# Convolutional Neural Networks

Automatic glaucoma screening degrades when a model moves to another hospital and camera; a neuro-symbolic framework combines anatomical graph reasoning with differentiable fuzzy clinical rules in one network, trained on 9,100 fundus images drawn from a corpus of 12,619 images across eight datasets in eight countries and tested on 485 fully held-out RIM-ONE images from a different Spanish hospital and camera. On the in-distribution test set, EfficientNet-B4 with a graph attention network reaches an AUC of 0.9612 (95% CI 0.951–0.972) versus 0.9472 for EfficientNet-B4 alone, yet the combined full model scores 0.6155 cross-hospital, 8.1 points below the baseline.

Automatic glaucoma screening degrades when a model moves to another hospital and camera; a neuro-symbolic framework combines anatomical graph reasoning with differentiable fuzzy clinical rules in one network, trained on 9,100 fundus images drawn from a corpus of 12,619 images across eight datasets in eight countries and tested on 485 fully held-out RIM-ONE images from a different Spanish hospital and camera. On the in-distribution test set, EfficientNet-B4 with a graph attention network reaches an AUC of 0.9612 (95% CI 0.951–0.972) versus 0.9472 for EfficientNet-B4 alone, yet the combined full model scores 0.6155 cross-hospital, 8.1 points below the baseline.

A Carnegie Mellon team released B-REAL, a supervised platform that maps raw video directly to behavior labels without pose estimation, with end-to-end inference latency below 15 ms on standard GPU or CPU hardware. On the CalMS21 mouse social-behavior benchmark, one minute of labeled video surpassed A-SOiD and CBAS trained on the full dataset; on fly aggression, it beat both baselines in all eight paired draws from one minute of labels upward. In closed loop, rewarding mice for B-REAL-detected grooming raised the rate of criterion grooming bouts by 129% from early to late sessions.

A Carnegie Mellon team released B-REAL, a supervised platform that maps raw video directly to behavior labels without pose estimation, with end-to-end inference latency below 15 ms on standard GPU or CPU hardware. On the CalMS21 mouse social-behavior benchmark, one minute of labeled video surpassed A-SOiD and CBAS trained on the full dataset; on fly aggression, it beat both baselines in all eight paired draws from one minute of labels upward. In closed loop, rewarding mice for B-REAL-detected grooming raised the rate of criterion grooming bouts by 129% from early to late sessions.

Saliency maps for convolutional classifiers on medical images now have a new training route: SalientNet needs no annotated saliency ground truth and instead requires the generated mask to keep enough information for a frozen classifier to reproduce its original prediction within a controlled tolerance. Across BreakHis, Brain MRI ND5 and FracAtlas, it reaches higher faithfulness (Win %) and lower prediction Drop (%) than Grad-CAM, Grad-CAM++ and LIME in nearly all dataset-architecture combinations, and on FracAtlas its maps correlate spatially with practitioner-annotated fracture regions, with a mean ground-truth active fraction of up to 0.96 for ResNet-18.

Saliency maps for convolutional classifiers on medical images now have a new training route: SalientNet needs no annotated saliency ground truth and instead requires the generated mask to keep enough information for a frozen classifier to reproduce its original prediction within a controlled tolerance. Across BreakHis, Brain MRI ND5 and FracAtlas, it reaches higher faithfulness (Win %) and lower prediction Drop (%) than Grad-CAM, Grad-CAM++ and LIME in nearly all dataset-architecture combinations, and on FracAtlas its maps correlate spatially with practitioner-annotated fracture regions, with a mean ground-truth active fraction of up to 0.96 for ResNet-18.

A cross-architecture comparison of CNNs, ViTs and Vision Mamba uses human eye-tracking heatmaps as an independent benchmark to quantify how closely model saliency matches human gaze, finding that Mamba reaches the highest localization scores on chest X-rays while its saliency intensity is nearly uncorrelated with human fixations.

A cross-architecture comparison of CNNs, ViTs and Vision Mamba uses human eye-tracking heatmaps as an independent benchmark to quantify how closely model saliency matches human gaze, finding that Mamba reaches the highest localization scores on chest X-rays while its saliency intensity is nearly uncorrelated with human fixations.

On structural MRI from three independent cohorts, Alzheimer's disease classifiers use age as a shortcut: older patients receive higher predicted risk. Residualizing age linearly in feature space (PMDN) brings the age-prediction correlation near zero in cognitively normal and mild cognitive impairment groups, with balanced accuracy 0.71 and Brier score about 0.22, and far less fold-to-fold spread than the adversarial CF-Net. Post hoc calibration further lowers probability error, with nonparametric isotonic regression and Bayesian binning performing best.

On structural MRI from three independent cohorts, Alzheimer's disease classifiers use age as a shortcut: older patients receive higher predicted risk. Residualizing age linearly in feature space (PMDN) brings the age-prediction correlation near zero in cognitively normal and mild cognitive impairment groups, with balanced accuracy 0.71 and Brier score about 0.22, and far less fold-to-fold spread than the adversarial CF-Net. Post hoc calibration further lowers probability error, with nonparametric isotonic regression and Bayesian binning performing best.

Across nine ImageNet convolutional networks, how much of a layer's own input patches can be reconstructed from its output falls with depth but is more consistently predicted by the layer's effective compression, and copying pretrained singular vectors onto a random encoder raises recoverability while copying the pretrained singular-value spectrum or activation sparsity lowers it.

Across nine ImageNet convolutional networks, how much of a layer's own input patches can be reconstructed from its output falls with depth but is more consistently predicted by the layer's effective compression, and copying pretrained singular vectors onto a random encoder raises recoverability while copying the pretrained singular-value spectrum or activation sparsity lowers it.

ChatGPT, Claude, Gemini and Grok each generated PyTorch helmet-compliance training scripts from three prompt tiers of increasing specificity, run 20 times on 972 balanced images: ten of twelve configurations converged to a 0.957–0.967 accuracy plateau, but the most detailed tier left Gemini and Grok near 0.58, with scripts that ran yet failed to converge. A backbone-by-scheduler ablation traced the failure to the prescribed from-scratch multi-scale network, which collapsed under both schedulers while a pretrained ResNet18 converged under either.

ChatGPT, Claude, Gemini and Grok each generated PyTorch helmet-compliance training scripts from three prompt tiers of increasing specificity, run 20 times on 972 balanced images: ten of twelve configurations converged to a 0.957–0.967 accuracy plateau, but the most detailed tier left Gemini and Grok near 0.58, with scripts that ran yet failed to converge. A backbone-by-scheduler ablation traced the failure to the prescribed from-scratch multi-scale network, which collapsed under both schedulers while a pretrained ResNet18 converged under either.

The work presents and validates a hybrid pipeline that first uses a volumetric convolutional neural network (a D3M-based VNet taking six channels of displacement and velocity) to classify each simulation particle as a halo or non-halo member, then applies a highly optimised and parallelised Friends-of-Friends algorithm to group the predicted halo members into distinct dark matter haloes; trained on GADGET-4 simulations labelled by ROCKSTAR, it reaches over 98% across all primary metrics for particle classification at the highest-resolution L100-N1283 configuration, yields catalogues with purity generally above 95% and completeness stable at about 93% above 5×10¹¹ M⊙, reproduces the halo mass function to within 5% of the reference while faithfully reconstructing internal density profiles,

The work presents and validates a hybrid pipeline that first uses a volumetric convolutional neural network (a D3M-based VNet taking six channels of displacement and velocity) to classify each simulation particle as a halo or non-halo member, then applies a highly optimised and parallelised Friends-of-Friends algorithm to group the predicted halo members into distinct dark matter haloes; trained on GADGET-4 simulations labelled by ROCKSTAR, it reaches over 98% across all primary metrics for particle classification at the highest-resolution L100-N1283 configuration, yields catalogues with purity generally above 95% and completeness stable at about 93% above 5×10¹¹ M⊙, reproduces the halo mass function to within 5% of the reference while faithfully reconstructing internal density profiles,