Tag: neural networks

A new theoretical framework trains neural networks natively on the Leech lattice, compressing weights to 0.76 bits per parameter while ...

Researchers in Iran have developed CNNHSIE, an image encryption algorithm that combines hyperchaotic systems with a VGG16 convolutional neural network ...

Researchers in Chongqing have developed a wavelet-guided deep learning framework that coordinates frequency-domain and spatial cues to sharply localize changes ...

Ultrasound AI received two new US patents in September 2026 covering AI-based drug-exposure detection and comprehensive imaging-based medical assessment, expanding ...

University of Manchester researchers used physics-based AI emulators to produce the first global-scale quantification of dissolved organic carbon exchange between ...

Researchers in China have developed FullReg, a semi-supervised regression framework that weights pseudo-labels by data similarity and stabilizes training with ...

Researchers in India have built a tri-backbone deep learning system with an intuitionistic fuzzy fusion module that classifies apple leaf ...

Researchers have developed MFKR Net, a lightweight deep learning model that identifies individuals from contactless middle finger knuckle images with ...

Researchers have developed a vertical federated deep learning framework using a binary manta ray optimization algorithm that selects cancer-related genes ...

Researchers have developed SLAW, a training framework that adapts label smoothing to the sharpness of the loss landscape and reweights ...