How NTK Adaptive Weighting and Multi‑Scale Fourier Features Enable PINNs to Solve High‑Frequency PDEs

This tutorial explains why standard physics‑informed neural networks fail on high‑frequency partial differential equations due to spectral bias, and demonstrates how random Fourier feature embeddings, multi‑scale concatenation or spatio‑temporal separation, and Neural Tangent Kernel‑based adaptive loss weighting together overcome the bias and achieve accurate, stable solutions for heat, Poisson, and wave equations using JAX.

Fourier FeaturesJAXMulti-Scale

0 likes · 23 min read

How NTK Adaptive Weighting and Multi‑Scale Fourier Features Enable PINNs to Solve High‑Frequency PDEs

Bighead's Algorithm Notes

Nov 16, 2025 · Artificial Intelligence

COGRASP: Multi‑Scale Stock Price Prediction Using Co‑Occurrence Graphs

This article reviews the COGRASP method, which builds dynamic co‑occurrence graphs from online sources, embeds them with graph neural networks, extracts short, medium, and long‑term patterns via attention‑based LSTMs, and aggregates these signals to achieve state‑of‑the‑art stock price prediction performance on real‑world CSI‑300 data.

ALSTMFinancial AIGraph Neural Network

0 likes · 14 min read

COGRASP: Multi‑Scale Stock Price Prediction Using Co‑Occurrence Graphs

Alibaba Cloud Big Data AI Platform

May 30, 2024 · Artificial Intelligence

How Pathformer Redefines Multi-Scale Time Series Forecasting with Adaptive Pathways

Pathformer, a new multi‑scale Transformer model introduced by Alibaba Cloud’s big‑data team and East China Normal University, leverages adaptive pathways to jointly model time resolution and time distance, achieving state‑of‑the‑art forecasting performance and strong generalization across cloud resource workloads and public datasets.

Multi-ScaleTransformeradaptive pathways

0 likes · 7 min read

How Pathformer Redefines Multi-Scale Time Series Forecasting with Adaptive Pathways

AntTech

Nov 7, 2023 · Artificial Intelligence

Multi‑Scale Stochastic Distribution Prediction for User Behavior Representation Learning

The paper proposes a multi‑scale stochastic distribution prediction (MSDP) framework that learns robust user behavior representations by predicting behavior distributions over random time windows, incorporates contrastive regularization, and demonstrates superior performance on both proprietary financial risk data and a public e‑commerce dataset compared with existing masked and next‑behavior pre‑training methods.

Multi-Scaleaidistribution prediction

0 likes · 13 min read

Multi‑Scale Stochastic Distribution Prediction for User Behavior Representation Learning

TiPaiPai Technical Team

Aug 2, 2021 · Artificial Intelligence

How Attention Boosts Text Recognition: From CNN‑Seq2Seq to Multi‑Scale Models

This article explains how attention mechanisms are applied to text recognition, covering the basic CNN‑Seq2Seq‑Attention architecture, multi‑scale attention extensions, and a 2D attentional irregular scene text recognizer with detailed network components, training loss, and experimental results.

CNNComputer VisionDeep Learning

0 likes · 8 min read

How Attention Boosts Text Recognition: From CNN‑Seq2Seq to Multi‑Scale Models