Biologically Inspired Hexagonal Deep Learning For Hexagonal Image Generation

Schlosser, Tobias; Beuth, Frederik; Kowerko, Danny

doi:10.1109/icip40778.2020.9190995

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li and He [14] presented a convex k-method employing various area parameter altering criteria and offered an enhanced ResNet via changeable shortcut connections Wightman et al [15] for numerous ResNet configurations in the Timm open-source toolbox, pre-trained models and shared competitive training parameters were made available. The study of Schlosser et al [16] added pre-activation ResNets by rearranging the building block's components to enhance the signal propagation path. All of the well-known efforts that have ResNet as their primary feature extractor are best suited for data that is defined on a square lattice [15], [16].…”

Section: Related Work 21 Residual Networkmentioning

confidence: 99%

See 1 more Smart Citation

Biologically inspired deep residual networks

Varghese,

Saroja

2023

IJ-AI

View full text Add to dashboard Cite

<p>Many difficult computer vision issues have been effectively tackled by deep neural networks. Not only that but it was discovered that traditional residual neural networks (ResNet) captures features with high generalizability, rendering it a cutting-edge convolutional neural network (CNN). The images classified by the authors of this research introduce a deep residual neural network that is biologically inspired introduces hexagonal convolutions along the skip connection. With the competitive training techniques, the effectiveness of several ResNet variations using square and hexagonal convolution is assessed. Using the hex-convolution on skip connection, we designed a family of ResNet architecture,hexagonal residual neural network (HexResNet), which achieves the highest testing accuracy of 94.02%, and 55.71% on Canadian Institute For Advanced Research (CIFAR)-10 and TinyImageNet, respectively. We demonstrate that the suggested method improves vanilla ResNet architectures’ baseline image classification accuracy on the CIFAR-10 dataset, and a similar effect was seen on the TinyImageNet dataset. For Tiny- ImageNet and CIFAR-10, we saw an average increase in accuracy of 1.46% and 0.48% in the baseline Top-1 accuracy, respectively. The generalized performance of advancements was reported for the suggested bioinspired deep residual networks. This represents an area that might be explored more extensively in the future to enhance all the discriminative power of image classification systems.</p>

show abstract

Section: Related Work 21 Residual Networkmentioning

confidence: 99%

“…The study of Schlosser et al [16] added pre-activation ResNets by rearranging the building block's components to enhance the signal propagation path. All of the well-known efforts that have ResNet as their primary feature extractor are best suited for data that is defined on a square lattice [15], [16].…”

Section: Related Work 21 Residual Networkmentioning

confidence: 99%

Biologically inspired deep residual networks

Varghese,

Saroja

2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…The deployed SWWAE-based model with residual learning is a further development of the general autoencoder which reuses the encoded positions for the decoding process supported by additional skip connections via residual learning. Its implementation is described in Schlosser et al (2020).…”

Section: Street Segment Classificationmentioning

confidence: 99%

Improving automated visual fault inspection for semiconductor manufacturing using a hybrid multistage system of deep neural networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

In the semiconductor industry, automated visual inspection aims to improve the detection and recognition of manufacturing defects by leveraging the power of artificial intelligence and computer vision systems, enabling manufacturers to profit from an increased yield and reduced manufacturing costs. Previous domain-specific contributions often utilized classical computer vision approaches, whereas more novel systems deploy deep learning based ones. However, a persistent problem in the domain stems from the recognition of very small defect patterns which are often in the size of only a few $$\mu $$ μ m and pixels within vast amounts of high-resolution imagery. While these defect patterns occur on the significantly larger wafer surface, classical machine and deep learning solutions have problems in dealing with the complexity of this challenge. This contribution introduces a novel hybrid multistage system of stacked deep neural networks (SH-DNN) which allows the localization of the finest structures within pixel size via a classical computer vision pipeline, while the classification process is realized by deep neural networks. The proposed system draws the focus over the level of detail from its structures to more task-relevant areas of interest. As the created test environment shows, our SH-DNN-based multistage system surpasses current approaches of learning-based automated visual inspection. The system reaches a performance (F1-score) of up to 99.5%, corresponding to a relative improvement of the system’s fault detection capabilities by 8.6-fold. Moreover, by specifically selecting models for the given manufacturing chain, runtime constraints are satisfied while improving the detection capabilities of currently deployed approaches.

show abstract

Deep Learning-Based Hexrep Neural Network for Convergence Free with Operator’s Efficacy in Hexagonal Image Processing

Varghese¹,

Saroja²

2022

Int. J. Image Grap.

View full text Add to dashboard Cite

The field of hexagonal image processing is concerned with the creation of image processing systems that combine the advantages of biological model-based evolutionary motivated frameworks. The structure and functionality of artificial neural networks were inspired by biological processes. The fundamental framework of recording and output devices limits their present state of the art. Prior neural networks have used square or hexagonal style input to completely connected layers, which resulted in a high coherence problem between two adjacent hexagonal kernel layers due to pooling. Previous research does not design the self-data structure to support convolution to increase computational efficiency, so it violates the convolution and pooling operator, which greatly degrades the image process performance. This paper introduces a novel paradigm Proficient Deep Learning-based Hexrep Neural Network that overcomes major significant problems in image operations structure constraint, coherence problem, and violation of convolution and pooling operator and achieves hexagonal image processing.

show abstract

Biologically Inspired Hexagonal Deep Learning For Hexagonal Image Generation

Cited by 3 publications

References 21 publications

Biologically inspired deep residual networks

Biologically inspired deep residual networks

Improving automated visual fault inspection for semiconductor manufacturing using a hybrid multistage system of deep neural networks

Deep Learning-Based Hexrep Neural Network for Convergence Free with Operator’s Efficacy in Hexagonal Image Processing

Contact Info

Product

Resources

About