ALLPCB
Building Graph Neural Networks with PyTorch
Overview of graph neural networks, graph basics and NetworkX graph creation, GNN types and challenges, plus a PyTorch spectral GNN example for node classification.
PixelLM: First Efficient Pixel-Level Inference Model Without SAM
PixelLM is an efficient pixel-level multimodal large model for open-domain multi-object reasoning segmentation without SAM, accompanied by the MUSE dataset.
Building a Sustainable AI Ecosystem with Smaller LLMs
Analysis of LLM model scale, hardware and cost trade-offs, showing how smaller models and cloud-native CPUs improve inference efficiency and sustainability.
What foundational devices do AI chips require?
Tsinghua's Future Chip Forum recap: Wei Shaojun outlines constraints for zettascale systems, device needs and prospects for 3D integration.
Deep Learning Advances in Polarization Image Fusion
Comprehensive review of polarization image fusion and deep learning methods (CNN, GAN), traditional algorithms, datasets, applications, and future research directions.
What Is AI Computation and How Does It Work?
AI overview with latent space representations and practical applications in manufacturing and semiconductor manufacturing, including predictive maintenance and quality assurance.
3U VPX XCZU47DR 8-Channel RF Transceiver Module
VPX361 8-channel RF transceiver using Xilinx Zynq UltraScale+ XCZU47DR SoC: eight 14-bit ADCs/DACs up to 6 GHz, 25 Gbps GTY backplane, DDR4/eMMC memory for radar and EW.
CNN for SAR Target Classification
Explore how CNNs enhance SAR target classification with advanced deep learning techniques for accurate, all-weather target identification.
CNN Image Classification Strategy
Explains how BagNets show ImageNet classification relies on local bag-of-features strategies, revealing CNN texture bias, patch-based evidence and robustness issues.
Simplifying Transformer Blocks
Simplifying Transformer blocks by removing skip connections, projections and normalization; introduces Simplified Attention to reduce parameters and raise training throughput.
Analog Devices MAX78002 AI Microcontroller Datasheet
Overview of the Analog Devices MAX78002 AI microcontroller - ultra-low-power dual-core MCU with power management and edge inference use cases for battery-powered devices.
Survey of LLM Inference on Tabular Data
Survey of table inference using large language models: tasks, datasets, methods (fine-tuning, in-context learning, tools), benchmarks and future research directions.
DeepPointMap: LiDAR SLAM Framework Using Deep Learning
DeepPointMap is a LiDAR SLAM framework using sparse neural descriptors for memory-efficient map representation and multi-scale localization including odometry and loop closure.
Renesas RZ/V2L Pretrained AI Model
RZ/V2L MPU with DRP-AI overview and pretrained plant leaf disease classification model; runtime modes, hardware/software requirements, and inference performance.
PCB Design for WT3000A-M6 Voice Module in Smart Toys
PCB implementation guide for smart toy hardware with WT3000A-M6 voice module: system architecture, audio capture, RF matching, power management, layout and safety.
Advances in Deep Learning for Polarimetric Imaging
Overview of deep learning-based polarimetric imaging methods for de-scattering and denoising in complex environments, with model embedding and future directions.
GPT and Neural Networks: Underlying Mechanisms
Technical overview of neural networks and GPT: how images and text are vectorized, forward/backpropagation, gradient descent training, activations, and prediction.
ESD Issues and Circuit Design Measures for Electronic Robots
Practical ESD protection and circuit design guidance for electronic robots: PCB layout, TVS diodes, filtering, grounding, sensor and interface hardening.
How Compute Chips Deliver Performance for ChatGPT
Explains how PCIe and compute cards form the compute foundation for generative AI systems, covering bus roles, testing, reliability, and high-speed interconnects.
Core Principles of Major Machine Learning Models
Survey of machine learning models grouped into six categories: neural networks, symbolic, decision trees, probabilistic, nearest neighbor, and ensemble methods.