deep-learning

Scientific Data, Published online: 25 May 2026; doi:10.1038/s41597-026-07495-7 A High-Resolution Multifocal RGB Pollen Grain Image Dataset for Deep Learning Computer Vision Tasks from Biobío Region, Chile

This paper takes the Turing computability boundary as a meta-axiom and constructs a unified dynamic general equilibrium framework of human-machine symbiosis. We first provide a rigorous mathematical definition of the Universal Turing Machine (UTM) using the standard seven-tuple structure, establish its equivalence to recursive functions and finite formal axiomatic systems, and prove that all cont…

IntroductionMulti-modal image registration leverages complementary information from diverse imaging sources to achieve precise spatial alignment. However, aligning visible (VIS), near-infrared (NIR), and thermal (TH) modalities remains challenging due to appearance differences and limited annotated datasets.MethodsThis study proposes a ResU-Net-inspired framework combining heatmap prediction and …

Diagnosing Alzheimer's disease (AD) is necessary to determine treatment options. AD categorization using machine learning (ML) relies on difficult, manually specified features. The most important stage in AD diagnosis is denoising to restore image stability and quality. An ensemble image denoising technique that combines Attention Guided Convolutional Neural Network (AGCNN), Adaptive Denoising Au…

Scientific Reports, Published online: 25 May 2026; doi:10.1038/s41598-026-54785-6 Lightweight deep learning model for nonconvulsive status epilepticus diagnosis using EEG time–frequency analysis

International audience

International audience

Forthcoming/in press

International audience

Scientific Reports, Published online: 24 May 2026; doi:10.1038/s41598-026-53767-y Research on the application of deep learning-driven urban change detection in sustainable development of hilly-area cities in western China

This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Gemma 4 ships with native function calling built in — trained from scratch, not prompt-engineered. But "built in" and "tuned for your specific tools" are different things. If you have a set of internal APIs, a specific tool schema, or edge-case behaviors that the base model handles inconsistently, fine-tuning on your own function…

Most AI document processing relies heavily on Retrieval-Augmented Generation (RAG). We chunk data into tiny pieces, vectorize it, and stitch the summaries together. RAG is excellent for finding a needle in a haystack, but it is fundamentally flawed when you need the model to understand the entire haystack at once. With the release of Gemma 4, specifically the native 128K context window , we final…

Access to quality tutoring still remains out of reach for millions of students in rural schools, NGO programs, and low-resource educational settings in many parts of the world. Most AI tutoring systems require continuous internet access and cloud infrastructure conditions that simply do not exist in these environments. This paper describes Vedixa, an offline-first adaptive tutoring system built a…

The Matthew Effect Index (MEI) is a new cohort-level effect-size index first developed in serious games analytics, measuring divergence between two cohorts produced by an information-gating mechanism. Like any new measurement instrument, MEI requires principled validation before its readings can be trusted. This primer demonstrates pipeline validation through a battery of five null controls, each…

Stage 1 pre-registration of a no-new-constants forward prediction derived from the UCT compression-interface theorem at d = 5. Predicts the structured readout floor f_U(5) = 24/25 = 0.9600 for U(5)-covariant readout, with primary discriminator f_{Z_2^5} = 31/32 = 0.96875 for sign-channel readout. Contains: theoretical input, prediction and discriminator, five-criterion architecture classifier, mu…

AAFL (Agent-Augmented Framework for Learning) is an instructional systems design framework for the agent era — where AI agents author first drafts and humans serve as Human-in-the-Loop (HITL) judgment-holders, anchored in workplace performance as the organizing outcome.The framework keeps ADDIE's five-phase spine and adds:Eight HITL decision gates (four pedagogical, four production) where human j…

Here is the structured summary entirely in English, optimized for the Zenodo description field: P = NP — The BiT: Bidirectional Information Topology in Quantum-Inspired Computation Abstract This work proposes a structural and architectural reinterpretation of the P versus NP problem through Bidirectional Information Topology (BiT) (p. 2). Classical computation assumes unidirectional state evoluti…