An Artificial Neural Network(ANN) is a well known universal approximator to model smooth and continuous functions. ANNs operate in two stages: learning and generalization. Learning of a neural network is to approximate the behavior of the training data while generalization is the ability to predict well beyond the training data. In order to have a good learning and generalization ability , a go...

Prior knowledge can highly improve the accuracy of segmentation algorithms for 3D medical images. A popular method for describing the variability of shape of organs are statistical shape models. One of the greatest challenges in statistical shape modeling is to compute a representation of the training shapes as vectors of corresponding landmarks, which is required to train the model. Many algor...

the objective of this research was to determine the best model and compare performances in terms of producing landuse maps from six supervised classification algorithms. as a result, different algorithms such as the minimum distance ofmean (mdm), mahalanobis distance (md), maximum likelihood (ml), artificial neural network (ann), spectral anglemapper (sam), and support vector machine (svm) were...

BACKGROUND Guideline adherence with respect to exercise-based cardiac rehabilitation (CR) is hampered by a large variety of complex guidelines and position statements, and the fact that these documents are not specifically designed for healthcare professionals prescribing exercise-based CR programs. This study aimed to develop clinical algorithms that can be used in clinical practice for prescr...

Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is memory-bandwidth bounded. Such a drawback of BN motivates us to explore recently proposed weight normalization algorithms (WN algorithms), i.e. weight normalization, normalization propag...

Anomaly detection, the recognition of faulty behavior, and diagnosis, process identification root cause a fault, in Cyber-Physical Production Systems (CPPS) are complex tasks, due to increasing complexity modularity modern production systems. But amount data, generated by sensors, offers solution: Machine Learning (ML) can be used automatically generate models for anomaly detection diagnosis ba...

Training neural networks with coarsely quantized weights is a key step towards learning on embedded platforms that have limited computing resources, memory capacity, and power consumption. Numerous recent publications have studied methods for training quantized networks, but these studies have been purely experimental. In this work, we investigate the theory of training quantized neural network...

This paper presents the development of several Efficient LEarning Algorithms for Neural NEtworks (ELEANNE). The ELEANNE 1 and ELEANNE 2 are two recursive leastsquares learning algorithms, proposed for training single-layered neural networks with analog output. This paper also proposes a new optimization strategy for training single-layered neural networks, which provides the basis for the devel...