Simulating a pipelined RISC processor

Pandey, Amit

doi:10.1109/inventive.2016.7824854

Cited by 7 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(e) Activation functions: The authors of [167] explore the effect of different activation functions on image classification results. They note that CNNs perform better than machine learning techniques because of their multi-layer hierarchical feature extraction that is controlled by variables such as the number of hidden layers, activation functions, learning rates, initial weights, and decay functions, however, they attributed the non-linearity of the network only to the activation function, which motivates their comparative investigation, regarding under-researched problems including (a) vanishing and exploding gradients during back-propagation, (b) zero-mean and range of outputs, (c) computational complexity of activation functions and (d) predictive performance of the model.…”

Section: Properties Of Resnet-18mentioning

confidence: 99%

“…While deep convolutional architectures had been shown to provide state-of-the-art performance on standard image classification benchmarks such as the ImageNet data set [39][40][41], it was quickly discovered that, in a somewhat counter-intuitive fashion, deeper networks only led to increased performance up to a point, after which increased network depth resulted in increasingly worse performance. This was due to what is known as the vanishing gradients problem [167,168]. In essence, the deeper a network becomes, the smaller the derivative used to adjust model weights becomes during backpropagation.…”

Section: Selection Of Resnet-18 As the Cnn Structure For The Work In ...mentioning

confidence: 99%

See 1 more Smart Citation

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges

Herzfeld,

Hessburg,

Trantow

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The objectives of this paper are to investigate the trade-offs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach (“VarioCNN”). Our solution is provided in the framework of a cyberinfrastructure that includes a +newly designed ML software, GEOCLASS-image (v1.0), modern high-resolution satellite image data sets (Maxar WorldView data), and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100–200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

show abstract

Section: Properties Of Resnet-18mentioning

confidence: 99%

Section: Selection Of Resnet-18 As the Cnn Structure For The Work In ...mentioning

confidence: 99%

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges

Herzfeld,

Hessburg,

Trantow

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…(e) Activation functions: [170] explore the effect of different activation functions on image classification results. They note that CNNs perform better than machine learning techniques because of their multi-layer hierarchical feature extraction which is controlled by variables such as number of hidden layers, activation functions, learning rates, initial weights, and decay functions, however, they attribute non-linearity of the network only to the activation function which motivates their comparative investigation, regarding under-researched problems including (a) vanishing and exploding gradients during back-propagation, (b) zero-mean and range of outputs, (c) compute complexity of activation functions and (d) predictive performance of the model.…”

Section: Properties Of Resnet-18mentioning

confidence: 99%

“…While deep convolutional architectures had been shown to provide state of the art performance on standard image classification benchmarks such as the ImageNet dataset [39][40][41], it was quickly discovered that, in a somewhat counter-intuitive fashion, deeper networks only led to increased performance up to a point, after which increased network depth resulted in increasingly worse performance. This was due to what is known as the vanishing gradients problem [170,171]. In essence, the deeper a network becomes, the smaller the derivative used to adjust model weights becomes during backpropagation.…”

Section: Applications Of Resnetsmentioning

confidence: 99%

Combining "Deep Learning" and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-image System to Create VarioCNN for Glacier Surges

Herzfeld,

Hessburg,

Trantow

et al. 2024

Preprint

View full text Add to dashboard Cite

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

show abstract

“…This was due to what is known as the vanishing gradients problem (Pandey & Srivastava, 2023;Ruder, 2016). In essence, the deeper a network becomes, the smaller the derivative used to adjust model weights becomes during backpropagation.…”

Section: Applications Of Resnetsmentioning

confidence: 99%

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-image System to Create VarioCNN for Glacier Surges

Herzfeld,

Hessburg,

Trantow

et al. 2024

Preprint

View full text Add to dashboard Cite

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach (“VarioCNN”). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image datasets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN, provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity, which for a marine-terminating glacier leads to sudden and substantial mass transfer from the cryosphere to the oceans, contributing significantly to sea-level-rise. The sudden and rapid acceleration characteristic of a surge results in formation of crevasses, whose spatial characteristics provide informants on the ice-dynamic processes that occur during the surge. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in 6 simplified classes.

show abstract

Simulating a pipelined RISC processor

Cited by 7 publications

References 4 publications

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-Image System to Create VarioCNN for Glacier Surges

Combining "Deep Learning" and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-image System to Create VarioCNN for Glacier Surges

Combining “Deep Learning” and Physically Constrained Neural Networks to Derive Complex Glaciological Change Processes from Modern High-Resolution Satellite Imagery: Application of the GEOCLASS-image System to Create VarioCNN for Glacier Surges

Contact Info

Product

Resources

About