ALLPCB
Deploy DeepSeek LLM on ELF 2 (RK3588) Development Board
Guide to converting and deploying the DeepSeek LLM on Rockchip RK3588 using RKLLM-Toolkit: environment setup, cross-compilation, model conversion and board deployment.
Common Deep Learning Methods for Small Object Detection
Survey of techniques for small object detection and face detection: image pyramids, FPNs, data augmentation, anchor strategies, SNIP/SNIPER training and context modeling.
AI-RAN Alliance Advances AI Integration in RAN
Overview of the AI-RAN Alliance formed at MWC 2024, its goals to integrate AI into radio access networks for 5G/6G, edge AI deployment, and contrast with OpenRAN.
AIGC basics and industry applications
Overview of AIGC and ChatGPT: technologies, industry chain, applications in text/image/video, e-commerce impact, and prompt engineering best practices.
Fourier Transform Fundamentals and Machine Learning Uses
Explains Fourier transform fundamentals, FFT use in signal processing and machine learning, and Python time-series examples for frequency-domain feature extraction.
EASY EAI Nano-TB (RV1126B) AIoT Board Data Sheet
Technical overview of the EASY EAI Nano-TB AIoT mainboard (RV1126B): quad-core Cortex-A53, up to 3 Tops NPU, dual MIPI CSI, MIPI DSI, dual GbE, WiFi 6, USB, GPIO, Linux SDK.
Visualization Techniques for Machine Learning
Guide to machine learning visualization techniques covering model structure, performance plots (ROC, confusion matrix), feature importance, and practical analysis.
AI in Image Super-Resolution and Upscaling
AI super-resolution and upscaling: GPU and transfer-learning advances, training-data limits, and applications in satellite, medical, gaming, and video-conferencing.
AI Smart Safety Helmet: Passive to Active Protection
Overview of AI smart safety helmet integrating AI vision, vital-sign and environmental sensors for real-time monitoring, alerts, positioning and intelligent management.
OpenAI's Defense Against LLM Attacks
OpenAI's study unveils an instruction hierarchy to boost LLM security against attacks like prompt injections, enhancing model safety.