scholarly journals A modeling framework for adaptive lifelong learning with transfer and savings through gating in the prefrontal cortex

2020 ◽  
Vol 117 (47) ◽  
pp. 29872-29882
Author(s):  
Ben Tsuda ◽  
Kay M. Tye ◽  
Hava T. Siegelmann ◽  
Terrence J. Sejnowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prefrontal Cortex ◽  
Reinforcement Learning ◽  
Modeling Framework ◽  
Simple Neural Network ◽  
Neuropsychological Impairments ◽  
And Storage ◽  
The Brain

The prefrontal cortex encodes and stores numerous, often disparate, schemas and flexibly switches between them. Recent research on artificial neural networks trained by reinforcement learning has made it possible to model fundamental processes underlying schema encoding and storage. Yet how the brain is able to create new schemas while preserving and utilizing old schemas remains unclear. Here we propose a simple neural network framework that incorporates hierarchical gating to model the prefrontal cortex’s ability to flexibly encode and use multiple disparate schemas. We show how gating naturally leads to transfer learning and robust memory savings. We then show how neuropsychological impairments observed in patients with prefrontal damage are mimicked by lesions of our network. Our architecture, which we call DynaMoE, provides a fundamental framework for how the prefrontal cortex may handle the abundance of schemas necessary to navigate the real world.

scholarly journals A modeling framework for adaptive lifelong learning with transfer and savings through gating in the prefrontal cortex

2020 ◽  
Author(s):  
Ben Tsuda ◽  
Kay M. Tye ◽  
Hava T. Siegelmann ◽  
Terrence J. Sejnowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prefrontal Cortex ◽  
Reinforcement Learning ◽  
Mixture Of Experts ◽  
Modeling Framework ◽  
Simple Neural Network ◽  
And Storage ◽  
The Brain

AbstractThe prefrontal cortex encodes and stores numerous, often disparate, schemas and flexibly switches between them. Recent research on artificial neural networks trained by reinforcement learning has made it possible to model fundamental processes underlying schema encoding and storage. Yet how the brain is able to create new schemas while preserving and utilizing old schemas remains unclear. Here we propose a simple neural network framework based on a modification of the mixture of experts architecture to model the prefrontal cortex’s ability to flexibly encode and use multiple disparate schemas. We show how incorporation of gating naturally leads to transfer learning and robust memory savings. We then show how phenotypic impairments observed in patients with prefrontal damage are mimicked by lesions of our network. Our architecture, which we call DynaMoE, provides a fundamental framework for how the prefrontal cortex may handle the abundance of schemas necessary to navigate the real world.

scholarly journals Generalization of Patterns by Identification with Polynomial Neural Network

2010 ◽  
Vol 61 (2) ◽  
pp. 120-124 ◽  
Author(s):  
Ladislav Zjavka
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Functional Dependence ◽  
Polynomial Neural Network ◽  
New Type ◽  
Input Variables ◽  
The Brain ◽  
Functional Output ◽  
Simplified Form

Generalization of Patterns by Identification with Polynomial Neural Network Artificial neural networks (ANN) in general classify patterns according to their relationship, they are responding to related patterns with a similar output. Polynomial neural networks (PNN) are capable of organizing themselves in response to some features (relations) of the data. Polynomial neural network for dependence of variables identification (D-PNN) describes a functional dependence of input variables (not entire patterns). It approximates a hyper-surface of this function with multi-parametric particular polynomials forming its functional output as a generalization of input patterns. This new type of neural network is based on GMDH polynomial neural network and was designed by author. D-PNN operates in a way closer to the brain learning as the ANN does. The ANN is in principle a simplified form of the PNN, where the combinations of input variables are missing.

scholarly journals A Study of Connectionism Theory

2020 ◽  
Vol 3 (3) ◽  
pp. 2335-2342
Author(s):  
Shahryar Banan ◽  
Muhammad Ridwan ◽  
Abdurahman Adisaputera
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Computational Neuroscience ◽  
Paradigm Shift ◽  
Interconnection Network ◽  
Mental Abilities ◽  
Artificial Neural ◽  
The Brain

The development of connectionism represents a paradigm shift in science. Connectionism has its root in cognitive and computational neuroscience. Likening the brain to a computer, connectionism tries to describe human mental abilities in terms of artificial neural networks. A neural network consists of a large number of nodes and units which are joined together to form an interconnection network. Within these interconnections, knowledge is distributed. Therefore learning is a processing by-product. This article is about the concept of connectionism, what it accounts for and what it doesn't take into account.  Finally, different approaches to connectionism are discussed.

scholarly journals Neural Networks—Deflection Prediction of Continuous Beams with GFRP Reinforcement

2021 ◽  
Vol 11 (8) ◽  
pp. 3429
Author(s):  
Željka Beljkaš ◽  
Nikola Baša
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Experimental Research ◽  
Fiber Reinforced Polymer ◽  
Glass Fiber Reinforced Polymer ◽  
Reinforced Polymer ◽  
Continuous Beams ◽  
Glass Fiber Reinforced ◽  
Gfrp Reinforcement

Deflections on continuous beams with glass fiber-reinforced polymer (GFRP) reinforcement are calculated in accordance with the appropriate standards (ACI 440.1R-15, CSA S806-12). However, experimental research provides results which differ from the values calculated pursuant to the standards, particularly when it comes to continuous beams. Machine learning methods can be applied for predicting a deflection level on continuous beams with GFRP (glass fiber-reinforced polymer) reinforcement and loaded with a concentrated load. This paper presents research on using artificial neural networks for deflection estimation and an optimal prediction model choice. It was necessary to first develop a database, in order to train the neural network. The database was formed based on the results of the experimental research on continuous beams with GFRP reinforcement. Using the best trained neural network model, high accuracy was obtained in estimating deflection, expressed over the mean absolute percentage error, 9.0%. This result indicates a high level of reliability in the prediction of deflection with the help of artificial neural networks.

Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning

2021 ◽  
Vol 2 (1) ◽  
pp. 1-25
Author(s):  
Yongsen Ma ◽  
Sheheryar Arshad ◽  
Swetha Muniraju ◽  
Eric Torkildson ◽  
Enrico Rantala ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Activity Recognition ◽  
Deep Neural Networks ◽  
State Machine ◽  
Recognition Algorithm ◽  
The State ◽  
Neural Architecture ◽  
Learning Agent

In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.

scholarly journals The Budapest Amyloid Predictor and Its Applications

Biomolecules ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 500
Author(s):  
László Keresztes ◽  
Evelin Szögi ◽  
Bálint Varga ◽  
Viktor Farkas ◽  
András Perczel ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Support Vector ◽  
User Needs ◽  
Computational Technique ◽  
Linear Support Vector Machine ◽  
Β Sheets ◽  
Artificial Neural ◽  
Amorphous Aggregation

The amyloid state of proteins is widely studied with relevance to neurology, biochemistry, and biotechnology. In contrast with nearly amorphous aggregation, the amyloid state has a well-defined structure, consisting of parallel and antiparallel β-sheets in a periodically repeated formation. The understanding of the amyloid state is growing with the development of novel molecular imaging tools, like cryogenic electron microscopy. Sequence-based amyloid predictors were developed, mainly using artificial neural networks (ANNs) as the underlying computational technique. From a good neural-network-based predictor, it is a very difficult task to identify the attributes of the input amino acid sequence, which imply the decision of the network. Here, we present a linear Support Vector Machine (SVM)-based predictor for hexapeptides with correctness higher than 84%, i.e., it is at least as good as the best published ANN-based tools. Unlike artificial neural networks, the decisions of the linear SVMs are much easier to analyze and, from a good predictor, we can infer rich biochemical knowledge. In the Budapest Amyloid Predictor webserver the user needs to input a hexapeptide, and the server outputs a prediction for the input plus the 6 × 19 = 114 distance-1 neighbors of the input hexapeptide.

scholarly journals Non-Destructive Micromagnetic Determination of Hardness and Case Hardening Depth Using Linear Regression Analysis and Artificial Neural Networks

Metals ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 18
Author(s):  
Rahel Jedamski ◽  
Jérémy Epp
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Regression Analysis ◽  
Artificial Neural Networks ◽  
Linear Regression ◽  
Linear Regression Analysis ◽  
Case Hardening ◽  
Artificial Neural ◽  
Non Destructive

Non-destructive determination of workpiece properties after heat treatment is of great interest in the context of quality control in production but also for prevention of damage in subsequent grinding process. Micromagnetic methods offer good possibilities, but must first be calibrated with reference analyses on known states. This work compares the accuracy and reliability of different calibration methods for non-destructive evaluation of carburizing depth and surface hardness of carburized steel. Linear regression analysis is used in comparison with new methods based on artificial neural networks. The comparison shows a slight advantage of neural network method and potential for further optimization of both approaches. The quality of the results can be influenced, among others, by the number of teaching steps for the neural network, whereas more teaching steps does not always lead to an improvement of accuracy for conditions not included in the initial calibration.

scholarly journals Optimal Artificial Neural Network Type Selection Method for Usage in Smart House Systems

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 47
Author(s):  
Vasyl Teslyuk ◽  
Artem Kazarian ◽  
Natalia Kryvinska ◽  
Ivan Tsmots
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Optimization Criterion ◽  
Fuzzy Input ◽  
Different Types ◽  
Smart House ◽  
Artificial Neural

In the process of the “smart” house systems work, there is a need to process fuzzy input data. The models based on the artificial neural networks are used to process fuzzy input data from the sensors. However, each artificial neural network has a certain advantage and, with a different accuracy, allows one to process different types of data and generate control signals. To solve this problem, a method of choosing the optimal type of artificial neural network has been proposed. It is based on solving an optimization problem, where the optimization criterion is an error of a certain type of artificial neural network determined to control the corresponding subsystem of a “smart” house. In the process of learning different types of artificial neural networks, the same historical input data are used. The research presents the dependencies between the types of neural networks, the number of inner layers of the artificial neural network, the number of neurons on each inner layer, the error of the settings parameters calculation of the relative expected results.

scholarly journals Nonlinear Time-Series Analysis of Pulsation of Post-AGB Stars by Genetic Algorithm/Neural Network Hybrid Systems

2000 ◽  
Vol 176 ◽  
pp. 135-136
Author(s):  
Toshiki Aikawa
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Hybrid System ◽  
Nonlinear Time Series ◽  
Photometric Data ◽  
Nonlinear Time Series Analysis ◽  
Agb Stars

AbstractSome pulsating post-AGB stars have been observed with an Automatic Photometry Telescope (APT) and a considerable amount of precise photometric data has been accumulated for these stars. The datasets, however, are still sparse, and this is a problem for applying nonlinear time series: for instance, modeling of attractors by the artificial neural networks (NN) to the datasets. We propose the optimization of data interpolations with the genetic algorithm (GA) and the hybrid system combined with NN. We apply this system to the Mackey–Glass equation, and attempt an analysis of the photometric data of post-AGB variables.

Sign in / Sign up

Export Citation Format

Share Document