scholarly journals Image and pattern reconstruction using differentiable plasticity

2022 ◽  
Vol 2161 (1) ◽  
pp. 012009
Author(s):  
Jigalur Priyanka ◽  
B G Prasad
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Network Size ◽  
Simple Method ◽  
New Techniques ◽  
New Approach ◽  
Network Connection ◽  
Novel Approach ◽  
Approaches To Study ◽  
The Brain

Abstract The brain is a substantial boon to humankind that adapts nature accordingly. The brain can learn and unlearn based on the situation. This singularity of human learning led to the research creating models using Artificial Intelligence (AI) to incorporate the brain’s behavior. The investigation opened up many new approaches to study AI with neural networks by adding new techniques to imitate the human brain’s functionalities. Many models can learn from experience like Recurrent Neural Network(RNN’s), Long Short Term Memory (LSTM) with the fixed network size. This paper describes the simple method of creating the model which will behave similar to the biological brain and recreates its differentiable plasticity to adopt the features of neural network connection. It also shows that applying plasticity and the Hebbian plastic connection rule can result in optimization in RNN. This new approach of reconstruction of images based on plastic neural network experiments shows that the above novel approach gives more optimized results than the traditionally used RNN techniques. In this paper, a proposal is made where models can memorize and reconstruct unseen sets of images by solving recurrent networks using plasticity rules.

scholarly journals Nearly Extensive Sequential Memory Lifetime Achieved by Coupled Nonlinear Neurons

2012 ◽  
Vol 24 (10) ◽  
pp. 2678-2699 ◽  
Author(s):  
Taro Toyoizumi
Keyword(s):  
Cognitive Processes ◽  
Neural Activity ◽  
Short Term Memory ◽  
Memory Performance ◽  
Linear Part ◽  
Network Size ◽  
Short Term ◽  
Time Step ◽  
Sequential Memory ◽  
The Brain

Many cognitive processes rely on the ability of the brain to hold sequences of events in short-term memory. Recent studies have revealed that such memory can be read out from the transient dynamics of a network of neurons. However, the memory performance of such a network in buffering past information has been rigorously estimated only in networks of linear neurons. When signal gain is kept low, so that neurons operate primarily in the linear part of their response nonlinearity, the memory lifetime is bounded by the square root of the network size. In this work, I demonstrate that it is possible to achieve a memory lifetime almost proportional to the network size, “an extensive memory lifetime,” when the nonlinearity of neurons is appropriately used. The analysis of neural activity revealed that nonlinear dynamics prevented the accumulation of noise by partially removing noise in each time step. With this error-correcting mechanism, I demonstrate that a memory lifetime of order [Formula: see text] can be achieved.

scholarly journals Toward Smart Lockdown: A Novel Approach for COVID-19 Hotspots Prediction Using a Deep Hybrid Neural Network

Computers ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 99
Author(s):  
Sultan Daud Khan ◽  
Louai Alarabi ◽  
Saleh Basalamah
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Time Scale ◽  
Prediction Models ◽  
Time Series Data ◽  
Short Term Memory ◽  
Economic Recession ◽  
Series Data ◽  
Economic Activities ◽  
Novel Approach

COVID-19 caused the largest economic recession in the history by placing more than one third of world’s population in lockdown. The prolonged restrictions on economic and business activities caused huge economic turmoil that significantly affected the financial markets. To ease the growing pressure on the economy, scientists proposed intermittent lockdowns commonly known as “smart lockdowns”. Under smart lockdown, areas that contain infected clusters of population, namely hotspots, are placed on lockdown, while economic activities are allowed to operate in un-infected areas. In this study, we proposed a novel deep learning prediction framework for the accurate prediction of hotpots. We exploit the benefits of two deep learning models, i.e., Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) and propose a hybrid framework that has the ability to extract multi time-scale features from convolutional layers of CNN. The multi time-scale features are then concatenated and provide as input to 2-layers LSTM model. The LSTM model identifies short, medium and long-term dependencies by learning the representation of time-series data. We perform a series of experiments and compare the proposed framework with other state-of-the-art statistical and machine learning based prediction models. From the experimental results, we demonstrate that the proposed framework beats other existing methods with a clear margin.

scholarly journals Kinematics approach with neural networks for early detection of sepsis (KANNEDS)

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Márcio Freire Cruz ◽  
Naoaki Ono ◽  
Ming Huang ◽  
Md. Altaf-Ul-Amin ◽  
Shigehiko Kanaya ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Early Detection ◽  
Short Term Memory ◽  
Dimensional Space ◽  
Vital Signs ◽  
Accurate Method ◽  
Severe Illness ◽  
Explanatory Variables ◽  
Novel Approach

Abstract Background Sepsis is a severe illness that affects millions of people worldwide, and its early detection is critical for effective treatment outcomes. In recent years, researchers have used models to classify positive patients or identify the probability for sepsis using vital signs and other time-series variables as input. Methods In our study, we analyzed patients’ conditions by their kinematics position, velocity, and acceleration, in a six-dimensional space defined by six vital signs. The patient is affected by the disease after a period if the position gets “near” to a calculated sepsis position in space. We imputed these kinematics features as explanatory variables of long short-term memory (LSTM), convolutional neural network (CNN) and linear neural network (LNN) and compared the prediction accuracies with only the vital signs as input. The dataset used contained information of approximately 4800 patients, each with 48 hourly registers. Results We demonstrated that the kinematics features models had an improved performance compared with vital signs models. The kinematics features model of LSTM achieved the best accuracy, 0.803, which was nine points higher than the vital signs model. Although with lesser accuracies, the kinematics features models of the CNN and LNN showed better performances than vital signs models. Conclusion Applying our novel approach for early detection of sepsis using neural networks will prove to be an invaluable, more accurate method than considering only simple vital signs as input variables. We expect that other researchers with similar objectives can use the model presented in this innovative approach to improve their results.

scholarly journals Designing a long short-term network for short-term forecasting of global horizontal irradiance

2021 ◽  
Vol 3 (4) ◽  
Author(s):  
Sourav Malakar ◽  
Saptarsi Goswami ◽  
Bhaswati Ganguli ◽  
Amlan Chakrabarti ◽  
Sugata Sen Roy ◽  
...  
Keyword(s):  
Neural Network ◽  
Solar Energy ◽  
Input Data ◽  
Short Term Memory ◽  
Network Size ◽  
Batch Size ◽  
Short Term ◽  
Climatic Zones ◽  
Lstm Network ◽  
Short Term Forecasting

AbstractLong short-term memory (LSTM) models based on specialized deep neural network-based architecture have emerged as an important model for forecasting time-series. However, the literature does not provide clear guidelines for design choices, which affect forecasting performance. Such choices include the need for pre-processing techniques such as deseasonalization, ordering of the input data, network size, batch size, and forecasting horizon. We detail this in the context of short-term forecasting of global horizontal irradiance, an accepted proxy for solar energy. Particularly, short-term forecasting is critical because the cloud conditions change at a sub-hourly having large impacts on incident solar radiation. We conduct an empirical investigation based on data from three solar stations from two climatic zones of India over two seasons. From an application perspective, it may be noted that despite the thrust given to solar energy generation in India, the literature contains few instances of robust studies across climatic zones and seasons. The model thus obtained subsequently outperformed three recent benchmark methods based on random forest, recurrent neural network, and LSTM, respectively, in terms of forecasting accuracy. Our findings underscore the importance of considering the temporal order of the data, lack of any discernible benefit from data pre-processing, the effect of making the LSTM model stateful. It is also found that the number of nodes in an LSTM network, as well as batch size, is influenced by the variability of the input data.

scholarly journals Application of a Convolutional Neural Network for the Detection of Sea Ice Leads

2021 ◽  
Vol 13 (22) ◽  
pp. 4571
Author(s):  
Jay P. Hoffman ◽  
Steven A. Ackerman ◽  
Yinghui Liu ◽  
Jeffrey R. Key ◽  
Iain L. McConnell
Keyword(s):  
Neural Network ◽  
Sea Ice ◽  
Convolutional Neural Network ◽  
Infrared Imaging ◽  
Critical Role ◽  
The Arctic ◽  
Detection Accuracy ◽  
New Approach ◽  
Novel Approach ◽  
Ice Leads

Despite accounting for a small fraction of the surface area in the Arctic, long and narrow sea ice fractures, known as “leads”, play a critical role in the energy flux between the ocean and atmosphere. As the volume of sea ice in the Arctic has declined over the past few decades, it is increasingly important to monitor the corresponding changes in sea ice leads. A novel approach has been developed using artificial intelligence (AI) to detect sea ice leads using satellite thermal infrared window data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS). In this new approach, a particular type of convolutional neural network, a U-Net, replaces a series of conventional image processing tests from our legacy algorithm. Results show the new approach has a high detection accuracy with F1 Scores on the order of 0.7. Compared to the legacy algorithm, the new algorithm shows improvement, with more true positives, fewer false positives, fewer false negatives, and better agreement between satellite instruments.

scholarly journals Neuro-wavelet Model for price prediction in high-frequency data in the Mexican Stock market

2021 ◽  
Vol 17 (1) ◽  
pp. 1-23
Author(s):  
Ricardo Massa Roldán ◽  
Montserrat Reyna Miranda ◽  
Vicente Gómez Salcido
Keyword(s):  
Neural Network ◽  
High Frequency ◽  
Short Term Memory ◽  
Arima Model ◽  
High Frequency Data ◽  
Frequency Data ◽  
New Techniques ◽  
Market Participants ◽  
Price Prediction ◽  
Technical Capacity

With the availability of high frequency data and new techniques for the management of noise in signals, we revisit the question, can we predict financial asset prices? The present work proposes an algorithm for next-step log-return prediction. Data in frequencies from 1 to 15 minutes, for 25 high capitalization assets in the Mexican market were used. The model applied consists on a wavelet followed by a Long Short-Term Memory neural network (LSTM). Application of either wavelets or neural networks in finance are common, the novelty comes from the application of the particular architecture proposed. The results show that, on average, the proposed LSTM neuro-wavelet model outperforms both an ARIMA model and a benchmark dense neural network model. We conclude that, although further research (in other stock markets, at higher frequencies, etc.) is in order, given the ever increasing technical capacity of market participants, the inclusion of the LSTM neuro-wavelet model is a valuable addition to the market participant toolkit, and might pose an advantage to traditional predictive tools.

scholarly journals Reconstruction of Process Forces in a Five-Axis Milling Center with a LSTM Neural Network in Comparison to a Model-Based Approach

2020 ◽  
Vol 4 (3) ◽  
pp. 62 ◽  
Author(s):  
Berend Denkena ◽  
Benjamin Bergmann ◽  
Dennis Stoppel
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Training Data ◽  
Motion Direction ◽  
Model Based ◽  
Process Forces ◽  
Novel Approach ◽  
The Neural Network ◽  
Drive Signals ◽  
Five Axis

Based on the drive signals of a milling center, process forces can be reconstructed. Therefore, a novel approach is presented to reconstruct the process forces with a long short-term memory neural network (LSTM) using drive signals as an input. The LSTM is evaluated and compared to a model-based approach. The latter compensates nonlinearities and disturbances such as friction and inertia. For training of the LSTM, multiple milling processes are considered to enhance the generalizability. Training data is generated by recording drive signals and process forces measured by a dynamometer. The LSTM is then evaluated using a test set, which comprises new process parameters. It is shown that the LSTM has a lower root mean square error (RMSE) in comparison to the model-based approach. Especially, when changing the feed motion direction during milling, the neural network clearly outperforms the model-based approach. Nevertheless, there are processes, where the LSTM induced oscillations, which do not correspond to the measured forces.

scholarly journals A Novel Approach for Detection of Fake News using Long Short Term Memory (LSTM)

2021 ◽  
Vol 10 (5) ◽  
pp. 3062-3066
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Text Mining ◽  
Short Term Memory ◽  
Online Media ◽  
Fake News ◽  
Short Term ◽  
Term Memory ◽  
Novel Approach ◽  
Long Short Term Memory

Online media for news consumption has doubtful advantages. From one perspective, it has minimal expense, simple access, and fast dispersal of data which leads individuals to search out and devour news from online media. On the other hand, it increases the wide spread of "counterfeit news", i.e., inferior quality news with purposefully bogus data. The broad spread of fake news contrarily affects people and society. Hence, fake news detection in social media has become an emerging research topic that is drawing attention from various researchers. In past, many creators proposed the utilization of text mining procedures and AI strategies to examine textual data and helps to foresee the believability of news. With more computational capacities and to deal with enormous datasets, deep learning models present a better presentation over customary text mining strategies and AI methods. Normally deep learning model, for example, LSTM model can identify complex patterns in the data. Long short term memory is a tree organized recurrent neural network (RNN) used to examine variable length sequential information. In our proposed framework we set up a fake news identification model dependent on LSTM neural network. Openly accessible unstructured news datasets are utilized to evaluate the exhibition of the model. The outcome shows the prevalence and exactness of LSTM model over the customary techniques specifically CNN for fake news recognition.

Using a recurrent neural network with S2 characteristics, efficient identification of localised cortical dysplasia

2021 ◽  
pp. 1-14
Author(s):  
A. Karthika ◽  
R. Subramanian ◽  
S. Karthik
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Short Term Memory ◽  
Focal Cortical Dysplasia ◽  
Cortical Dysplasia ◽  
Support Vector ◽  
Sensitivity Rate ◽  
Long Short Term Memory ◽  
Artificial Neural Network Ann ◽  
The Brain

Focal cortical dysplasia (FCD) is an inborn anomaly in brain growth and morphological deformation in lesions of the brain which induces focal seizures. Neurosurgical therapies were performed for the detection of FCD. Furthermore, it can be overcome through the presurgical evaluation of epilepsy. The surgical result is attained basically through the output of the presurgical output. In preprocessing the process of increasing true positives with the decrease in false negatives occurs which results in an effective outcome. MRI (Magnetic Resonance Imaging) outputs are efficient to predict the FCD lesions through T1- MPRAGE and T2- FLAIR efficient output can be obtained. In our proposed work we extract the S2 features through the testing of T1, T2 images. Using RNN-LSTM (Recurrent neural network-Long short-term memory) test images were trained and the FCD lesions were segmented. The output of our work is compared with the proposed work yields better results compared to the existing system such as artificial neural network (ANN), support vector machine (SVM), and convolution neural network (CNN). This approach obtained an accuracy rate of 0.195% (ANN), 0.20% (SVM), 0.14% (CNN), specificity rate of 0.23% (ANN), 0.15% (SVM), 0.13% (CNN) and sensitivity rate of 0.22% (ANN), 0.14% (SVM), 0.08% (CNN) respectively in comparison with RNN-LSTM.

scholarly journals Complementary topology of maintenance and manipulation brain networks in working memory

2018 ◽  
Author(s):  
S.W. Davis ◽  
C.A. Crowell ◽  
L. Beynel ◽  
L. Deng ◽  
D. Lakhlani ◽  
...  
Keyword(s):  
Working Memory ◽  
Parietal Cortex ◽  
Cognitive Functions ◽  
Short Term Memory ◽  
Brain Activity ◽  
Real Life ◽  
Protective Mechanism ◽  
Alphabetical Order ◽  
Novel Approach ◽  
The Brain

AbstractWorking memory (WM) is assumed to consist of a process that sustains memory representations in an active state (maintenance) and a process that operates on these activated representations (manipulation). Prior fMRI studies have examined maintenance and manipulation in separate task conditions, whereas in real life these processes operate simultaneously. In the current study, the neural mechanisms of maintenance and manipulation were disentangled during the same task by parametrically varying these processes. During fMRI, participants maintained consonant letters in WM while sorting them in alphabetical order. Maintenance was investigated by varying the number of letters held in WM and manipulation by varying the number of moves required to sort the list alphabetically. The study yielded three main findings. First, the degree of both maintenance and manipulation demand had significant effects on behavior that were associated with different cortical regions: maintenance was associated with bilateral prefrontal and left parietal cortex, and manipulation with right parietal activity, a link that is consistent with the role of parietal cortex in symbolic computations. Second, univariate fMRI and tractography based on diffusion-weighted imaging showed that maintenance and manipulation regions are supported by two dissociable structural networks. Finally, maintenance and manipulation functional networks became increasingly segregated with increasing demand, possibly reflecting the protection of information held in WM from interference generated by manipulation operations. These results represent a novel approach to study the brain as an adaptive system that coordinates multiple ongoing cognitive processes.Significance StatementDespite the importance of working memory (WM) in everyday life, little is known about how the brain is able to simultaneously maintain and manipulate information stored in short-term memory buffers. We examined evidence for two distinct, concurrent cognitive functions supporting maintenance and manipulation abilities by testing brain activity as participants performed a WM alphabetization task. We found behavioral and neural evidence in support of dissociable cognitive functions associated with these two operations. Furthermore, we found that connectivity between these networks was increasingly segregated as difficulty increased, and that this effect was positively related to individual WM ability. These results provide evidence that network segregation may act as a protective mechanism to enable successful performance under increasing WM demand.

Sign in / Sign up

Export Citation Format

Share Document