graph neural networks

Dynamics of a nonlinear Predator–Prey model with intra-specific competition and infected prey using Takagi–Sugeno method and neural network

Automatic grading of HER2 immunohistochemical whole-slide images based on a multi-scale hierarchical graph neural network

Objective The HER2 immunohistochemical (IHC) score of breast cancer is a critical precursor for determining eligibility for anti-HER2 targeted therapy, as the final HER2 status (positive/negative/low) is determined by IHC results combined with FISH confirmation for equivocal 2 + cases according to ASCO/CAP guidelines....

How Far Can We Predict African Crop Yields? A Multimodal Benchmark Across 1,109 Districts and 42 Years

How accurately can we predict crop yields across sub-Saharan Africa using publicly available data? We address this question by establishing the first comprehensive machine learning benchmark on HarvestStat Africa, covering 1,109 administrative districts in 33 countries over 42 years (1981–2022). We engineer 246 feature...

How Far Can We Predict African Crop Yields? A Multimodal Benchmark Across 1,109 Districts and 42 Years

How accurately can we predict crop yields across sub-Saharan Africa using publicly available data? We address this question by establishing the first comprehensive machine learning benchmark on HarvestStat Africa, covering 1,109 administrative districts in 33 countries over 42 years (1981–2022). We engineer 246 feature...

DSTGAT: A Spatio-Temporal Dynamic Graph Attention Network for User Activity Recognition

A dynamic graph learning module based on Gumbel-Softmax sampling is proposed to adaptively reconstruct the sensor adjacency matrix and a Talking-Head graph attention mechanism is employed to facilitate cross-head feature interaction, enhancing global semantic fusion.

AI-Based Optimization of ALU Power Consumption in Modern Computer Architectures

To address the power efficiency bottlenecks and thermal design limits inherent in modern sub-micron microprocessors, this paper introduces an AI-driven optimization framework designed to minimize dynamic and static power dissipation in multi-bit Arithmetic Logic Units (ALUs) without sacrificing operating frequency or t...

marimo-flow

Reactive marimo notebooks for ML experimentation, with MLflow tracking, PINA physics-informed neural networks, and a multi-agent team built on pydantic-graph and Ollama Cloud.

Artificial intelligence in electronic design automation: A review of AI-Assisted Logic Gate Synthesis and Optimization

This paper reviews the application of Artificial Intelligence in Electronic Design Automation, focusing on AI-driven logic gate synthesis and optimization. It discusses Graph Neural Networks, Reinforcement Learning, and Large Circuit Models, along with their applications, benefits, challenges, and limitations in electr...

AI-Driven Logic Synthesis and Optimization in Modern Electronic Design Automation: From Learned Heuristics to Generative Circuit Design

AbstractThe exponential growth in integrated circuit (IC) complexity, combined with tight power, performance and area (PPA) limits, has strained traditional Electronic Design Automation (EDA) techniques. Classical logic synthesis relies on hand-engineered heuristics whose runtime and solution quality struggle to scale...

Postmodern Physics of Hamzah Information.(311)

.. استدلال ۲۱ از ۱۰۰: مغالطه‌ی چرخه‌های پژواک شناختی و فروپاشی الگوریتم‌های فیلترینگ مشارکتی در شبکه‌های اجتماعی ($\text{The Cognitive Echo Chamber Fallacy and Collaborative Filtering Collapse in Social Networks}$) ۱. مقدمه و طرح صورت تفصیلی فوق‌تخصصی معما ($\text{Echo Chamber Paradox Setup}$) در تمامی چارچوب‌های سنتی...

Can Machine Learning Predict Solvation Effects on Energies and Geometries of Highly Charged Molecules?

This work systematically investigates which model architectures and architectural components are required to predict solvation energies and corresponding forces for molecules with total charges ranging from −5 to +5, and shows that an explicit and robust treatment of molecular charge is essential for reliable performan...

Spatiotemporal quench prediction of No-Insulation superconducting coils using a GNN-Informer fusion model

Abstract Quench prediction is essential for the safe operation of no-insulation high-temperature superconducting coils in fusion magnet systems. This study proposes a spatiotemporal quench prediction model that integrates a Graph Neural Network with Informer to fuse multi-sensor spatial correlations and long-term tempo...