scholarly journals Handwritten Digit Recognition: Hyperparameters-Based Analysis

2020 ◽  
Vol 10 (17) ◽  
pp. 5988
Author(s):  
Saleh Albahli ◽  
Fatimah Alhassan ◽  
Waleed Albattah ◽  
Rehan Ullah Khan
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Digit Recognition ◽  
The Neural Network ◽  
Solution Models ◽  
Handwritten Digit ◽  
Optimal Values ◽  
Data Scientist

Neural networks have several useful applications in machine learning. However, benefiting from the neural-network architecture can be tricky in some instances due to the large number of parameters that can influence performance. In general, given a particular dataset, a data scientist cannot do much to improve the efficiency of the model. However, by tuning certain hyperparameters, the model’s accuracy and time of execution can be improved. Hence, it is of utmost importance to select the optimal values of hyperparameters. Choosing the optimal values of hyperparameters requires experience and mastery of the machine learning paradigm. In this paper, neural network-based architectures are tested based on altering the values of hyperparameters for handwritten-based digit recognition. Various neural network-based models are used to analyze different aspects of the same, primarily accuracy based on hyperparameter values. The extensive experimentation setup in this article should, therefore, provide the most accurate and time-efficient solution models. Such an evaluation will help in selecting the optimized values of hyperparameters for similar tasks.

scholarly journals Mobility Speed Effect and Neural Network Optimization for Deep MIMO Beamforming in mmWave Networks

2020 ◽  
Vol 12 (6) ◽  
pp. 1-14
Author(s):  
Mustafa S. Aljumaily ◽  
Husheng Li
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Network Architecture ◽  
Base Stations ◽  
Neural Network Architecture ◽  
Millimetre Wave ◽  
The Neural Network ◽  
Dataset Size ◽  
Speed Effect ◽  
The Impact

Beamforming for millimetre-wave (mmWave) frequencies has been studied for many years. It is considered as an important enabling technology for communications in these high-frequency ranges and it received a lot of attention in the research community. The special characteristics of the mmWave band made the beamforming problem a challenging one because it depends on many environmental and operational factors. These challenges made any model-based architecture fit only special applications, working scenarios, and specific environment geometry. All these reasons increased the need for more general machine learning based beamforming systems that can work in different environments and conditions. This increased the need for an extended adjustable dataset that can serve as a tool for any machine learning technique to build an efficient beamforming architecture. Deep MIMO dataset has been used in many architectures and designs and has proved its benefits and flexibility to fit in many cases. In this paper, we study the extension of collaborative beamforming that includes many cooperating base stations by studying the impact of User Equipment (UE) speed ranges on the beamforming performance, optimizing the parameters of the neural network architecture of the beamforming design, and suggesting the optimal design that gives the best performance for as a small dataset as possible. Suggested architecture can achieve the same performance achieved before with up to 33% reduction in the dataset size used to train the system which provides a huge reduction in the data collection and processing time.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach

2021 ◽  
Vol 12 (6) ◽  
pp. 1-21
Author(s):  
Jayant Gupta ◽  
Carl Molnar ◽  
Yiqun Xie ◽  
Joe Knight ◽  
Shashi Shekhar
Keyword(s):  
Neural Network ◽  
Spatial Variability ◽  
Network Architecture ◽  
Network Models ◽  
Neural Network Architecture ◽  
Neural Network Models ◽  
Climatic Zones ◽  
The Neural Network ◽  
Plant Hardiness ◽  
Interpretation Model

Spatial variability is a prominent feature of various geographic phenomena such as climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all (OSFA) approach to train single deep neural network models that do not account for spatial variability. Quantification of spatial variability can be challenging due to the influence of many geophysical factors. In preliminary work, we proposed a spatial variability aware neural network (SVANN-I, formerly called SVANN ) approach where weights are a function of location but the neural network architecture is location independent. In this work, we explore a more flexible SVANN-E approach where neural network architecture varies across geographic locations. In addition, we provide a taxonomy of SVANN types and a physics inspired interpretation model. Experiments with aerial imagery based wetland mapping show that SVANN-I outperforms OSFA and SVANN-E performs the best of all.

Morphological Convolutional Neural Network Architecture for Digit Recognition

2019 ◽  
Vol 30 (9) ◽  
pp. 2876-2885 ◽  
Author(s):  
Dorra Mellouli ◽  
Tarek M. Hamdani ◽  
Javier J. Sanchez-Medina ◽  
Mounir Ben Ayed ◽  
Adel M. Alimi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Digit Recognition

scholarly journals Towards Better Interpretability in Deep Q-Networks

2019 ◽  
Vol 33 ◽  
pp. 4561-4569 ◽  
Author(s):  
Raghuram Mandyam Annasamy ◽  
Katia Sycara
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Empirical Studies ◽  
Superior Performance ◽  
Training Algorithms ◽  
Neural Network Architecture ◽  
Q Learning ◽  
The Neural Network ◽  
Learning Techniques ◽  
Out Of Sample

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model’s behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-art deep Q-learning models. However, results suggest that the features extracted by the neural network are extremely shallow and subsequent testing using out-of-sample examples shows that the agent can easily overfit to trajectories seen during training.

scholarly journals Interpretable deep neural network for cancer survival analysis by integrating genomic and clinical data

2019 ◽  
Vol 12 (S10) ◽  
Author(s):  
Jie Hao ◽  
Youngsoon Kim ◽  
Tejaswini Mallavarapu ◽  
Jung Hun Oh ◽  
Mingon Kang
Keyword(s):  
Neural Network ◽  
Survival Analysis ◽  
Cancer Patient ◽  
Clinical Data ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Patient Survival ◽  
Biological Mechanisms ◽  
Neural Network Architecture ◽  
The Neural Network

Abstract Background Understanding the complex biological mechanisms of cancer patient survival using genomic and clinical data is vital, not only to develop new treatments for patients, but also to improve survival prediction. However, highly nonlinear and high-dimension, low-sample size (HDLSS) data cause computational challenges to applying conventional survival analysis. Results We propose a novel biologically interpretable pathway-based sparse deep neural network, named Cox-PASNet, which integrates high-dimensional gene expression data and clinical data on a simple neural network architecture for survival analysis. Cox-PASNet is biologically interpretable where nodes in the neural network correspond to biological genes and pathways, while capturing the nonlinear and hierarchical effects of biological pathways associated with cancer patient survival. We also propose a heuristic optimization solution to train Cox-PASNet with HDLSS data. Cox-PASNet was intensively evaluated by comparing the predictive performance of current state-of-the-art methods on glioblastoma multiforme (GBM) and ovarian serous cystadenocarcinoma (OV) cancer. In the experiments, Cox-PASNet showed out-performance, compared to the benchmarking methods. Moreover, the neural network architecture of Cox-PASNet was biologically interpreted, and several significant prognostic factors of genes and biological pathways were identified. Conclusions Cox-PASNet models biological mechanisms in the neural network by incorporating biological pathway databases and sparse coding. The neural network of Cox-PASNet can identify nonlinear and hierarchical associations of genomic and clinical data to cancer patient survival. The open-source code of Cox-PASNet in PyTorch implemented for training, evaluation, and model interpretation is available at: https://github.com/DataX-JieHao/Cox-PASNet.

Neural Network Based Intelligent Learning of Fuzzy Logic Controller Parameters

2004 ◽  
Author(s):  
Manish Kumar ◽  
Devendra P. Garg
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Network Architecture ◽  
Fuzzy Logic Controller ◽  
Rule Base ◽  
Neural Network Architecture ◽  
The Neural Network ◽  
Neuro Fuzzy ◽  
Learning Capabilities ◽  
Optimal Signal

Design of an efficient fuzzy logic controller involves the optimization of parameters of fuzzy sets and proper choice of rule base. There are several techniques reported in recent literature that use neural network architecture and genetic algorithms to learn and optimize a fuzzy logic controller. This paper presents methodologies to learn and optimize fuzzy logic controller parameters that use learning capabilities of neural network. Concepts of model predictive control (MPC) have been used to obtain optimal signal to train the neural network via backpropagation. The strategies developed have been applied to control an inverted pendulum and results have been compared for two different fuzzy logic controllers developed with the help of neural networks. The first neural network emulates a PD controller, while the second controller is developed based on MPC. The proposed approach can be applied to learn fuzzy logic controller parameter online via the use of dynamic backpropagation. The results show that the Neuro-Fuzzy approaches were able to learn rule base and identify membership function parameters accurately.

Sign in / Sign up

Export Citation Format

Share Document