scholarly journals Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation

2021 ◽  
Vol 11 (22) ◽  
pp. 10786
Author(s):  
Kyuchang Kang ◽  
Changseok Bae
Keyword(s):  
Neural Networks ◽  
Visual Stimuli ◽  
Training Data ◽  
Memory Model ◽  
Distributed Representation ◽  
Data Sets ◽  
Memory Process ◽  
Practical Applications ◽  
Proposed Model ◽  
Continual Learning

Recent achievements on CNN (convolutional neural networks) and DNN (deep neural networks) researches provide a lot of practical applications on computer vision area. However, these approaches require construction of huge size of training data for learning process. This paper tries to find a way for continual learning which does not require prior high-cost training data construction by imitating a biological memory model. We employ SDR (sparse distributed representation) for information processing and semantic memory model, which is known as a representation model of firing patterns on neurons in neocortex area. This paper proposes a novel memory model to reflect remembrance of morphological semantics of visual input stimuli. The proposed memory model considers both memory process and recall process separately. First, memory process converts input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST (Modified National Institute of Standards and Technology) and Fashion-MNIST data sets show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli.

scholarly journals Generalization-Based Acquisition of Training Data for Motor Primitive Learning by Neural Networks

2021 ◽  
Vol 11 (3) ◽  
pp. 1013
Author(s):  
Zvezdan Lončarević ◽  
Rok Pahič ◽  
Aleš Ude ◽  
Andrej Gams
Keyword(s):  
Neural Networks ◽  
Dimensionality Reduction ◽  
Gaussian Process Regression ◽  
Search Space ◽  
Robot Learning ◽  
Training Data ◽  
Practical Applications ◽  
Latent Space ◽  
Real Robot ◽  
Low Dimensional

Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of these techniques require the availability of a sufficiently large database of example task executions to compute the latent space. However, the generation of many example task executions on a real robot is tedious, and prone to errors and equipment failures. The main result of this paper is a new approach for efficient database gathering by performing a small number of task executions with a real robot and applying statistical generalization, e.g., Gaussian process regression, to generate more data. We have shown in our experiments that the data generated this way can be used for dimensionality reduction with autoencoder neural networks. The resulting latent spaces can be exploited to implement robot learning more efficiently. The proposed approach has been evaluated on the problem of robotic throwing at a target. Simulation and real-world results with a humanoid robot TALOS are provided. They confirm the effectiveness of generalization-based database acquisition and the efficiency of learning in a low-dimensional latent space.

scholarly journals A Novel Active Contours Model for Environmental Change Detection from Multitemporal Synthetic Aperture Radar Images

2020 ◽  
Vol 12 (11) ◽  
pp. 1746
Author(s):  
Salman Ahmadi ◽  
Saeid Homayouni
Keyword(s):  
Synthetic Aperture Radar ◽  
Change Detection ◽  
Active Contours ◽  
Training Data ◽  
Synthetic Aperture ◽  
Data Sets ◽  
Difference Image ◽  
Proposed Model ◽  
The Difference ◽  
Aperture Radar

In this paper, we propose a novel approach based on the active contours model for change detection from synthetic aperture radar (SAR) images. In order to increase the accuracy of the proposed approach, a new operator was introduced to generate a difference image from the before and after change images. Then, a new model of active contours was developed for accurately detecting changed regions from the difference image. The proposed model extracts the changed areas as a target feature from the difference image based on training data from changed and unchanged regions. In this research, we used the Otsu histogram thresholding method to produce the training data automatically. In addition, the training data were updated in the process of minimizing the energy function of the model. To evaluate the accuracy of the model, we applied the proposed method to three benchmark SAR data sets. The proposed model obtains 84.65%, 87.07%, and 96.26% of the Kappa coefficient for Yellow River Estuary, Bern, and Ottawa sample data sets, respectively. These results demonstrated the effectiveness of the proposed approach compared to other methods. Another advantage of the proposed model is its high speed in comparison to the conventional methods.

Simple Convolutional-Based Models: Are They Learning the Task or the Data?

2021 ◽  
pp. 1-17
Author(s):  
Luis Sa-Couto ◽  
Andreas Wichert
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Training Data ◽  
Model Complexity ◽  
Data Sets ◽  
Simple Task ◽  
Data Set ◽  
Knowing That ◽  
Handwritten Digit ◽  
End To End

Abstract Convolutional neural networks (CNNs) evolved from Fukushima's neocognitron model, which is based on the ideas of Hubel and Wiesel about the early stages of the visual cortex. Unlike other branches of neocognitron-based models, the typical CNN is based on end-to-end supervised learning by backpropagation and removes the focus from built-in invariance mechanisms, using pooling not as a way to tolerate small shifts but as a regularization tool that decreases model complexity. These properties of end-to-end supervision and flexibility of structure allow the typical CNN to become highly tuned to the training data, leading to extremely high accuracies on typical visual pattern recognition data sets. However, in this work, we hypothesize that there is a flip side to this capability, a hidden overfitting. More concretely, a supervised, backpropagation based CNN will outperform a neocognitron/map transformation cascade (MTCCXC) when trained and tested inside the same data set. Yet if we take both models trained and test them on the same task but on another data set (without retraining), the overfitting appears. Other neocognitron descendants like the What-Where model go in a different direction. In these models, learning remains unsupervised, but more structure is added to capture invariance to typical changes. Knowing that, we further hypothesize that if we repeat the same experiments with this model, the lack of supervision may make it worse than the typical CNN inside the same data set, but the added structure will make it generalize even better to another one. To put our hypothesis to the test, we choose the simple task of handwritten digit classification and take two well-known data sets of it: MNIST and ETL-1. To try to make the two data sets as similar as possible, we experiment with several types of preprocessing. However, regardless of the type in question, the results align exactly with expectation.

scholarly journals Simulation of flood flow in a river system using artificial neural networks

2005 ◽  
Vol 9 (4) ◽  
pp. 313-321 ◽  
Author(s):  
R. R. Shrestha ◽  
S. Theobald ◽  
F. Nestmann
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Flow Simulation ◽  
Simulation Models ◽  
River System ◽  
Training Data ◽  
Data Sets ◽  
Network Training ◽  
Artificial Neural ◽  
Flood Flow

Abstract. Artificial neural networks (ANNs) provide a quick and flexible means of developing flood flow simulation models. An important criterion for the wider applicability of the ANNs is the ability to generalise the events outside the range of training data sets. With respect to flood flow simulation, the ability to extrapolate beyond the range of calibrated data sets is of crucial importance. This study explores methods for improving generalisation of the ANNs using three different flood events data sets from the Neckar River in Germany. An ANN-based model is formulated to simulate flows at certain locations in the river reach, based on the flows at upstream locations. Network training data sets consist of time series of flows from observation stations. Simulated flows from a one-dimensional hydrodynamic numerical model are integrated for network training and validation, at a river section where no measurements are available. Network structures with different activation functions are considered for improving generalisation. The training algorithm involved backpropagation with the Levenberg-Marquardt approximation. The ability of the trained networks to extrapolate is assessed using flow data beyond the range of the training data sets. The results of this study indicate that the ANN in a suitable configuration can extend forecasting capability to a certain extent beyond the range of calibrated data sets.

scholarly journals Methods for maintenance of neural networks in continual learning scenarios

2021 ◽  
Author(s):  
Bhasker Sri Harsha Suri ◽  
Manish Srivastava ◽  
Kalidas Yeturu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Production Systems ◽  
Image Data ◽  
Training Data ◽  
Learning Loss ◽  
Unseen Data ◽  
Scoring Schemes ◽  
The Difference ◽  
Continual Learning

Neural networks suffer from catastrophic forgetting problem when deployed in a continual learning scenario where new batches of data arrive over time; however they are of different distributions from the previous data used for training the neural network. For assessing the performance of a model in a continual learning scenario, two aspects are important (i) to compute the difference in data distribution between a new and old batch of data and (ii) to understand the retention and learning behavior of deployed neural networks. Current techniques indicate the novelty of a new data batch by comparing its statistical properties with that of the old batch in the input space. However, it is still an open area of research to consider the perspective of a deployed neural network’s ability to generalize on the unseen data samples. In this work, we report a dataset distance measuring technique that indicates the novelty of a new batch of data while considering the deployed neural network’s perspective. We propose the construction of perspective histograms which are a vector representation of the data batches based on the correctness and confidence in the prediction of the deployed model. We have successfully tested the hypothesis empirically on image data coming MNIST Digits, MNIST Fashion, CIFAR10, for its ability to detect data perturbations of type rotation, Gaussian blur, and translation. Upon new data, given a model and its training data, we have proposed and evaluated four new scoring schemes, retention score (R), learning score (L), Oscore and SP-score for studying how much the model can retain its performance on past data, how much it can learn new data, the combined expression for the magnitude of retention and learning and stability-plasticity characteristics respectively. The scoring schemes have been evaluated MNIST Digits and MNIST Fashion data sets on different types of neural network architectures based on the number of parameters, activation functions, and learning loss functions, and an instance of a typical analysis report is presented. Machine learning model maintenance is a reality in production systems in the industry, and we hope our proposed methodology offers a solution to the need of the day in this aspect.

scholarly journals SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification

2020 ◽  
Vol 12 (20) ◽  
pp. 3358
Author(s):  
Vasileios Syrris ◽  
Ondrej Pesek ◽  
Pierre Soille
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Supervised Classification ◽  
Deep Neural Networks ◽  
Satellite Image ◽  
Data Retrieval ◽  
Remote Sensing Image ◽  
Training Data ◽  
Data Sets ◽  
Remote Sensing Image Classification

Automatic supervised classification with complex modelling such as deep neural networks requires the availability of representative training data sets. While there exists a plethora of data sets that can be used for this purpose, they are usually very heterogeneous and not interoperable. In this context, the present work has a twofold objective: (i) to describe procedures of open-source training data management, integration, and data retrieval, and (ii) to demonstrate the practical use of varying source training data for remote sensing image classification. For the former, we propose SatImNet, a collection of open training data, structured and harmonized according to specific rules. For the latter, two modelling approaches based on convolutional neural networks have been designed and configured to deal with satellite image classification and segmentation.

Counting the Hidden Defects in Software Documents

2010 ◽  
pp. 519-538
Author(s):  
Frank Padberg
Keyword(s):  
Neural Networks ◽  
Training Data ◽  
Estimation Methods ◽  
Model Parameters ◽  
Small Data ◽  
Data Sets ◽  
Software Inspection ◽  
Bayesian Techniques ◽  
Standard Quality ◽  
Small Data Sets

The author uses neural networks to estimate how many defects are hidden in a software document. Input for the models are metrics that get collected when effecting a standard quality assurance technique on the document, a software inspection. For inspections, the empirical data sets typically are small. The author identifies two key ingredients for a successful application of neural networks to small data sets: Adapting the size, complexity, and input dimension of the networks to the amount of information available for training; and using Bayesian techniques instead of cross-validation for determining model parameters and selecting the final model. For inspections, the machine learning approach is highly successful and outperforms the previously existing defect estimation methods in software engineering by a factor of 4 in accuracy on the standard benchmark. The author’s approach is well applicable in other contexts that are subject to small training data sets.

Methods for maintenance of neural networks in continual learning scenarios

2021 ◽  
Author(s):  
Bhasker Sri Harsha Suri ◽  
Manish Srivastava ◽  
Kalidas Yeturu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Production Systems ◽  
Image Data ◽  
Training Data ◽  
Learning Loss ◽  
Unseen Data ◽  
Scoring Schemes ◽  
The Difference ◽  
Continual Learning

Neural networks suffer from catastrophic forgetting problem when deployed in a continual learning scenario where new batches of data arrive over time; however they are of different distributions from the previous data used for training the neural network. For assessing the performance of a model in a continual learning scenario, two aspects are important (i) to compute the difference in data distribution between a new and old batch of data and (ii) to understand the retention and learning behavior of deployed neural networks. Current techniques indicate the novelty of a new data batch by comparing its statistical properties with that of the old batch in the input space. However, it is still an open area of research to consider the perspective of a deployed neural network’s ability to generalize on the unseen data samples. In this work, we report a dataset distance measuring technique that indicates the novelty of a new batch of data while considering the deployed neural network’s perspective. We propose the construction of perspective histograms which are a vector representation of the data batches based on the correctness and confidence in the prediction of the deployed model. We have successfully tested the hypothesis empirically on image data coming MNIST Digits, MNIST Fashion, CIFAR10, for its ability to detect data perturbations of type rotation, Gaussian blur, and translation. Upon new data, given a model and its training data, we have proposed and evaluated four new scoring schemes, retention score (R), learning score (L), Oscore and SP-score for studying how much the model can retain its performance on past data, how much it can learn new data, the combined expression for the magnitude of retention and learning and stability-plasticity characteristics respectively. The scoring schemes have been evaluated MNIST Digits and MNIST Fashion data sets on different types of neural network architectures based on the number of parameters, activation functions, and learning loss functions, and an instance of a typical analysis report is presented. Machine learning model maintenance is a reality in production systems in the industry, and we hope our proposed methodology offers a solution to the need of the day in this aspect.

Sign in / Sign up

Export Citation Format

Share Document