cnn

A tweet criticizing CNN's Erin Burnett for complaining about the flood of AI-generated translated content on X, reframing it as a business crisis for CNN rather than for X.

A quote from Ben Affleck describing his long interest in computers, digital film workflows, and how convolutional neural networks have been used for edge detection and green-screen compositing in visual effects, posted on Simon Willison's blog.

This paper evaluates 21 Natural Visibility Graph topological metrics for cyber-attack classification using SHAP, Permutation Importance, Boruta, and RFE consensus ranking, showing that a Top3 clustering-coefficient subset achieves 97.15% accuracy on CICIDS2018 while cutting runtime by 96%.

Researchers from University of North Texas propose montage and blending fusion techniques for EEG time-frequency images with a lightweight CNN to predict rTMS depression therapy outcomes, and show that near-perfect accuracy under segment-level validation collapses to near-chance under subject-disjoint cross-validation, cautioning about validation methodology in EEG literature.

A comprehensive visual guide to language models for text classification, including hands-on experiments with RNNs, CNNs, transformers, and calibration techniques.

This paper introduces GPU undervolting as a hardware-level defense to improve CNN adversarial robustness and energy efficiency during training by inducing beneficial stochastic faults.

This preprint demonstrates that evaluation resolution significantly affects the identification of brain-like learning rules in the visual cortex (V1), using CNNs with various learning rules and fMRI data.

Presents a globally trained CNN for forest above-ground biomass estimation using multi-sensor satellite data, with a sparse field calibration workflow to adapt predictions locally. Achieves improved accuracy over uncalibrated global models and ESA CCI products.

PhysAttNet is a physics-informed attention framework that augments lightweight CNN forecasters with domain-guided regularization to improve accuracy and generalization in industrial and astrophysical time series forecasting.

This paper proposes a multi-representation deep learning framework combining CNNs, LSTMs, and recurrence plot analysis to characterize alpha and gamma EEG biomarkers in Fragile X Syndrome, showing improved classification over single-modality baselines.

This paper evaluates CNN pretraining strategies on the JONES-19 cultural design dataset, finding that learning from scratch with multi-crop sampling can match ImageNet pretraining for structured design data, suggesting smaller curated datasets may be more effective in specialized design domains.

A deep learning CNN model from Seoul National University forecast a very strong El Niño months ahead of NOAA's physics-based models, and has been validated as the models converged. The AI also predicts a La Niña flip in 2028, far beyond traditional forecast horizons.

This paper introduces a loss-aware feature-map pruning framework for convolutional neural networks using multi-armed bandits (UCB1 and Thompson Sampling) to selectively remove redundant feature maps, reducing computational cost while preserving accuracy.

This paper systematically evaluates how post-training quantization affects the interpretability of CNN models using Grad-CAM and LIME, revealing that classification accuracy is not a reliable indicator of interpretability stability and that architecture selection is critical for trustworthy deployment.

This paper proposes a lightweight CNN classifier that uses Fourier-Bessel Series Expansion with Euclidean Distance (FBSE-ED) to represent EEG signals as images, achieving 93.60% accuracy in predicting the outcome of rTMS depression therapy, outperforming both EEG-specific and pretrained deep learning models.

This paper analytically computes the optimal representations under a contrastive loss for basic augmentations and natural images with stationary statistics, showing that the optimal CNN first-layer filters are sinusoids and that weights can be computed via a waterfilling algorithm.

Promotion of Stanford's CS231n lectures from 2017 covering CNNs, computer vision, and deep learning fundamentals.

This paper introduces Manifestation Units, a typed tuple protocol for organizing per-component statistics from mechanistic interpretability analyses into structured, queryable fields. The protocol is demonstrated across vision (β-VAE, CNN) and language (GPT-2) models, showing improved retrieval and causal sufficiency.

This paper presents an automated deep learning approach for brain tumor detection in MRI images using CNN and ResNet architectures with transfer learning, achieving up to 97% accuracy.

This paper proposes eCNNTO, a CNN with residual connections to accelerate density-based topology optimization by predicting near-optimal densities from early iteration histories, achieving up to 97% reduction in iterations and strong generalization across different boundary conditions, geometries, and mesh resolutions.