The article chronicles Andrew Ng’s life—from his early education and family background to his pioneering roles at Google, Stanford, and Baidu—highlighting his AI breakthroughs, philosophy on learning, and the launch of deeplearning.ai courses that aim to build an AI‑driven society.
This guide outlines a step‑by‑step learning roadmap for ordinary programmers aiming to become data scientists, covering essential math, statistics, machine learning fundamentals, feature engineering, deep learning resources, open‑source tools, and practical project advice to navigate the AI field effectively.
This article reviews YouTube’s recommendation system research from 2008 to 2016, detailing four development stages—user‑video graph walks, video‑video graph walks, search‑based methods with collaborative filtering, and deep neural networks—highlighting key algorithms, system architectures, and experimental results.
Alibaba’s AI breakthroughs—from a foot‑scanning shopping demo that lets a Google engineer instantly find matching shoes, to a record‑setting vehicle detection model on KITTI and world‑leading OCR for real‑time image review—showcase the power and commercial potential of modern computer‑vision research.
The article summarizes the inaugural Tencent Social Advertising university algorithm contest, highlighting the winning team’s approach, detailed interviews with three top teams, their feature engineering, model choices, challenges faced, and advice for future participants in mobile app conversion rate prediction.
The article details Qunar's development of an AI-powered customer service robot, describing its motivation, data analysis, multi‑phase cognitive system architecture, knowledge‑base management, evaluation mechanisms, and future integration into a group‑wide intelligent service platform to improve service efficiency and reduce costs.
This article surveys major recommendation system techniques—from collaborative filtering and matrix factorization to clustering and deep‑learning approaches like YouTube’s two‑stage neural network—explaining their principles, strengths, and practical considerations for building effective personalized recommenders.
This article examines how deep‑learning‑based AI models, from symbolic and statistical NLP methods to Karpathy's recurrent network, progressively learn to generate Chinese wuxia novels, poetry, and web fiction, revealing both their surprising advances and inherent limitations.
Suning’s Silicon Valley research team presented a novel keyword‑based sentence similarity method at the 9th Web Science conference, highlighting how incorporating keywords, part‑of‑speech, and word position improves chatbot accuracy and efficiency, achieving up to 30% better relevance judgments.
Alibaba’s AI assistant “Ali Xiaomì” is exploring machine reading comprehension to automatically understand e‑commerce rules and product information, leveraging deep learning models and datasets such as SQuAD, bAbI, and MCTest, while addressing challenges of long texts, answer granularity, and real‑world deployment.
This article details the design and implementation of a live‑stream video quality monitoring platform that combines subjective labeling, machine‑learning models, and a multi‑layer architecture to automatically evaluate and alert on video quality across thousands of streams.
The article recaps Liulishuo engineers' experience at Spark Summit 2017, covering Spark 2.2's cost‑based optimizer, production‑ready Structured Streaming, deep‑learning support via UDFs, live demos recognizing James Bond, and insights from vendor booths and industry case studies.
This article compares the most popular open‑source deep‑learning frameworks—including TensorFlow, Caffe, Caffe2, CNTK, MXNet, Torch, PyTorch, Deeplearning4J and Theano—detailing their origins, key features, strengths, weaknesses, ecosystem support, and the trade‑offs between open‑source and proprietary AI solutions.
In an interview at the 2015 HPC User Forum, experts discuss how cloud computing, big data analytics (HPDA), deep learning, and software‑defined architectures are reshaping high‑performance computing and outline emerging trends, challenges, and strategic advice for Chinese HPC vendors.
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.
This article explains how to speed up TensorFlow deep‑learning model training by using a single GPU, configuring session parameters, assigning operations to specific devices, employing multi‑GPU parallelism, and leveraging distributed TensorFlow on Kubernetes, while also discussing synchronous versus asynchronous training modes and practical best practices.
At the 2017 QCon Beijing conference, Suning’s Silicon Valley Research Institute director Jim demonstrated how deep‑learning techniques can transform e‑commerce by vectorizing product data for smarter search relevance and by combining AI models with limited labeled data to build conversational chat‑bot platforms that understand user intent.
Neural Complete, an open‑source project by Pascal van Kooten, trains a neural network to auto‑complete the code of another neural network using LSTM and Keras, demonstrating AI‑driven metaprogramming that could accelerate software development, research, and numerous future applications.
This article reviews the BiCNet framework, a bidirectional coordination network that lets multiple AI agents learn cooperative strategies in StarCraft micro‑battles, achieving state‑of‑the‑art performance across various combat scenarios and demonstrating broad applicability to real‑world multi‑agent tasks.
This article describes a cloud‑based intelligent logistics scheduling platform for food‑delivery services that leverages big‑data analytics, deep‑learning prediction models, and visualisation tools to achieve multi‑objective dynamic optimization, improve dispatch efficiency, and enhance user experience across thousands of cities.
The paper introduces BiCNet, a bidirectional coordination network that learns optimal multi‑agent strategies in StarCraft micro‑battles—ranging from collision‑free movement to complex cover attacks and focused fire—outperforming prior state‑of‑the‑art methods and demonstrating scalable potential for real‑world cooperative AI tasks.
This article explains how improved latency‑controlled BLSTM acoustic models can boost online speech‑recognition accuracy while cutting decoding computation, detailing two model refinements that achieve 40‑60% speed gains with minimal loss in recognition performance.
This article explains how latency‑controlled BLSTM acoustic models were refined to accelerate online speech recognition while preserving accuracy, detailing the training strategy, computational trade‑offs, and two model enhancements that achieve up to 60% faster decoding with modest resource savings.
This interview with Alibaba researcher Xu Yinghui reveals how the company built large‑scale deep reinforcement learning systems for search, recommendation, logistics and online advertising, detailing team structures, technical breakthroughs, training challenges, and future directions such as multi‑agent learning and GAN integration.
Recursive Neural Networks (RNN) extend deep learning to tree and graph structures, using Back‑Propagation Through Structure (BPTS) for training; this article explains their theory, forward and backward computations, implementation details, code snippets, and applications in natural language and scene parsing, while noting practical challenges.
The article outlines the key competencies, responsibilities, and career development advice for data professionals across the entire data stack—from building big‑data platforms and data warehouses to visualization, analysis, algorithm engineering, and deep‑learning applications—emphasizing the importance of creating business value with data.
This article examines the challenges of high‑dimensional sparse features in search ranking, explains why traditional linear models struggle, and describes how deep neural networks with novel encoding schemes and online updates can dramatically improve CTR prediction and real‑time performance.
This article explores how Taobao leverages reinforcement learning, multi‑armed bandits, and reward‑shaping techniques to improve large‑scale e‑commerce search ranking and recommendation, detailing problem modeling, algorithm designs such as Tabular Q‑learning and DDPG, experimental results from Double‑11, and advanced models like GBDT+FTRL and Wide‑&‑Deep.
StarCraft, a classic real‑time strategy game, has become a key testbed for deep reinforcement learning and AI research, and Alibaba's open‑source Gym StarCraft platform now offers Python‑based, TensorFlow‑compatible tools that simplify agent development and evaluation within the OpenAI Gym ecosystem.
The article recounts the author’s experience at AAAI‑2017 in San Francisco, summarizes key talks, panels and award‑winning papers, and details Ctrip’s hybrid collaborative‑filtering model with a stacked denoising auto‑encoder that improves recommendation performance and addresses data sparsity.
This article explores how Alibaba's Taobao leverages reinforcement learning, Markov decision processes, and reward shaping to improve large‑scale product search ranking and recommendation, detailing problem modeling, algorithm designs such as Tabular Q‑learning and DDPG, experimental results, and advanced recommendation models like GBDT‑FTRL and Wide‑Deep.
This article provides a comprehensive guide to Long Short-Term Memory networks, covering their motivation, detailed forward and backward equations, gate mechanisms, training algorithm, gradient checking, and a full C++ implementation, while also introducing the simpler GRU variant.
The article reviews the rapid progress of deep learning at Google, its historical roots, key breakthroughs by researchers like Kurzweil and Hinton, current applications across speech, vision and medicine, and the ongoing challenges of building truly intelligent artificial brains.
The article offers a comprehensive overview of the 2016 NIPS conference in Barcelona, detailing its history, attendance, Hulu’s contributions as presenters and reviewers, key tutorials, invited talks, award-winning papers, symposium highlights, and the broader impact of deep learning and AI advancements.
Ctrip announced that its AI‑driven recommendation system paper, titled “A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems,” has been accepted by the prestigious AAAI conference, highlighting the company’s cutting‑edge deep‑learning techniques, large‑scale deployment, and broader AI innovations in travel services.
This article explains the fundamentals of recurrent neural networks (RNNs), their role in language modeling, various RNN architectures such as bidirectional and deep RNNs, the back‑propagation through time (BPTT) training algorithm, gradient challenges, vectorization techniques, and provides a step‑by‑step code implementation.
The article announces the open‑source release of kaldi‑ctc, a GPU‑accelerated CTC‑based end‑to‑end speech recognition toolkit built on Kaldi, warp‑ctc and cuDNN, highlighting its 5‑6× training speedup, real‑time decoding factor of 0.02, and performance comparisons on the LibriSpeech corpus.
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.
The Interspeech 2016 conference in San Francisco showcased major advances in speech recognition, synthesis, far‑field processing, and language modeling, highlighting CTC extensions, deep CNN innovations, WaveNet’s generative audio, and new techniques for multi‑microphone acoustic modeling.
This article reviews the evolution of automatic question answering systems, outlines their core processing framework, and details how deep neural networks—especially CNNs, RNNs, and DCNNs—enable semantic representation, matching, and answer generation, while also discussing current challenges and future directions.
This article reviews the latest ACL research on deep‑learning‑driven natural‑language processing, covering advances in spoken dialogue policy optimization, retrieval‑based chatbots, information extraction, sentiment analysis, syntactic parsing efficiency, and word‑ and sentence‑vector techniques, highlighting key papers, datasets, and future challenges.
The article reviews the evolution and challenges of deep learning, outlines major commercial platforms such as DistBelief, COTS, and Adam, compares open‑source frameworks like MXNet, TensorFlow and Petuum, and highlights their architectures, performance metrics, and diverse applications ranging from image recognition to recommendation systems.
The article reviews ACL 2016’s tutorial program, summarizing key talks on computer‑aided translation, neural machine translation, semantic sense representation, short‑text understanding, and highlights selected papers on multimodal translation, coverage modeling, and language‑vision grounding, illustrating deep learning’s impact on NLP research.
At the ICML pre‑conference tutorial, experts presented deep residual networks, stochastic gradient methods for large‑scale learning, and deep reinforcement learning, highlighting architectural innovations, optimization theory, noise‑reduction techniques, and practical considerations for building scalable, high‑performance AI models.
Image search, once limited by early CBIR techniques, has surged back thanks to deep learning, offering improved relevance, coverage, scalability, and user experience across applications like e‑commerce, shopping, entertainment, and surveillance, while integrating data, users, models, and systems to bridge the semantic gap.
This article provides a humorous yet informative, non‑mathematical guide to deep learning, covering neural network basics, layer addition, training methods, back‑propagation, unsupervised pre‑training, regularization, ResNet shortcuts, GPU computation, framework choices, and practical advice for applying deep learning to industrial data.
This article presents how deep learning techniques are applied to Sogou's mobile search advertising, detailing the system architecture, feature design, multi‑model fusion strategies, engineering implementation, evaluation metrics, and future directions for improving CTR prediction performance.
On July 23, 2016, Hujiang hosted a technology salon focused on data applications, featuring five expert presentations covering data-driven operations in online education, O2O logistics, e‑commerce recommendation systems, pitfalls in personalization, and deep‑learning‑based image search, accompanied by case studies and visual materials.
The Ctrip Technology Center hosted a deep learning meetup in Shanghai featuring academic and industry experts who presented applications of AI in tourism, advertising, natural language processing, computer vision, knowledge graphs, recommendation systems, and discussed future research directions.
This article breaks down AlphaGo’s four‑part system—policy network, fast rollout, value network, and Monte Carlo Tree Search—explaining their functions, training methods, and how they combine to achieve professional‑grade Go performance, while comparing them with the DarkForest implementation.
This article breaks down AlphaGo’s breakthrough architecture—four specialized neural‑network modules, Monte‑Carlo Tree Search, and deep reinforcement learning—to explain how the system moved from imitation learning to self‑improvement and ultimately defeated top human Go players.
Mobile image search has become a critical user demand, and since its 2014 launch, Alibaba’s Paizhi Tao has evolved through multiple iterations to a robust AI-driven pipeline comprising category prediction, object detection, deep and local image feature extraction, scalable retrieval indexing, and relevance-based ranking.
Mobile visual search, a long‑standing dream, has evolved from early research to a production‑grade system at Pailitao, where a five‑module AI pipeline—category prediction, object detection, feature extraction, indexing, and ranking—enables billions of images to be searched instantly on mobile devices.
The article reviews symbolic knowledge bases such as WordNet, ConceptNet and FrameNet, explains how deep learning replaces them with vector‑based semantic representations, and discusses encoder‑decoder RNNs, attention mechanisms, and future directions for truly understanding language through experiential learning.
This article explores how biometric authentication, especially facial recognition powered by deep‑learning CNNs, is reshaping mobile financial services by enhancing security, improving user experience, and integrating big‑data analytics for risk control.
The article critiques the rapid rise of face‑recognition research by highlighting unfair comparisons, lack of statistical validation, misleading accuracy metrics versus real‑world verification rates, and the hype surrounding deep neural networks, urging a more rigorous and application‑focused evaluation of AI systems.
The article chronicles Facebook's evolution from a social platform into a leading AI research hub, detailing the founding of FAIR, its key personnel, ambitious goals, major projects such as memory networks, embedding world, DeepFace, language technology, and the M assistant, and highlights the open, collaborative nature of its AI work.
This article provides a concise overview of numerous deep learning libraries and frameworks available for Python, Matlab, C++, Java, JavaScript, Lua, Julia, Haskell, .NET, and R, highlighting their main features, language bindings, and typical use cases in artificial intelligence research and development.
The article traces humanity’s long‑standing quest for intelligent machines—from early mechanical curiosities and Turing’s seminal test to modern breakthroughs in deep learning, highlighting how hierarchical feature learning, massive data, and collaborative open‑source efforts are reshaping AI and its future impact.
This guide outlines a comprehensive, step‑by‑step Python learning path for aspiring data scientists, covering environment setup, core language fundamentals, regular expressions, scientific libraries such as NumPy, SciPy, Matplotlib, Pandas, data visualization, machine‑learning with scikit‑learn, and an introduction to deep learning, with curated resources and practice projects.
Baidu's Big Data Machine Learning team, led by Xia Fen, unveiled a suite of five novel algorithms that together allow trillion‑scale feature processing, minute‑level model updates, and up to thousand‑fold efficiency gains in training and inference, dramatically surpassing existing solutions such as Google's billion‑feature systems.
