Tagged articles

121 articles

Page 2 of 2

Jun 7, 2018 · Artificial Intelligence

Upgrading HED Edge Detection to TensorFlow 1.7: Refactored Code and New Layer Techniques

This tutorial walks through rewriting the HED edge‑detection network for TensorFlow 1.7, covering deprecated API fixes, migration from TF‑Slim to tf.layers, matrix initialization, batch normalization nuances, and a comprehensive review of convolution variants such as 1×1, depthwise, separable, and dilated convolutions, plus guidance on transposed convolutions and modern architectures like ResNet and Inception.

Batch NormalizationCNNConvolution

0 likes · 24 min read

Upgrading HED Edge Detection to TensorFlow 1.7: Refactored Code and New Layer Techniques

Alibaba Cloud Developer

May 14, 2018 · Artificial Intelligence

How to Build Real-Time Voice Recognition on Mobile with TensorFlow Lite

This article explains how to implement client‑side human voice recognition on mobile devices using TensorFlow Lite, detailing the mel‑spectrogram feature extraction, algorithmic optimizations such as ARM instruction set and multithreading, model selection with Inception‑v3 CNN, training procedures, and deployment steps.

CNNMel SpectrogramTensorFlow Lite

0 likes · 16 min read

How to Build Real-Time Voice Recognition on Mobile with TensorFlow Lite

JD Tech

May 4, 2018 · Artificial Intelligence

Optical Flow: Principles, Methods, and Applications in Computer Vision

This article introduces the fundamentals and evolution of optical flow, covering classic algorithms such as Horn‑Schunck and Lucas‑Kanade, modern deep‑learning approaches like FlowNet, and their practical applications in video detection, semantic segmentation, and novel view synthesis.

CNNDeep LearningImage Processing

0 likes · 15 min read

Optical Flow: Principles, Methods, and Applications in Computer Vision

Ctrip Technology

May 2, 2018 · Artificial Intelligence

Document OCR: From Computer Vision Fundamentals to Ctrip's Full-Text OCR Implementation

This article explains the evolution of optical character recognition, outlines the complete OCR processing pipeline—including image input, preprocessing, binarization, noise removal, tilt correction, layout analysis, character segmentation, recognition, and post‑processing—while showcasing Ctrip's real‑world OCR project, its architecture, accuracy metrics, and key computer‑vision techniques such as CNN, HSV, HOG, LBP, and Haar features.

CNNComputer VisionImage Processing

0 likes · 13 min read

Document OCR: From Computer Vision Fundamentals to Ctrip's Full-Text OCR Implementation

Xianyu Technology

Apr 26, 2018 · Artificial Intelligence

Client‑Side Image Similarity Computation: Methods, Experiments, and Findings

This study compares hash‑based, CNN‑based, and local‑feature methods for client‑side image similarity detection in e‑commerce, showing that while hash methods are fast and CNNs are accurate but costly, the Hessian‑Affine detector combined with SIFT descriptors delivers the optimal balance of computational efficiency, robustness to transformations, and high recall/precision for on‑device duplicate filtering.

CNNMobile ComputingSIFT

0 likes · 11 min read

Client‑Side Image Similarity Computation: Methods, Experiments, and Findings

Tencent TDS Service

Mar 15, 2018 · Artificial Intelligence

Step-by-Step TensorFlow Setup on Windows and Build MNIST CNN from Scratch

This guide walks you through installing Anaconda, creating a TensorFlow virtual environment on Windows, configuring CPU and GPU versions, and implementing both a basic softmax regression and a deep convolutional neural network for MNIST digit recognition, complete with code snippets, training tips, and visualization tools.

AnacondaCNNDeep Learning

0 likes · 21 min read

Step-by-Step TensorFlow Setup on Windows and Build MNIST CNN from Scratch

Tencent Cloud Developer

Mar 13, 2018 · Artificial Intelligence

TensorFlow MNIST Tutorial: Environment Setup, Softmax Regression, and CNN Implementation

This beginner‑friendly TensorFlow tutorial by Chen Yidong walks readers through Windows environment setup, explains TensorFlow’s graph‑execution model, and demonstrates both softmax linear regression and a deep convolutional neural network for MNIST, while also covering utility scripts, TensorBoard visualization, and CPU/GPU or multi‑GPU deployment.

CNNGPUMNIST

0 likes · 13 min read

TensorFlow MNIST Tutorial: Environment Setup, Softmax Regression, and CNN Implementation

Baobao Algorithm Notes

Feb 28, 2018 · Artificial Intelligence

Mastering Text Classification: From TF‑IDF to Word Embeddings and Deep Learning

This article provides a comprehensive guide to text classification, covering traditional pipelines, bag‑of‑words and TF‑IDF features, dimensionality‑reduction techniques, word‑embedding models such as GloVe, word2vec and fastText, and modern deep‑learning architectures like CNN, RCNN and HAN.

CNNDeep LearningNLP

0 likes · 9 min read

Mastering Text Classification: From TF‑IDF to Word Embeddings and Deep Learning

Architecture Digest

Feb 24, 2018 · Artificial Intelligence

Eight Neural Network Architectures Every Machine Learning Researcher Should Know

This article explains why machine learning is essential for complex tasks, defines neural networks, outlines three reasons to study them, and provides concise overviews of eight fundamental neural network architectures—including perceptron, CNN, RNN, LSTM, Hopfield, Boltzmann machines, deep belief networks, and deep autoencoders—grouped by their structural categories.

AI architecturesCNNDeep Learning

0 likes · 23 min read

Eight Neural Network Architectures Every Machine Learning Researcher Should Know

Meituan Technology Team

Feb 2, 2018 · Mobile Development

WhereAreYou: Mobile AR App for Vehicle Finding Using Core ML and Multi‑CNN Detection

The WhereAreYou hackathon project demonstrates an iOS AR app that visualizes nearby ride‑hailing cars by converting multiple CNN models to Core ML, using ARKit to map GPS bearings, then switching to vision‑based YOLO‑style detection and tracking for real‑time vehicle identification and distance labeling.

ARKitCNNCore ML

0 likes · 16 min read

WhereAreYou: Mobile AR App for Vehicle Finding Using Core ML and Multi‑CNN Detection

58 Tech

Feb 2, 2018 · Artificial Intelligence

Deep Learning Applications in 58.com Intelligent Recommendation System

This article details how 58.com leverages deep learning models such as FNN, Wide&Deep, CNN+DNN, and YouTube DNN recall, along with a custom AI platform, to enhance recommendation ranking and recall, achieving measurable improvements in click‑through rates and overall system performance.

CNNDNNFNN

0 likes · 13 min read

Deep Learning Applications in 58.com Intelligent Recommendation System

Hulu Beijing

Jan 25, 2018 · Artificial Intelligence

How Batch Normalization Accelerates Neural Network Training and Improves Generalization

This article explains the motivation, core principles, and implementation details of Batch Normalization, including how it normalizes each mini‑batch, restores learned feature distributions, and is applied in convolutional neural networks to speed up training and boost model generalization.

Batch NormalizationCNNDeep Learning

0 likes · 6 min read

How Batch Normalization Accelerates Neural Network Training and Improves Generalization

MaGe Linux Operations

Nov 5, 2017 · Artificial Intelligence

How Deep Learning Transforms Modern Face Recognition: From Basics to DeepFace

This article surveys the evolution of face recognition from traditional image‑based methods to real‑time video processing, highlights key researchers and open‑source projects, explains the four‑stage pipeline, details DeepFace's deep‑learning architecture, and provides practical installation and usage instructions for Python developers.

CNNComputer VisionDatasets

0 likes · 21 min read

How Deep Learning Transforms Modern Face Recognition: From Basics to DeepFace

Hujiang Technology

Oct 12, 2017 · Artificial Intelligence

An Overview of Machine Learning and Deep Learning: Definitions, Concepts, and Core Techniques

This article provides a comprehensive introduction to machine learning and deep learning, covering their definitions, classifications, key algorithms, neural network structures, core concepts such as generalization and regularization, and typical architectures like CNN and RNN, illustrated with numerous diagrams.

CNNNeural NetworksRNN

0 likes · 22 min read

An Overview of Machine Learning and Deep Learning: Definitions, Concepts, and Core Techniques

21CTO

Oct 9, 2017 · Artificial Intelligence

How Wukong’s AI Porn Detection System Achieves 99.5% Accuracy

This article explains the challenges of image‑based porn detection, details the multi‑label classification approach of the Wukong system, and reveals the deep‑learning techniques—including CNN evolution, transfer learning, loss functions, adversarial training, and GAN‑based data augmentation—that enable over 99.5% accuracy with massive daily request volumes.

CNNGANImage Classification

0 likes · 18 min read

How Wukong’s AI Porn Detection System Achieves 99.5% Accuracy

21CTO

Sep 30, 2017 · Artificial Intelligence

Top 10 Cutting-Edge Deep Learning Architectures for Computer Vision

This article surveys recent breakthroughs in deep learning for computer vision, explains what constitutes an advanced architecture, outlines common vision tasks, and provides concise overviews plus paper and Keras implementation links for ten influential models such as AlexNet, VGG, ResNet, and GAN.

CNNImage ClassificationKeras

0 likes · 15 min read

Top 10 Cutting-Edge Deep Learning Architectures for Computer Vision

Baidu Intelligent Testing

Sep 20, 2017 · Frontend Development

Applying Deep Learning to Predict Front-End Compatibility Bugs in Mobile Apps

This article explores how deep learning, specifically convolutional neural networks built with Caffe, can be used to automatically detect and predict static UI compatibility bugs such as text overlap in mobile app front‑ends, reducing reliance on manual testing.

CNNCaffeDeep Learning

0 likes · 5 min read

Applying Deep Learning to Predict Front-End Compatibility Bugs in Mobile Apps

High Availability Architecture

Jul 14, 2017 · Artificial Intelligence

Facial Emotion Recognition Using Convolutional Neural Networks: Dataset, Model Architecture, and Evaluation

This article presents a deep‑learning approach for recognizing seven basic human facial expressions using a balanced FER2013 dataset, describes the CNN architecture built with Keras and OpenCV preprocessing, reports training on AWS GPU, and analyzes validation results and visualizations.

AWS GPUCNNComputer Vision

0 likes · 11 min read

Facial Emotion Recognition Using Convolutional Neural Networks: Dataset, Model Architecture, and Evaluation

Tencent TDS Service

May 25, 2017 · Artificial Intelligence

Running a CNN on Mobile: TensorFlow & OpenCV Document Detection Guide

This article walks through a real‑world mobile implementation of a convolutional neural network for document detection, covering problem definition, limitations of traditional OpenCV pipelines, the adoption of a HED edge‑detection network, data preparation, model training, TensorFlow library trimming, and deployment tricks for iOS and Android.

CNNDocument DetectionEdge Detection

0 likes · 23 min read

Running a CNN on Mobile: TensorFlow & OpenCV Document Detection Guide

Qunar Tech Salon

Apr 24, 2017 · Artificial Intelligence

Advances in Image Super-Resolution Using Deep Learning: CNN, GAN, and PixelCNN

Recent advances in image super-resolution leverage deep learning techniques such as convolutional neural networks, residual learning, perceptual loss, generative adversarial networks, and PixelCNN to reconstruct high-resolution details from low-resolution inputs, addressing challenges of scalability, training efficiency, and multi-scale upscaling.

CNNDeep LearningGAN

0 likes · 13 min read

Advances in Image Super-Resolution Using Deep Learning: CNN, GAN, and PixelCNN

Qunar Tech Salon

Dec 5, 2016 · Artificial Intelligence

Understanding Convolutional Neural Networks for OCR and CAPTCHA Recognition

This article introduces the fundamentals of neural networks for image recognition, explains regression vs classification, describes convolution, pooling and fully connected layers, illustrates the classic LeNet‑5 model on the MNIST dataset, and shows how a TensorFlow‑based CNN can be trained to recognize CAPTCHA images, achieving high accuracy.

CNNCaptchaLeNet-5

0 likes · 10 min read

Understanding Convolutional Neural Networks for OCR and CAPTCHA Recognition