Tagged articles

11 articles

Page 1 of 1

Mar 24, 2026 · Artificial Intelligence

How PeRCNN Turns Convolution Kernels into Differential Operators for Physics‑Informed Learning

PeRCNN embeds physics directly into its architecture by replacing additive nonlinearities with element‑wise multiplication in Π‑blocks, enabling convolution kernels to act as finite‑difference operators, which yields superior forward and inverse PDE solving, accurate coefficient identification, robust equation discovery, and interpretable models, as demonstrated on multiple reaction‑diffusion benchmarks.

Deep LearningPeRCNNconvolutional neural network

0 likes · 22 min read

How PeRCNN Turns Convolution Kernels into Differential Operators for Physics‑Informed Learning

Qborfy AI

Jul 1, 2025 · Artificial Intelligence

Why CNNs Outperform Fully Connected Networks: A Deep Dive into Architecture and Applications

This article explains the fundamentals of convolutional neural networks (CNNs), detailing their definition, advantages over fully connected networks, architectural components such as input, hidden, and output layers, key operations like convolution, pooling, and activation, and showcases practical applications and notable insights.

CNNComputer VisionDeep Learning

0 likes · 5 min read

Why CNNs Outperform Fully Connected Networks: A Deep Dive into Architecture and Applications

ITPUB

Mar 13, 2024 · Artificial Intelligence

From AlphaGo to ChatGPT: Unraveling the Secrets Behind Modern AI Breakthroughs

This article walks readers through the evolution of artificial intelligence—from early expert systems and machine learning basics to convolutional neural networks, the AlphaGo series, MuZero's rule‑free learning, and the generative power of large language models like ChatGPT—highlighting how deep learning, Monte Carlo tree search, and self‑play collaborate to achieve unprecedented performance across games, science, and language.

AIAlphaGoChatGPT

0 likes · 39 min read

From AlphaGo to ChatGPT: Unraveling the Secrets Behind Modern AI Breakthroughs

Rare Earth Juejin Tech Community

Aug 6, 2023 · Artificial Intelligence

Explaining Image Recognition: Logistic Regression and Convolutional Neural Networks

This article introduces the principles of image recognition, compares traditional logistic regression with convolutional neural networks, demonstrates their implementation using Python code, visualizes model weights, and explains key concepts such as padding, convolution, pooling, receptive fields, and multi‑layer feature extraction.

convolutional neural networkexplainable AIimage recognition

0 likes · 12 min read

Explaining Image Recognition: Logistic Regression and Convolutional Neural Networks

DeWu Technology

Jul 18, 2021 · Artificial Intelligence

Deep Learning Techniques for Sentiment Analysis

The article explains how deep‑learning models, particularly convolutional neural networks with token‑level padding, kernel size three, and max‑pooling, can automatically classify e‑commerce product reviews into eight sentiment categories, offering scalable insight for decision‑making and paving the way for recommendation, QA, and risk‑assessment applications.

Deep LearningSentiment Analysisconvolutional neural network

0 likes · 9 min read

Deep Learning Techniques for Sentiment Analysis

Alibaba Cloud Developer

Jul 8, 2019 · Artificial Intelligence

How RAGE Accelerates Accurate Answer Generation for E‑Commerce Q&A

This article introduces the RAGE model, a multi‑layer gated convolutional neural network that leverages review extraction, representation, and fusion to dramatically improve response speed and answer quality for product‑related questions in e‑commerce platforms, outperforming existing seq2seq and attention‑based approaches.

RAGE modelanswer generationconvolutional neural network

0 likes · 18 min read

How RAGE Accelerates Accurate Answer Generation for E‑Commerce Q&A

Alibaba Cloud Developer

Jul 2, 2019 · Artificial Intelligence

How RAGE Boosts E‑Commerce QA with Fast, Accurate Answer Generation

This article presents the RAGE model, a review‑driven answer generation system for e‑commerce that leverages multi‑layer gated convolutional networks, word‑mover's distance comment extraction, and hierarchical attention to dramatically improve response speed, answer relevance, and overall generation quality.

RAGEanswer generationconvolutional neural network

0 likes · 17 min read

How RAGE Boosts E‑Commerce QA with Fast, Accurate Answer Generation

Tencent Cloud Developer

Oct 12, 2018 · Artificial Intelligence

Understanding Convolutional Neural Networks (CNN) with Keras

The article introduces convolutional neural networks, explains core concepts such as convolution, padding, stride, and pooling, demonstrates how to calculate output dimensions, and provides a step‑by‑step Keras example that builds, compiles, and trains a multi‑layer CNN for image classification.

CNNComputer VisionDeep Learning

0 likes · 8 min read

Understanding Convolutional Neural Networks (CNN) with Keras

Tencent Cloud Developer

Mar 21, 2018 · Artificial Intelligence

Abusive Comment Detection Using TextCNN: A Strategy + Algorithm Approach

The article proposes a hybrid approach that first filters blacklist words and then classifies suspicious comments with a character-level TextCNN, achieving around 89% precision and 87% recall, demonstrating that simple convolutional networks outperform keyword filters and RNNs for short, noisy abusive Chinese text.

Abusive Comment DetectionDeep LearningNLP

0 likes · 10 min read

Abusive Comment Detection Using TextCNN: A Strategy + Algorithm Approach

21CTO

Dec 19, 2017 · Artificial Intelligence

How Deep Neural Networks Decode Images: From CNNs to RNNs

This article explains the fundamental principles behind deep neural networks for image recognition, covering convolutional and recurrent architectures, their training processes, feature extraction mechanisms, and the emerging ability to generate automatic image captions.

Deep LearningRecurrent Neural Networkconvolutional neural network

0 likes · 13 min read

How Deep Neural Networks Decode Images: From CNNs to RNNs

dbaplus Community

Oct 12, 2016 · Artificial Intelligence

Mastering Convolutional Neural Networks: Theory, Training, and Implementation

This article provides a comprehensive guide to convolutional neural networks, covering their advantages over fully‑connected nets, architectural patterns, detailed forward and backward calculations, ReLU activation, pooling strategies, Python implementation with NumPy, gradient checking, and a practical MNIST application.

BackpropagationDeep LearningNumPy

0 likes · 22 min read

Mastering Convolutional Neural Networks: Theory, Training, and Implementation