Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke, Vadim

doi:10.1515/itms-2015-0007

Cited by 9 publications

(18 citation statements)

References 38 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For datasets whose entries are tiny and simple images on a monotonous background, the best MPL allocation is "11...100...0" (e.g., see [15]). Versions of MPL allocations with fewer "ones" should be nonetheless tried in the first turn.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets

Romanuke

2017

Information Technology and Management Science

View full text Add to dashboard Cite

-A problem of appropriately allocating pooling layers in convolutional neural networks is considered. The consideration is based on CIFAR-10, NORB, and EEACL26 datasets for preventing "overfitting" in a solution of the problem. For highly accurate image recognition within these datasets, the networks are used with the max pooling operation. The most common form of such operation, which is a 2 2  pooling layer, is applied with a stride of 2 without padding after convolutional layers. Based on performance against a series of the network architectures, a rule for the best allocation of max pooling layers is formulated. The rule is to insert a few pooling layers after the starting convolutional layers and to insert a one pooling layer after the last but one convolutional layer ("11...100...010"). For much simpler datasets, the best allocation is "11...100...0".

show abstract

Section: Discussionmentioning

confidence: 99%

“…Thus, this is 3 for CIFAR-10 and 1 for EEACL26. This is 1 for NORB as well due to splitting the stereo-images and averaging (it is not training set expansion [15]). The filter's depth of a successive ConvL is equal to the number of filters of the antecedent ConvL.…”

mentioning

confidence: 99%

Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets

Romanuke

2017

Information Technology and Management Science

View full text Add to dashboard Cite

show abstract

“…However, yielding to PSTSSD 0.08 r  on average (see Fig. 2 Before verification, the best one of 100 2LPs (30) must be trained further until its performance becomes unimprovable [5], [8], [28]. The best 2LP (30) performs at an average CEP, which is 9.31 %.…”

Section: Models Of Stsm6080i and Stsm6080i Ndpdmentioning

confidence: 99%

“…Such a CEP is tolerable. Figure 6 visualizes STSOs by maximal SDs in (31), which form STSM6080Is of EEACLs successfully classified (the left-side images) with the best 2LP (30) further-trained [4], [28] with the 438 additional passes (438AP further-trained 2LP). Successful classification under lesser SDs is shown below.…”

Section: Models Of Stsm6080i and Stsm6080i Ndpdmentioning

confidence: 99%

“…This is quite implementable owing to the fact that NDFD effaces some distinguishers of DDOs, which allows applying 2LP to accurately classify DDOs. The solution of problem (23) is to be used for other classification problems, where the number of features is a thousand or a few thousands by a few tens of classes [7], [12], [28], [30]. For DDOs that are visualized, an optimal 2LP will be effective for classifying simpler images, rather than recognizing scenes.…”

Section: Solution Propagation and Conclusionmentioning

confidence: 99%

See 1 more Smart Citation

Classifying Scaled-Turned-Shifted Objects with Optimal Pixel-to-Scale-Turn-Shift Standard Deviations Ratio in Training 2-Layer Perceptron on Scaled-Turned-Shifted 4800-Featured Objects under Normally Distributed Feature Distortion

Romanuke

2017

Electrical, Control and Communication Engineering

View full text Add to dashboard Cite

-The problem of classifying diversely distorted objects is considered. The classifier is a 2-layer perceptron capable of classifying greater amounts of objects in a unit of time. This is an advantage of the 2-layer perceptron over more complex neural networks like the neocognitron, the convolutional neural network, and the deep learning neural networks. Distortion types are scaling, turning, and shifting. The object model is a monochrome 60 × 80 image of the enlarged English alphabet capital letter. Consequently, there are 26 classes of 4800-featured objects. Training sets have a parameter, which is the ratio of the pixel-to-scale-turn-shift standard deviations, which allows controlling normally distributed feature distortion. An optimal ratio is found, at which the performance of the 2-layer perceptron is still unsatisfactory. Then, the best classifier is further trained with additional 438 passes of training sets by increasing the training smoothness tenfold. This aids in decreasing the ultimate classification error percentage from 35.23 % down to 12.92 %. However, the expected practicable distortions are smaller, so the percentage corresponding to them becomes just 1.64 %, which means that only one object out of 61 is misclassified. Such a solution scheme is directly applied to other classification problems, where the number of features is a thousand or a few thousands by a few tens of classes.

show abstract

A novel approach to the development of neural network architecture based on metaheuristic protis approach

Harumy,

Zarlis,

Lydia

et al. 2023

EEJET

View full text Add to dashboard Cite

Determining the best model for the neural network architecture and how to optimize the architecture with the metaheuristic Protis Approach is a subject of the study. A comprehensive investigation and utilization of metaheuristic methods are necessary. These methods aim to solve problems and adapt from the lifestyle of the amoeba protis. In this study, the proposed method modifies the life cycle of the amoeba, which consists of four phases: prophase, metaphase, anaphase, and telophase. These four phases are modified in the neural network architecture to optimize the appropriate number of hidden layers and produce an efficient architecture model. The results show that the protis approach optimized the neural network architecture, especially in generating hidden layers to improve the neural network model. Distinctive features of the results obtained are that the average range of degenerate neurons in the hidden layer is 0 to 35 neurons in each layer. The standard number of neurons makes it possible to solve the problem of determining the best model on the neural network architecture. The protis algorithm embedded in the protis recurrent neural network for categorical data measurements produces an average RMSE value, representing the difference between actual measurements and predictions, equal to 0.066. Consequently, the developed model surpasses the current classical neural network model in terms of performance. Regarding accuracy, the protis algorithm embedded in the neural network for categorical and time series data achieves an average precision of 0.952 and a recall of 0.950. The protis convolutional neural network achieves an accuracy of 95.9 %. Therefore, from the three tested datasets, the protis convolutional neural network exhibits the highest accuracy value

show abstract

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Cited by 9 publications

References 38 publications

Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets

Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets

Classifying Scaled-Turned-Shifted Objects with Optimal Pixel-to-Scale-Turn-Shift Standard Deviations Ratio in Training 2-Layer Perceptron on Scaled-Turned-Shifted 4800-Featured Objects under Normally Distributed Feature Distortion

A novel approach to the development of neural network architecture based on metaheuristic protis approach

Contact Info

Product

Resources

About