We deliver AI algorithm tutorials and the latest news, curated by a team of researchers from Peking University, Shanghai Jiao Tong University, Central South University, and leading AI companies such as Huawei, Kuaishou, and SenseTime. Join us in the AI alchemy—making life better!
This tutorial shows how to download NASA GES DISC SO₂ data for the 2022 Hunga Tonga–Hunga Ha'apai eruption, extract relevant fields with H5py, build a Pandas DataFrame, and create both scatter‑plot and time‑varying heat‑map visualizations using Matplotlib, Seaborn and Folium.
This article reviews Ladder Networks and the Γ‑Model for semi‑supervised learning, explains how they minimize supervised and unsupervised costs, presents experimental results on MNIST, CIFAR‑10 and SVHN, and details the Virtual Adversarial Training method with TensorFlow code.
This article introduces FaunaDB, explains how to create a free account and access key, and provides a step‑by‑step Python tutorial that demonstrates creating a collection and performing all CRUD operations with concise code examples.
The article presents DGHL, a deep generative model that uses a ConvNet generator and alternating back‑propagation to learn hierarchical latent factors for online detection of point and subsequence anomalies in multivariate time‑series, handling missing data and achieving state‑of‑the‑art F1 scores on several benchmark datasets.
This article explains how TSDAE, a transformer‑based denoising auto‑encoder, converts noisy job description sentences into robust vector embeddings, details its training process, loss function, dataset preparation, and demonstrates using FAISS for similarity search on the resulting Job2Vec representations.
This tutorial walks a JavaScript‑savvy developer through creating a Rust‑based Apollo Federation GraphQL API, covering project setup with Cargo, required dependencies, async main function, schema and type definitions, federation extensions, and how to run the user and dog sub‑services on separate ports.
This article surveys relation extraction, defining the task, categorizing its five main forms, and detailing key approaches such as entity position encoding, dependency‑tree methods like shortest dependency path and BRCNN, as well as distant supervision with multi‑instance learning and selective attention.
The article introduces three useful C++23 additions—a literal suffix for size_t and ptrdiff_t that ensures portable index types, a multidimensional subscript operator enabling concise matrix element access, and a std::string/std::string_view contains() function that simplifies substring checks—each likely to see frequent use.
This tutorial walks through adding pagination and flexible where‑filters to the User List interface, configuring gqlgen extensions, handling GraphQL errors, wrapping mutations in transactions, and building unit, integration, and end‑to‑end tests for a Go clean‑architecture project using Ent and gqlgen.
This article explains how Intel and Facebook's BF16 support, combined with the Intel Extension for PyTorch (IPEX) and oneDNN, automates type and layout conversions and adds graph‑fusion optimizations, delivering 1.4×‑4.3× inference and up to 2.4× training speedups on Xeon CPUs for models such as DLRM, BERT‑Large, and ResNext‑101‑32x4d.
