scholarly journals A robust deep neural network for denoising task-based fMRI data: An application to working memory and episodic memory

2019 ◽  
Author(s):  
Zhengshi Yang ◽  
Xiaowei Zhuang ◽  
Karthik Sreenivasan ◽  
Virendra Mishra ◽  
Tim Curran ◽  
...  
Keyword(s):  
Neural Network ◽  
Working Memory ◽  
Episodic Memory ◽  
Gray Matter ◽  
Deep Neural Network ◽  
Memory Task ◽  
Fmri Data ◽  
Elderly Subjects ◽  
Fully Connected ◽  
Time Point

ABSTRACTIn this study, a deep neural network (DNN) is proposed to reduce the noise in task-based fMRI data without explicitly modeling noise. The DNN artificial neural network consists of one temporal convolutional layer, one long short-term memory (LSTM) layer, one time-distributed fully-connected layer, and one unconventional selection layer in sequential order. The LSTM layer takes not only the current time point but also what was perceived in a previous time point as its input to characterize the temporal autocorrelation of fMRI data. The fully-connected layer weights the output of the LSTM layer, and the output denoised fMRI time series is selected by the selection layer. Assuming that task-related neural response is limited to gray matter, the model parameters in the DNN network are optimized by maximizing the correlation difference between gray matter voxels and white matter or ventricular cerebrospinal fluid voxels. Instead of targeting a particular noise source, the proposed neural network takes advantage of the task design matrix to better extract task-related signal in fMRI data. The DNN network, along with other traditional denoising techniques, has been applied on simulated data, working memory task fMRI data acquired from a cohort of healthy subjects and episodic memory task fMRI data acquired from a small set of healthy elderly subjects. Qualitative and quantitative measurements were used to evaluate the performance of different denoising techniques. In the simulation, DNN improves fMRI activation detection and also adapts to varying hemodynamic response functions across different brain regions. DNN efficiently reduces physiological noise and generates more homogeneous task-response correlation maps in real data.

scholarly journals A robust deep neural network for denoising task-based fMRI data: An application to working memory and episodic memory

2020 ◽  
Vol 60 ◽  
pp. 101622 ◽  
Author(s):  
Zhengshi Yang ◽  
Xiaowei Zhuang ◽  
Karthik Sreenivasan ◽  
Virendra Mishra ◽  
Tim Curran ◽  
...  
Keyword(s):  
Neural Network ◽  
Working Memory ◽  
Episodic Memory ◽  
Deep Neural Network ◽  
Fmri Data

scholarly journals Are visual working memory and episodic memory distinct processes? Insight from stroke patients by lesion-symptom mapping

2021 ◽  
Author(s):  
Selma Lugtmeijer ◽  
◽  
Linda Geerligs ◽  
Frank Erik de Leeuw ◽  
Edward H. F. de Haan ◽  
...  
Keyword(s):  
Working Memory ◽  
Episodic Memory ◽  
Visual Working Memory ◽  
Visual Memory ◽  
Right Hemisphere ◽  
Memory Task ◽  
Stroke Patients ◽  
Lesion Symptom Mapping ◽  
Criterion Setting ◽  
The Right

AbstractWorking memory and episodic memory are two different processes, although the nature of their interrelationship is debated. As these processes are predominantly studied in isolation, it is unclear whether they crucially rely on different neural substrates. To obtain more insight in this, 81 adults with sub-acute ischemic stroke and 29 elderly controls were assessed on a visual working memory task, followed by a surprise subsequent memory test for the same stimuli. Multivariate, atlas- and track-based lesion-symptom mapping (LSM) analyses were performed to identify anatomical correlates of visual memory. Behavioral results gave moderate evidence for independence between discriminability in working memory and subsequent memory, and strong evidence for a correlation in response bias on the two tasks in stroke patients. LSM analyses suggested there might be independent regions associated with working memory and episodic memory. Lesions in the right arcuate fasciculus were more strongly associated with discriminability in working memory than in subsequent memory, while lesions in the frontal operculum in the right hemisphere were more strongly associated with criterion setting in subsequent memory. These findings support the view that some processes involved in working memory and episodic memory rely on separate mechanisms, while acknowledging that there might also be shared processes.

Challenging the Recognition of Facial Expression via Deep Learning

2014 ◽  
Vol 571-572 ◽  
pp. 717-720
Author(s):  
De Kun Hu ◽  
Yong Hong Liu ◽  
Li Zhang ◽  
Gui Duo Duan
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Back Propagation ◽  
Stochastic Gradient Descent ◽  
Excellent Performance ◽  
Proposed Model ◽  
Input Layer ◽  
Fully Connected

A deep Neural Network model was trained to classify the facial expression in unconstrained images, which comprises nine layers, including input layer, convolutional layer, pooling layer, fully connected layers and output layer. In order to optimize the model, rectified linear units for the nonlinear transformation, weights sharing for reducing the complexity, “mean” and “max” pooling for subsample, “dropout” for sparsity are applied in the forward processing. With large amounts of hard training faces, the model was trained via back propagation method with stochastic gradient descent. The results of shows the proposed model achieves excellent performance.

scholarly journals Traces of semantization - from episodic to semantic memory in a spiking cortical network model

2021 ◽  
Author(s):  
Nikolaos Chrysanthidis ◽  
Florian Fiebig ◽  
Anders Lansner ◽  
Pawel Herman
Keyword(s):  
Neural Network ◽  
Episodic Memory ◽  
Semantic Memory ◽  
Network Model ◽  
Hebbian Learning ◽  
Contextual Information ◽  
Memory Task ◽  
Learning Rule ◽  
Mechanistic Explanation ◽  
Spike Timing

Episodic memory is the recollection of past personal experiences associated with particular times and places. This kind of memory is commonly subject to loss of contextual information or "semantization", which gradually decouples the encoded memory items from their associated contexts while transforming them into semantic or gist-like representations. Novel extensions to the classical Remember/Know behavioral paradigm attribute the loss of episodicity to multiple exposures of an item in different contexts. Despite recent advancements explaining semantization at a behavioral level, the underlying neural mechanisms remain poorly understood. In this study, we suggest and evaluate a novel hypothesis proposing that Bayesian-Hebbian synaptic plasticity mechanisms might cause semantization of episodic memory. We implement a cortical spiking neural network model with a Bayesian-Hebbian learning rule called Bayesian Confidence Propagation Neural Network (BCPNN), which captures the semantization phenomenon and offers a mechanistic explanation for it. Encoding items across multiple contexts leads to item-context decoupling akin to semantization. We compare BCPNN plasticity with the more commonly used spike-timing dependent plasticity (STDP) learning rule in the same episodic memory task. Unlike BCPNN, STDP does not explain the decontextualization process. We also examine how selective plasticity modulation of isolated salient events may enhance preferential retention and resistance to semantization. Our model reproduces important features of episodicity on behavioral timescales under various biological constraints whilst also offering a novel neural and synaptic explanation for semantization, thereby casting new light on the interplay between episodic and semantic memory processes.

scholarly journals Partial Label Learning Based on Fully Connected Deep Neural Network

2022 ◽  
Vol 16 ◽  
pp. 287-297
Author(s):  
Houjie Li ◽  
Lei Wu ◽  
Jianjun He ◽  
Ruirui Zheng ◽  
Yu Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Process Model ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Ground Truth ◽  
Training Sample ◽  
Support Vector ◽  
Partial Label Learning ◽  
Fully Connected

The ambiguity of training samples in the partial label learning framework makes it difficult for us to develop learning algorithms and most of the existing algorithms are proposed based on the traditional shallow machine learn- ing models, such as decision tree, support vector machine, and Gaussian process model. Deep neu- ral networks have demonstrated excellent perfor- mance in many application fields, but currently it is rarely used for partial label learning frame- work. This study proposes a new partial label learning algorithm based on a fully connected deep neural network, in which the relationship between the candidate labels and the ground- truth label of each training sample is established by defining three new loss functions, and a regu- larization term is added to prevent overfitting. The experimental results on the controlled U- CI datasets and real-world partial label datasets reveal that the proposed algorithm can achieve higher classification accuracy than the state-of- the-art partial label learning algorithms.

scholarly journals Extradural Motor Cortex Stimulation might improve episodic and working memory in patients with Parkinson’s disease

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Carla Piano ◽  
Marco Ciavarro ◽  
Francesco Bove ◽  
Daniela Di Giuda ◽  
Fabrizio Cocciolillo ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Working Memory ◽  
Parkinson's Disease ◽  
Motor Cortex ◽  
Episodic Memory ◽  
Memory Task ◽  
Motor Symptoms ◽  
Motor Cortex Stimulation ◽  
Short Term ◽  
Verbal Episodic Memory

Abstract Electric Extradural Motor Cortex Stimulation (EMCS) is a neurosurgical procedure suggested for treatment of patients with advanced Parkinson’s disease (PD). We report two PD patients treated by EMCS, who experienced worsening of motor symptoms and cognition 5 years after surgery, when EMCS batteries became discharged. One month after EMCS restoration, they experienced a subjective improvement of motor symptoms and cognition. Neuropsychological assessments were carried out before replacement of batteries (off-EMCS condition) and 6 months afterward (on-EMCS condition). As compared to off-EMCS condition, in on-EMCS condition both patients showed an improvement on tasks of verbal episodic memory and backward spatial short-term/working memory task, and a decline on tasks of selective visual attention and forward spatial short-term memory. These findings suggest that in PD patients EMCS may induce slight beneficial effects on motor symptoms and cognitive processes involved in verbal episodic memory and in active manipulation of information stored in working memory.

A Parametric Level Set Method for Topology Optimization based on Deep Neural Network (DNN)

2021 ◽  
pp. 1-14
Author(s):  
Hao Deng ◽  
Albert C. To
Keyword(s):  
Neural Network ◽  
Topology Optimization ◽  
Differential Equations ◽  
Level Set Method ◽  
Level Set ◽  
Deep Neural Network ◽  
Implicit Function ◽  
Zero Level ◽  
Fully Connected ◽  
Parametric Level Set Method

Abstract This paper proposes a new parametric level set method for topology optimization based on Deep Neural Network (DNN). In this method, the fully connected deep neural network is incorporated into the conventional level set methods to construct an effective approach for structural topology optimization. The implicit function of level set is described by fully connected deep neural networks. A DNN-based level set optimization method is proposed, where the Hamilton-Jacobi partial differential equations (PDEs) are transformed into parametrized ordinary differential equations (ODEs). The zero-level set of implicit function is updated through updating the weights and biases of networks. The parametrized reinitialization is applied periodically to prevent the implicit function from being too steep or too flat in the vicinity of its zero-level set. The proposed method is implemented in the framework of minimum compliance, which is a well-known benchmark for topology optimization. In practice, designers desire to have multiple design options, where they can choose a better conceptual design base on their design experience. One of the major advantages of DNN-based level set method is capable to generate diverse and competitive designs with different network architectures. Several numerical examples are presented to verify the effectiveness of proposed DNN-based level set method.

Sign in / Sign up

Export Citation Format

Share Document