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!
The article explains Shannon information content, entropy, cross‑entropy, KL‑divergence, conditional entropy and mutual information, illustrating each concept with coin‑flip and dice examples, visual formulas, and discusses their roles as loss functions and evaluation metrics in machine‑learning models.
This article explains how to convert a TensorFlow image‑classification model to TensorFlow Lite, apply different quantization techniques, benchmark the resulting models on a Raspberry Pi 4, and compare latency, size, and accuracy to demonstrate the trade‑offs of edge AI deployment.
This tutorial walks through the theory and implementation of Neural Radiance Fields (NeRF) in PyTorch, covering positional encoding, the MLP architecture, differentiable volume rendering, hierarchical sampling, training tricks, and references to the original research.
This article explains how HTTPS combines HTTP with SSL/TLS, walks through the TLS handshake steps, describes symmetric and asymmetric encryption, the role of X.509 certificates, digital signatures, certificate chains, and provides a hands‑on OpenSSL guide for manually verifying a server certificate.
This article walks through creating a Linux packet sniffer that bypasses libpcap, explains PF_PACKET raw sockets, shows how to bind to a specific interface, enable promiscuous mode, attach a BPF filter compiled with tcpdump, and parse Ethernet and IP headers in a continuous receive loop.
The article walks through creating a lightweight, extensible Node.js command‑line utility without third‑party libraries, covering the command‑pattern design, implementation of split, upper, and word‑count commands, dynamic command loading, and best practices for modular, maintainable CLI development on Linux.
The article explains how to train robots to learn tasks directly from raw video using model-based reinforcement learning, covering POMDP formulation, CNN auto‑encoders, latent‑space representations, iLQR optimization, and a step‑by‑step pipeline with concrete examples and references.
This article walks through building the first stage of an open‑source MLOps pipeline—data ingestion and storage—by outlining requirements, selecting tools such as Argo Workflows, Minio and Great Expectations, showing how to set up a minikube cluster, and providing Python scripts and an Argo CronWorkflow to extract, transform, and load OpenAQ air‑quality data into Minio.
This guide walks through setting up Docker on a Windows or Linux host, enabling Nvidia GPU support via the Container Toolkit, pulling a TensorFlow GPU image, launching a Jupyter Notebook server inside the container, and connecting it to Google Colab for deep‑learning training.
The article explains how transfer learning reduces data and time requirements in deep learning by reusing pretrained models for vision, natural language processing, and reinforcement learning, while discussing challenges such as overfitting, the need for progressive networks, entropy regularization, domain adaptation, multi‑task learning, and model distillation.
