CNNS
PulseAugur coverage of CNNS — every cluster mentioning CNNS across labs, papers, and developer communities, ranked by signal.
6 天有情绪数据
-
New MDSE attack fools Spiking Neural Networks and traditional models
Researchers have developed a new adversarial attack method called Mixed Dynamic Spiking Estimation (MDSE) specifically for Spiking Neural Networks (SNNs). This attack demonstrates that the effectiveness of white-box adv…
-
AI learning rules align with early primate vision, diverge in higher areas
Researchers have published a study comparing how different learning rules in artificial neural networks align with visual processing in both humans and macaques. The study found that early visual cortex alignment was co…
-
Paper questions weight decay's role in deep learning stability
A new paper investigates the role of weight decay in deep learning training stability, challenging its common perception as a simple regularization technique. The research analyzes how weight decay affects parameter dyn…
-
Vision Mamba models show promise for AI-generated image detection
A new research paper investigates the effectiveness of Vision Mamba models in detecting AI-generated images. The study systematically evaluates various Vision Mamba architectures against established methods like CNNs, V…
-
Active learning research challenges need for candidate models
Researchers have explored a new approach to active learning that bypasses the need for initial candidate models. This method utilizes randomly initialized CNNs and transformers, demonstrating that active learning can be…
-
New framework integrates multimodal brain network analysis
Researchers have developed Supervised Deep Multimodal Matrix Factorization (SD3MF), a novel framework for analyzing brain networks. This interpretable method extends traditional matrix factorization to handle supervised…
-
ECG foundation models benefit from contrastive learning and state space architectures
Researchers have conducted a systematic study on pretraining strategies and scaling for electrocardiography (ECG) foundation models. They evaluated five different self-supervised learning objectives, finding that contra…
-
New SWAP-Score metric evaluates neural networks without training
Researchers have introduced SWAP-Score, a novel zero-shot metric designed to evaluate neural networks without requiring training. This method measures a network's expressivity using sample-wise activation patterns and d…
-
New AdaLoc method secures adaptable AI model usage control
Researchers have developed a new method called AdaLoc to enhance the security of deep neural networks (DNNs) by embedding an access key within a subset of the model's parameters. This approach allows for adaptable model…
-
New research reveals implicit bias drives neural scaling laws in deep learning
Researchers have identified two new dynamical scaling laws that describe how neural network performance changes with complexity measures throughout training. These laws, observed across various architectures like CNNs a…
-
Vision Transformers optimize spatio-temporal vegetation classification efficiency
Researchers have developed an optimized Vision Transformer (ViT) approach for classifying vegetation pixels over time, addressing computational challenges in plant phenology monitoring. This new method offers significan…
-
KAConvNet integrates Kolmogorov-Arnold theorem with CNNs for vision tasks
Researchers have introduced KAConvNet, a novel convolutional neural network architecture that integrates the Kolmogorov-Arnold representation theorem. This new approach aims to enhance interpretability and efficiency by…
-
AI model uses neuro-anatomy for efficient Alzheimer's disease classification
Researchers have developed NeuroAPS-Net, a novel deep learning model designed for efficient Alzheimer's disease classification using MRI data. This model converts T1-weighted MRI scans into anatomically informed 2D poin…
-
Benign overfitting in adversarial training boosts Vision Transformer robustness
Researchers have theoretically analyzed adversarial training for Vision Transformers (ViTs), finding it can achieve near-zero robust training loss and generalization error under specific conditions. This defense strateg…