123 results match your criteria memory network's


An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory.

Sci Rep 2021 Nov 26;11(1):22978. Epub 2021 Nov 26.

Mogo Auto Intelligence and Telematics Information Technology Co., Ltd, Beijing, China.

Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CRNN. Read More

View Article and Full-Text PDF
November 2021

Biophysical mechanism of the interaction between default mode network and working memory network.

Cogn Neurodyn 2021 Dec 19;15(6):1101-1124. Epub 2021 Apr 19.

East China University of Science and Technology, Shanghai, 200237 China.

Default mode network (DMN) is a functional brain network with a unique neural activity pattern that shows high activity in resting states but low activity in task states. This unique pattern has been proved to relate with higher cognitions such as learning, memory and decision-making. But neural mechanisms of interactions between the default network and the task-related network are still poorly understood. Read More

View Article and Full-Text PDF
December 2021

Anti-cancer Peptide Recognition Based on Grouped Sequence and Spatial Dimension Integrated Networks.

Interdiscip Sci 2021 Oct 12. Epub 2021 Oct 12.

People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, Xinjiang, China.

The diversification of the characteristic sequences of anti-cancer peptides has imposed difficulties on research. To effectively predict new anti-cancer peptides, this paper proposes a more suitable feature grouping sequence and spatial dimension-integrated network algorithm for anti-cancer peptide sequence prediction called GRCI-Net. The main process is as follows: First, we implemented the fusion reduction of binary structure features and K-mer sparse matrix features through principal component analysis and generated a set of new features; second, we constructed a new bidirectional long- and short-term memory network. Read More

View Article and Full-Text PDF
October 2021

Across-Area Synchronization Supports Feature Integration in a Biophysical Network Model of Working Memory.

Front Neural Circuits 2021 20;15:716965. Epub 2021 Sep 20.

Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.

Working memory function is severely limited. One key limitation that constrains the ability to maintain multiple items in working memory simultaneously is so-called swap errors. These errors occur when an inaccurate response is in fact accurate relative to a non-target stimulus, reflecting the failure to maintain the appropriate association or "binding" between the features that define one object (e. Read More

View Article and Full-Text PDF
September 2021

DeepAtrophy: Teaching a neural network to detect progressive changes in longitudinal MRI of the hippocampal region in Alzheimer's disease.

Neuroimage 2021 11 24;243:118514. Epub 2021 Aug 24.

Penn Image Computing and Science Laboratory (PICSL), Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States; Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, United States.

Measures of change in hippocampal volume derived from longitudinal MRI are a well-studied biomarker of disease progression in Alzheimer's disease (AD) and are used in clinical trials to track therapeutic efficacy of disease-modifying treatments. However, longitudinal MRI change measures based on deformable registration can be confounded by MRI artifacts, resulting in over-estimation or underestimation of hippocampal atrophy. For example, the deformation-based-morphometry method ALOHA (Das et al. Read More

View Article and Full-Text PDF
November 2021

Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory.

Front Neurosci 2021 8;15:636127. Epub 2021 Apr 8.

Sandia National Laboratories, Livermore, CA, United States.

In-memory computing based on non-volatile resistive memory can significantly improve the energy efficiency of artificial neural networks. However, accurate training has been challenging due to the nonlinear and stochastic switching of the resistive memory elements. One promising analog memory is the electrochemical random-access memory (ECRAM), also known as the redox transistor. Read More

View Article and Full-Text PDF

Link Prediction Based on Stochastic Information Diffusion.

IEEE Trans Neural Netw Learn Syst 2021 Feb 4;PP. Epub 2021 Feb 4.

Link prediction (LP) in networks aims at determining future interactions among elements; it is a critical machine-learning tool in different domains, ranging from genomics to social networks to marketing, especially in e-commerce recommender systems. Although many LP techniques have been developed in the prior art, most of them consider only static structures of the underlying networks, rarely incorporating the network's information flow. Exploiting the impact of dynamic streams, such as information diffusion, is still an open research topic for LP. Read More

View Article and Full-Text PDF
February 2021

Inhibitory Neural Network's Impairments at Hippocampal CA1 LTP in an Aged Transgenic Mouse Model of Alzheimer's Disease.

Int J Mol Sci 2021 Jan 12;22(2). Epub 2021 Jan 12.

Department of Biomedical Sciences, Graduate School, Chonnam National University, 61186 Gwangju, Korea.

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by a rapid accumulation of amyloid β (Aβ) protein in the hippocampus, which impairs synaptic structures and neuronal signal transmission, induces neuronal loss, and diminishes memory and cognitive functions. The present study investigated the impact of neuregulin 1 (NRG1)-ErbB4 signaling on the impairment of neural networks underlying hippocampal long-term potentiation (LTP) in 5xFAD mice, a model of AD with greater symptom severity than that of TG2576 mice. Specifically, we observed parvalbumin (PV)-containing hippocampal interneurons, the effect of NRG1 on hippocampal LTP, and the functioning of learning and memory. Read More

View Article and Full-Text PDF
January 2021

Memory-Augmented Capsule Network for Adaptable Lung Nodule Classification.

IEEE Trans Med Imaging 2021 10 30;40(10):2869-2879. Epub 2021 Sep 30.

Computer-aided diagnosis (CAD) systems must constantly cope with the perpetual changes in data distribution caused by different sensing technologies, imaging protocols, and patient populations. Adapting these systems to new domains often requires significant amounts of labeled data for re-training. This process is labor-intensive and time-consuming. Read More

View Article and Full-Text PDF
October 2021

Intelligent Fault Diagnosis for Chemical Processes Using Deep Learning Multimodel Fusion.

IEEE Trans Cybern 2020 Dec 30;PP. Epub 2020 Dec 30.

Deep learning technology has been widely used in fault diagnosis for chemical processes. However, most deep learning technologies currently adopted only use a single network stack or a certain network stack with multilayer perceptron (MLP) behind it. Compared with traditional fault diagnosis technologies, this method has made progress in both the diagnosis accuracy and speed, but due to the limited performance of a single network, the accuracy or speed cannot meet the requirements to the greatest extent. Read More

View Article and Full-Text PDF
December 2020

Improving Alzheimer's stage categorization with Convolutional Neural Network using transfer learning and different magnetic resonance imaging modalities.

Heliyon 2020 Dec 10;6(12):e05652. Epub 2020 Dec 10.

Univ. Bordeaux, CNRS, UMR 5287, Institut de Neurosciences Cognitives et Intégratives d'Aquitaine (INCIA), Bordeaux, France.

Background: Alzheimer's Disease (AD) is a neurodegenerative disease characterized by progressive loss of memory and general decline in cognitive functions. Multi-modal imaging such as structural MRI and DTI provide useful information for the classification of patients on the basis of brain biomarkers. Recently, CNN methods have emerged as powerful tools to improve classification using images. Read More

View Article and Full-Text PDF
December 2020

Enhanced Equivalence Projective Simulation: A Framework for Modeling Formation of Stimulus Equivalence Classes.

Neural Comput 2021 02 30;33(2):483-527. Epub 2020 Nov 30.

Department of Behavioral Science, Oslo Metropolitan University, 0130 Oslo, Norway

Formation of stimulus equivalence classes has been recently modeled through equivalence projective simulation (EPS), a modified version of a projective simulation (PS) learning agent. PS is endowed with an episodic memory that resembles the internal representation in the brain and the concept of cognitive maps. PS flexibility and interpretability enable the EPS model and, consequently the model we explore in this letter, to simulate a broad range of behaviors in matching-to-sample experiments. Read More

View Article and Full-Text PDF
February 2021

Development of a Deep Learning Network to Classify Inferior Vena Cava Collapse to Predict Fluid Responsiveness.

J Ultrasound Med 2021 Aug 10;40(8):1495-1504. Epub 2020 Oct 10.

Department of Medicine, Division of Pulmonary Critical Care and Sleep, Warren Alert Medical School of Brown University, Providence, Rhode Island, USA.

Objectives: To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically ill patients.

Methods: We used a data set of IVC ultrasound (US) videos to train the LSTM network. The data set was created from IVC US videos of spontaneously breathing critically ill patients undergoing intravenous fluid resuscitation as part of 2 prior prospective studies. Read More

View Article and Full-Text PDF

Network structure of cascading neural systems predicts stimulus propagation and recovery.

J Neural Eng 2020 11 4;17(5):056045. Epub 2020 Nov 4.

Neuroscience Graduate Group, University of Pennsylvania, Philadelphia, PA 19104, United States of America.

Objective: Many neural systems display spontaneous, spatiotemporal patterns of neural activity that are crucial for information processing. While these cascading patterns presumably arise from the underlying network of synaptic connections between neurons, the precise contribution of the network's local and global connectivity to these patterns and information processing remains largely unknown.

Approach: Here, we demonstrate how network structure supports information processing through network dynamics in empirical and simulated spiking neurons using mathematical tools from linear systems theory, network control theory, and information theory. Read More

View Article and Full-Text PDF
November 2020

An Attention-Guided Deep Neural Network for Annotating Abnormalities in Chest X-ray Images: Visualization of Network Decision Basis

Annu Int Conf IEEE Eng Med Biol Soc 2020 07;2020:1258-1261

Despite the potential of deep convolutional neural networks for classification of thorax diseases from chest X-ray images, this task is still challenging as it is categorized as a weakly supervised learning problem, and deep neural networks in general suffer from a lack of interpretability. In this paper, a deep convolutional neural network framework with recurrent attention mechanism was investigated to annotate abnormalities in chest X-ray images. A modified MobileNet architecture was adapted in the framework for classification and the prediction difference analysis method was utilized to visualize the basis of network's decision on each image. Read More

View Article and Full-Text PDF

Sleep and Epilepsy Link by Plasticity.

Front Neurol 2020 28;11:911. Epub 2020 Aug 28.

Institute of Behavioral Sciences, Semmelweis University, Budapest, Hungary.

We aimed to explore the link between NREM sleep and epilepsy. Based on human and experimental data we propose that a sleep-related epileptic transformation of normal neurological networks underlies epileptogenesis. Major childhood epilepsies as medial temporal lobe epilepsy (MTLE), absence epilepsy (AE) and human perisylvian network (PN) epilepsies - made us good models to study. Read More

View Article and Full-Text PDF

Precise spatial memory in local random networks.

Phys Rev E 2020 Aug;102(2-1):022405

Department of Physics, Department of Biology, and Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, Georgia 30322, USA.

Self-sustained, elevated neuronal activity persisting on timescales of 10 s or longer is thought to be vital for aspects of working memory, including brain representations of real space. Continuous-attractor neural networks, one of the most well-known modeling frameworks for persistent activity, have been able to model crucial aspects of such spatial memory. These models tend to require highly structured or regular synaptic architectures. Read More

View Article and Full-Text PDF

The Use of Neural Networks and Genetic Algorithms to Control Low Rigidity Shafts Machining.

Sensors (Basel) 2020 Aug 19;20(17). Epub 2020 Aug 19.

Faculty of Management, Lublin University of Technology, 20-618 Lublin, Poland.

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective function optimized by a genetic algorithm was replaced with a neural network trained on real-life data. Read More

View Article and Full-Text PDF

Brain-inspired replay for continual learning with artificial neural networks.

Nat Commun 2020 08 13;11(1):4069. Epub 2020 Aug 13.

Center for Neuroscience and Artificial Intelligence, Department of Neuroscience, Baylor College of Medicine, Houston, TX 77030, USA.

Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these networks are trained on something new, they rapidly forget what was learned before. In the brain, a mechanism thought to be important for protecting memories is the reactivation of neuronal activity patterns representing those memories. Read More

View Article and Full-Text PDF

A Cross-Domain Metal Trace Restoring Network for Reducing X-Ray CT Metal Artifacts.

IEEE Trans Med Imaging 2020 12 30;39(12):3831-3842. Epub 2020 Nov 30.

Metal artifacts commonly appear in computed tomography (CT) images of the patient body with metal implants and can affect disease diagnosis. Known deep learning and traditional metal trace restoring methods did not effectively restore details and sinogram consistency information in X-ray CT sinograms, hence often causing considerable secondary artifacts in CT images. In this paper, we propose a new cross-domain metal trace restoring network which promotes sinogram consistency while reducing metal artifacts and recovering tissue details in CT images. Read More

View Article and Full-Text PDF
December 2020

The Domain-General Multiple Demand (MD) Network Does Not Support Core Aspects of Language Comprehension: A Large-Scale fMRI Investigation.

J Neurosci 2020 06 21;40(23):4536-4550. Epub 2020 Apr 21.

Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139

Aside from the language-selective left-lateralized frontotemporal network, language comprehension sometimes recruits a domain-general bilateral frontoparietal network implicated in executive functions: the multiple demand (MD) network. However, the nature of the MD network's contributions to language comprehension remains debated. To illuminate the role of this network in language processing in humans, we conducted a large-scale fMRI investigation using data from 30 diverse word and sentence comprehension experiments (481 unique participants [female and male], 678 scanning sessions). Read More

View Article and Full-Text PDF

Causal importance of low-level feature selectivity for generalization in image recognition.

Authors:
Jumpei Ukita

Neural Netw 2020 May 24;125:185-193. Epub 2020 Feb 24.

Department of Physiology, The University of Tokyo School of Medicine, Hongo, Bunkyo-ku, Tokyo 113-0033, Japan. Electronic address:

Although our brain and deep neural networks (DNNs) can perform high-level sensory-perception tasks, such as image or speech recognition, the inner mechanism of these hierarchical information-processing systems is poorly understood in both neuroscience and machine learning. Recently, Morcos et al. (2018) examined the effect of class-selective units in DNNs, i. Read More

View Article and Full-Text PDF

The Neural Mechanisms of Associative Memory Revisited: fMRI Evidence from Implicit Contingency Learning.

Front Psychiatry 2019 3;10:1002. Epub 2020 Feb 3.

Center of Old Age Psychiatry, Psychiatric University Hospital (UPK), University of Basel, Basel, Switzerland.

The literature describes a basic neurofunctional antagonism between episodic memory encoding and retrieval with opposed patterns of neural activation and deactivation, particularly in posterior midline regions. This has been coined the encoding/retrieval (E/R) flip. The present fMRI study uses an innovative task paradigm to further elucidate neurofunctional relations of encoding and retrieval in associative memory. Read More

View Article and Full-Text PDF
February 2020

A neural network for online spike classification that improves decoding accuracy.

J Neurophysiol 2020 04 26;123(4):1472-1485. Epub 2020 Feb 26.

Department of Biomedical Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania.

Separating neural signals from noise can improve brain-computer interface performance and stability. However, most algorithms for separating neural action potentials from noise are not suitable for use in real time and have shown mixed effects on decoding performance. With the goal of removing noise that impedes online decoding, we sought to automate the intuition of human spike-sorters to operate in real time with an easily tunable parameter governing the stringency with which spike waveforms are classified. Read More

View Article and Full-Text PDF

Multimodal pathway for brain tumor-related epilepsy patients: Observational study.

Acta Neurol Scand 2020 Jun 26;141(6):450-462. Epub 2020 Feb 26.

Biostatistic Unit, Regina Elena National Cancer Institute, IRCCS IFO, Rome, Italy.

Objectives: Brain tumor-related epilepsy patients (BTRE) have a complex profile due to the simultaneous presence of two pathologies: brain tumor and epilepsy. That illness and their treatments could induce physical, cognitive, emotional disturbances, and possible social isolation, with detrimental effect on patients' quality of life (QoL). Aim of this observational pilot study is to evaluate whether a multimodal rehabilitation pathway (MRP) consisting of epileptological follow-up, neurocognitive training, emotional support, and social support could produce an improvement in perceived quality of life of 33 patients with BTRE. Read More

View Article and Full-Text PDF

Three-Dimensional (3D) Vertical Resistive Random-Access Memory (VRRAM) Synapses for Neural Network Systems.

Materials (Basel) 2019 Oct 22;12(20). Epub 2019 Oct 22.

Medical Research Institute, Ewha Womans University, Seoul 03760, Korea.

Memristor devices are generally suitable for incorporation in neuromorphic systems as synapses because they can be integrated into crossbar array circuits with high area efficiency. In the case of a two-dimensional (2D) crossbar array, however, the size of the array is proportional to the neural network's depth and the number of its input and output nodes. This means that a 2D crossbar array is not suitable for a deep neural network. Read More

View Article and Full-Text PDF
October 2019

Can multisensory training aid visual learning? A computational investigation.

J Vis 2019 09;19(11)

Department of Computer Science, University of Rochester, Rochester, NY, USA.

Although real-world environments are often multisensory, visual scientists typically study visual learning in unisensory environments containing visual signals only. Here, we use deep or artificial neural networks to address the question, Can multisensory training aid visual learning? We examine a network's internal representations of objects based on visual signals in two conditions: (a) when the network is initially trained with both visual and haptic signals, and (b) when it is initially trained with visual signals only. Our results demonstrate that a network trained in a visual-haptic environment (in which visual, but not haptic, signals are orientation-dependent) tends to learn visual representations containing useful abstractions, such as the categorical structure of objects, and also learns representations that are less sensitive to imaging parameters, such as viewpoint or orientation, that are irrelevant for object recognition or classification tasks. Read More

View Article and Full-Text PDF
September 2019

The Default Mode Network's Role in Discrete Emotion.

Trends Cogn Sci 2019 10 16;23(10):851-864. Epub 2019 Aug 16.

Department of Psychology and Neuroscience, University of North Carolina, Chapel Hill, NC, USA.

Emotions are often assumed to manifest in subcortical limbic and brainstem structures. While these areas are clearly important for representing affect (e.g. Read More

View Article and Full-Text PDF
October 2019

Mechanoresponsive Polymerized Liquid Metal Networks.

Adv Mater 2019 Oct 12;31(40):e1903864. Epub 2019 Aug 12.

Air Force Research Laboratory, Materials and Manufacturing Directorate, Wright-Patterson AFB, Dayton, OH, 45433, USA.

Room-temperature liquid metals, such as nontoxic gallium alloys, show enormous promise to revolutionize stretchable electronics for next-generation soft robotic, e-skin, and wearable technologies. Core-shell particles of liquid metal with surface-bound acrylate ligands are synthesized and polymerized together to create cross-linked particle networks comprising >99.9% liquid metal by weight. Read More

View Article and Full-Text PDF
October 2019

Functional network connectivity impairments and core cognitive deficits in schizophrenia.

Hum Brain Mapp 2019 11 16;40(16):4593-4605. Epub 2019 Jul 16.

Maryland Psychiatric Research Center, Department of Psychiatry, University of Maryland School of Medicine, Baltimore, Maryland.

Cognitive deficits contribute to functional disability in patients with schizophrenia and may be related to altered functional networks that serve cognition. We evaluated the integrity of major functional networks and assessed their role in supporting two cognitive functions affected in schizophrenia: processing speed (PS) and working memory (WM). Resting-state functional magnetic resonance imaging (rsfMRI) data, N = 261 patients and 327 controls, were aggregated from three independent cohorts and evaluated using Enhancing NeuroImaging Genetics through Meta Analysis rsfMRI analysis pipeline. Read More

View Article and Full-Text PDF
November 2019