A calibration strategy using full-Jones corrections with an in-field unpolarised calibrator and visibility-based multi-epoch alignment enables sub-arcsecond polarimetric imaging with LOFAR at metre wavelengths.
super hub Canonical reference
Learning Representations by Back- Propagating Errors
Canonical reference. 100% of citing Pith papers cite this work as background.
31
Pith papers citing it
23.4k
external citations · Crossref
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
authors
co-cited works
fields
cs.LG 11 stat.ML 3 cond-mat.str-el 2 cs.CV 2 q-bio.NC 2 astro-ph.GA 1 astro-ph.IM 1 astro-ph.SR 1 cs.AI 1 cs.CL 1roles
background 6polarities
background 6representative citing papers
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
pKANrtm uses a physics-aware multi-fidelity KAN to emulate high-fidelity radiative transfer coefficients for atmospheric correction with superior accuracy and large speedups over direct libRadtran runs.
Local 2- and 3-cycles enhance RNN computational capacity for Boolean functions, predicted by structural statistics, while adding interneurons boosts large networks.
A beta-VAE analysis of pop-cosmos models finds that five latent dimensions capture the rest-frame optical SED, corresponding to stellar mass, recent star formation, dust, and two gas ionization states.
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
Supervised learning approaches including kernel estimation, random forests, additive models, and deep learning are proposed to estimate conditional covariance matrices for removing multivariate environmental influences in SHM beyond standard response surface modeling.
Backpropagated gradients from vision models predict higher visual cortex signals but diverge from brain hierarchies in spatial and temporal organization.
Adaptive RBF-KAN adds multiple radial basis kernels and LOOCV-based shape initialization to FastKAN, with benchmark tests on 2D functions showing kernel-specific advantages for smooth, discontinuous, and oscillatory cases.
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
HBLL decomposes DNNs into hierarchical blocks trained with local variational objectives to achieve O(log N) parallel training time without end-to-end backpropagation.
Controlled benchmarks of five algorithms across six languages show C and C++ tied for fastest, Rust 9% behind, Julia 3.3x slower, Go 5x slower, and Python 315x slower, with workload-dependent rank shifts and differing memory footprints.
Ada2MS is a new optimizer that exponentially mixes elementwise and global second-moment estimates to interpolate between AdamW and momentum-SGD behaviors and reports competitive results on visual tasks under a unified protocol.
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
eDySec is a deep learning-based framework that detects malicious PyPI packages through dynamic analysis, halving feature dimensionality, reducing false positives by 82%, false negatives by 79%, and boosting accuracy by 3% with near-perfect stability.
A cycle-based reentry architecture is proposed to guarantee self-model emergence, self-preservation, and prompt-injection immunity in AGI via a D-I loop and a new S-measure of integrated information.
Machine learning models RuBR_comb, RuBR_loc, and RuBR_DA for real-bogus classification of transients using combined simulated data and domain adaptation for the Roman RAPID pipeline.
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
A neural network classifies 20,196 TESS eclipsing binaries into 13,376 EA, 2,114 EB, and 4,706 EW systems after achieving 99% accuracy on held-out test data.
Experts rate AI scenarios as more likely, less risky, more beneficial, and more valuable than the public, applying different weightings to risk versus benefit.
citing papers explorer
-
Polarisation and Faraday rotation measure imaging at metre wavelengths with sub-arcsecond resolution: a foundational calibration strategy
A calibration strategy using full-Jones corrections with an in-field unpolarised calibrator and visibility-based multi-epoch alignment enables sub-arcsecond polarimetric imaging with LOFAR at metre wavelengths.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov-Arnold Networks
pKANrtm uses a physics-aware multi-fidelity KAN to emulate high-fidelity radiative transfer coefficients for atmospheric correction with superior accuracy and large speedups over direct libRadtran runs.
-
Identifying structural design principles shaping the computational abilities of recurrent neural networks
Local 2- and 3-cycles enhance RNN computational capacity for Boolean functions, predicted by structural statistics, while adding interneurons boosts large networks.
-
pop-cosmos: Disentangling galaxy properties from observables using data-driven approaches
A beta-VAE analysis of pop-cosmos models finds that five latent dimensions capture the rest-frame optical SED, corresponding to stellar mass, recent star formation, dust, and two gas ionization states.
-
Direct High-Magnetic-Field Coupling to Stripe Order in a Cuprate Superconductor
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
-
Anchor PCA
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
-
Removal of Multivariate Environmental Influences in Structural Health Monitoring through Conditional Covariances and Supervised Learning
Supervised learning approaches including kernel estimation, random forests, additive models, and deep learning are proposed to estimate conditional covariance matrices for removing multivariate environmental influences in SHM beyond standard response surface modeling.
-
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
Backpropagated gradients from vision models predict higher visual cortex signals but diverge from brain hierarchies in spatial and temporal organization.
-
Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks
Adaptive RBF-KAN adds multiple radial basis kernels and LOOCV-based shape initialization to FastKAN, with benchmark tests on 2D functions showing kernel-specific advantages for smooth, discontinuous, and oscillatory cases.
-
A Meta Reinforcement Learning Approach to Goals-Based Wealth Management
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
-
CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans
CAHAL introduces a physics-informed mixture-of-experts super-resolution network for clinical MRI that conditions on resolution and anisotropy and uses edge-penalised, Fourier, and segmentation-guided losses to reduce hallucinations compared with prior generative methods.
-
Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
Embedding selection mechanisms into generative simulators enables amortized Bayesian inference to produce debiased, well-calibrated posteriors without tractable likelihoods.
-
Pulse Shape Discrimination Algorithms: Survey and Benchmark
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
-
Breaking chains with trees: Deep learning with $\mathcal{O}(\log N)$ parallel time complexity
HBLL decomposes DNNs into hierarchical blocks trained with local variational objectives to achieve O(log N) parallel training time without end-to-end backpropagation.
-
Behind Python: The Languages That Power AI
Controlled benchmarks of five algorithms across six languages show C and C++ tied for fastest, Rust 9% behind, Julia 3.3x slower, Go 5x slower, and Python 315x slower, with workload-dependent rank shifts and differing memory footprints.
-
Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates
Ada2MS is a new optimizer that exponentially mixes elementwise and global second-moment estimates to interpolate between AdamW and momentum-SGD behaviors and reports competitive results on visual tasks under a unified protocol.
-
Soft Learning
Soft Learning optimally combines heterogeneous ML specialists via cross-validated non-negative least squares, achieving top performance on 70% of 37 datasets with formal guarantees and 72-435x CPU speedups over deep networks.
-
eDySec: A Deep Learning-based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem
eDySec is a deep learning-based framework that detects malicious PyPI packages through dynamic analysis, halving feature dimensionality, reducing false positives by 82%, false negatives by 79%, and boosting accuracy by 3% with near-perfect stability.
-
Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI
A cycle-based reentry architecture is proposed to guarantee self-model emergence, self-preservation, and prompt-injection immunity in AGI via a D-I loop and a new S-measure of integrated information.
-
Identifying Gems from Roman RAPIDly
Machine learning models RuBR_comb, RuBR_loc, and RuBR_DA for real-bogus classification of transients using combined simulated data and domain adaptation for the Roman RAPID pipeline.
-
CRADIPOR: Crash Dispersion Predictor
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
-
The Phenomenological Classification of TESS Eclipsing Binaries
A neural network classifies 20,196 TESS eclipsing binaries into 13,376 EA, 2,114 EB, and 4,706 EW systems after achieving 99% accuracy on held-out test data.
-
Perception Gaps in Risk, Benefit, and Value Between Experts and Public Challenge Socially Accepted AI
Experts rate AI scenarios as more likely, less risky, more beneficial, and more valuable than the public, applying different weightings to risk versus benefit.
-
How Complexity Contributes to Learning Opacity in Machine Learning
Neural network learning opacity stems from three dynamical complexity properties in training, rendering some sources of opacity irreducible.
-
The Mathematics of AI Winters: The mathematical Taxonomy of Paradigm Fragility in AI Winter
Established mathematical bottlenecks in representation, optimization, complexity, and high-dimensional learning aligned with the central disappointments of early AI research periods.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.
-
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
- A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
- Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
- Lectures on insulating and conducting quantum spin liquids