tensor decomposition

AntTech

Jan 24, 2025 · Artificial Intelligence

High‑Resolution Hyperspectral Intelligent Fusion Imaging: Background, Key Achievements, and Future Directions

The talk presents a comprehensive overview of high‑resolution hyperspectral intelligent fusion imaging, covering its background, three major research contributions—including tensor‑coupled imaging mechanisms, structured low‑rank tensor models, and model‑guided low‑rank fusion methods—and outlines future research challenges and directions.

AIRemote Sensingfusion imaging

0 likes · 14 min read

High‑Resolution Hyperspectral Intelligent Fusion Imaging: Background, Key Achievements, and Future Directions

Model Perspective

Aug 19, 2023 · Artificial Intelligence

Unlocking Hidden Patterns: How Tensor Decomposition Powers Modern AI

This article introduces tensors and tensor decomposition, explains core operations, explores CP and other factorization methods, and demonstrates Python implementations for music and movie recommendation systems, highlighting how these techniques reveal hidden structures in large‑scale data.

Big DataCP decompositionMachine Learning

0 likes · 15 min read

Unlocking Hidden Patterns: How Tensor Decomposition Powers Modern AI

DataFunSummit

Jun 11, 2022 · Artificial Intelligence

Transforming Regular Expressions into Neural Networks for Text Classification and Slot Filling

This article explains how regular expressions can be converted into equivalent neural network models—FA‑RNN for classification and FST‑RNN for slot filling—by leveraging finite‑state automata, tensor decomposition, and pretrained word embeddings, achieving zero‑shot performance and strong results in low‑resource scenarios.

FA-RNNText Classificationneural networks

0 likes · 17 min read

Transforming Regular Expressions into Neural Networks for Text Classification and Slot Filling

Xiaohongshu Tech REDtech

May 18, 2022 · Artificial Intelligence

Sliding Spectrum Decomposition for Diversified Recommendation in Feed Systems

The paper introduces Sliding Spectrum Decomposition (SSD), a tensor‑based method that quantifies feed diversity through singular‑value volume within sliding windows, integrates quality‑exploration trade‑offs, and employs a hybrid CB2CF model for item embeddings, achieving superior offline and online performance versus DPP in Xiaohongshu’s feed.

Machine Learningdiversityonline A/B testing

0 likes · 10 min read