The authors introduce dRVFL and edRVFL frameworks that stack RVFL layers with fixed random weights and closed-form outputs, reporting superior benchmark performance when combined with sparse-pretrained RVFL.
Schmidhuber, Deep learning in neural networks: An overview, Neural Networks 61 (2015) 85 – 117
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Semi-supervised DL anomaly detector (VAE + classifier) for model-independent searches in DARWIN, outperforming classical likelihood tests on simulated WIMP injections while learning directly from raw high-dimensional outputs.
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.
Standard NLP classifiers can surface valid injury precursors from raw construction safety reports.
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.
MiniGPT is a self-contained PyTorch implementation of standard GPT autoregressive modeling that reaches 1.478 validation loss on Tiny Shakespeare with a 10.77M-parameter model and produces recognizable Shakespeare-style text.
An ANN trained on compound pendulum measurements predicts g with mean absolute error 0.000592 cm/s² but is framed only as an educational tool for regression and validation concepts.
citing papers explorer
-
Random Vector Functional Link Neural Network based Ensemble Deep Learning
The authors introduce dRVFL and edRVFL frameworks that stack RVFL layers with fixed random weights and closed-form outputs, reporting superior benchmark performance when combined with sparse-pretrained RVFL.
-
Model-independent searches of new physics in DARWIN with a semi-supervised deep learning pipeline
Semi-supervised DL anomaly detector (VAE + classifier) for model-independent searches in DARWIN, outperforming classical likelihood tests on simulated WIMP injections while learning directly from raw high-dimensional outputs.
-
Sharpness-Aware Minimization with Z-Score Gradient Filtering
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.
-
Automatically Learning Construction Injury Precursors from Text
Standard NLP classifiers can surface valid injury precursors from raw construction safety reports.
-
Robustness Analysis of USmorph: II. Optimizing Feature Extraction, Dimensionality Reduction, and Clustering for Unsupervised Galaxy Morphology Classification
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.
-
MiniGPT: Rebuilding GPT from First Principles
MiniGPT is a self-contained PyTorch implementation of standard GPT autoregressive modeling that reaches 1.478 validation loss on Tiny Shakespeare with a 10.77M-parameter model and produces recognizable Shakespeare-style text.
-
Integrating Artificial Neural Networks into Undergraduate Physics Laboratory: A Compound Pendulum Case Study
An ANN trained on compound pendulum measurements predicts g with mean absolute error 0.000592 cm/s² but is framed only as an educational tool for regression and validation concepts.