Neural network node output distributions are nonlinear projections along hypersurfaces via Radon transforms, yielding geometric interpretations for nonlinearity, pooling, activations, and adversarial examples.
Imagenet classification with deep convolutional neural networks
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2019 7verdicts
UNVERDICTED 7representative citing papers
A context-aware CNN using 1792x1792 images and spatial feature aggregation outperforms patch-based methods for colorectal cancer grading by 3.61%.
FPCNet uses an encoder-decoder architecture with MD and SEU modules to learn multi-context crack features and achieves faster, more accurate pixel-level detection than prior methods on CFD and G45 datasets.
Iterative temporal differencing with fixed random synaptic feedback can replace the activation function derivative in error backpropagation.
Modifying capsule networks to use dynamic routing for intermediate equivariant features instead of output class capsules yields faster training and higher accuracy on multi-class problems.
A two-stage coefficient grouping algorithm for parallel filter banks that increases sharing and reduces registers, LUTs, and DSP48s by up to 50% on FPGAs.
Survey of data preprocessing techniques (cleaning, transformation, reduction) and their effects on downstream data mining models.
citing papers explorer
-
Neural Networks, Hypersurfaces, and Radon Transforms
Neural network node output distributions are nonlinear projections along hypersurfaces via Radon transforms, yielding geometric interpretations for nonlinearity, pooling, activations, and adversarial examples.
-
Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images
A context-aware CNN using 1792x1792 images and spatial feature aggregation outperforms patch-based methods for colorectal cancer grading by 3.61%.
-
FPCNet: Fast Pavement Crack Detection Network Based on Encoder-Decoder Architecture
FPCNet uses an encoder-decoder architecture with MD and SEU modules to learn multi-context crack features and achieves faster, more accurate pixel-level detection than prior methods on CFD and G45 datasets.
-
Iterative temporal differencing with random synaptic feedback weights support error backpropagation for deep learning
Iterative temporal differencing with fixed random synaptic feedback can replace the activation function derivative in error backpropagation.
-
Using dynamic routing to extract intermediate features for developing scalable capsule networks
Modifying capsule networks to use dynamic routing for intermediate equivariant features instead of output class capsules yields faster training and higher accuracy on multi-class problems.
-
Optimized Sharing of Coefficients in Parallel Filter Banks
A two-stage coefficient grouping algorithm for parallel filter banks that increases sharing and reduces registers, LUTs, and DSP48s by up to 50% on FPGAs.
-
Preprocessing Methods and Pipelines of Data Mining: An Overview
Survey of data preprocessing techniques (cleaning, transformation, reduction) and their effects on downstream data mining models.