounting evidence suggests that neural networks of cerebral cortex operate at a critical regime, which is defined as a transition point between two phases of short lasting and chaotic activity. However, despite the fact that criticality brings about certain functional advantages for information processing, its supporting evidence is still far from conclusive, as it has been mostly based on power law scaling of size and durations of cascades of activity...
2017: PloS One
MohammadMehdi Kafashan, ShiNung Ching
A long-standing and influential hypothesis in neural information processing is that early sensory networks adapt themselves to produce efficient codes of afferent inputs. Here, we show how a nonlinear recurrent network provides an optimal solution for the efficient coding of an afferent input and its history. We specifically consider the problem of producing lightweight codes, ones that minimize both ℓ1 and ℓ2 constraints on sparsity and energy, respectively. When embedded in a linear coding paradigm, this problem results in a non-smooth convex optimization problem...
July 22, 2017: Neural Networks: the Official Journal of the International Neural Network Society
Antonio Jimeno Yepes
Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised learning algorithm methods are used as one of the approaches to perform disambiguation. Features extracted from the context of an ambiguous word are used to identify the proper sense of such a word. The type of features have an impact on machine learning methods, thus affect disambiguation performance...
August 7, 2017: Journal of Biomedical Informatics
Yifan Zhang, Michiel Vanmeert, Aleksandra Siekierska, Annelii Ny, Jubi John, Geert Callewaert, Eveline Lescrinier, Wim Dehaen, Peter A M de Witte, Rafal M Kaminski
Epilepsy is a chronic brain disorder characterized by recurrent seizures due to abnormal, excessive and synchronous neuronal activities in the brain. It affects approximately 65 million people worldwide, one third of which are still estimated to suffer from refractory seizures. Glutamic acid decarboxylase (GAD) that converts glutamate into GABA is a key enzyme in the dynamic regulation of neural network excitability. Importantly, clinical evidence shows that lowered GAD activity is associated with several forms of epilepsy which are often treatment resistant...
August 3, 2017: Scientific Reports
Quan Wang, Constantin A Rothkopf, Jochen Triesch
The ability to learn sequential behaviors is a fundamental property of our brains. Yet a long stream of studies including recent experiments investigating motor sequence learning in adult human subjects have produced a number of puzzling and seemingly contradictory results. In particular, when subjects have to learn multiple action sequences, learning is sometimes impaired by proactive and retroactive interference effects. In other situations, however, learning is accelerated as reflected in facilitation and transfer effects...
August 2017: PLoS Computational Biology
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"