MT8391 (Genio 720) Specifications for Edge AIoT

Overview of the MediaTek MT8391 (Genio 720) edge AI platform: 6 nm octa-core CPU, 10 TOPS NPU, dual ISPs, LPDDR5 support and multi-interface connectivity for AIoT devices.

Common Deep Learning Applications in AI

Survey of deep learning applications in AI: image recognition, NLP, speech, recommendation systems, autonomous driving, healthcare, cybersecurity, and VR.

How CNNs Solve Edge Detection

Overview of convolutional neural networks: principles like padding, stride, pooling and filters, edge detection fundamentals, architecture patterns and a Keras MNIST implementation.

Random Forest: What It Is and How It Works

Technical overview of random forest algorithms, bagging, bias-variance tradeoffs, and GPU-accelerated implementations (RAPIDS) for faster model training.

Length Extrapolation with Positional Encoding

Survey of length extrapolation approaches analyzing positional encoding methods and their effects on extending model context windows for long-sequence inference.

Parallel Computing and Acceleration Techniques for Neural Networks

Overview of parallel computing and acceleration for neural networks, covering data/model parallelism, GPU/TPU and software optimizations like mixed precision.

Understanding Generative Adversarial Networks (GANs)

Explains how generative adversarial networks (GANs) work and shows step-by-step training of a PyTorch GAN on MNIST, including network design and training loop.

LLM Inference Optimization for NLP Applications

System-level overview of LLM inference optimization, detailing techniques and tradeoffs to improve throughput for Transformer-based large language models.

Deploy DeepSeek-R1 on RK3588 Development Board — Part 1

Technical guide to porting DeepSeek-R1 onto RK3588-based edge hardware: model conversion, cross-compilation, board deployment, and measured CPU, memory, and NPU performance.

Infrared Thermal Imaging in Anti-Drowning Systems

Analysis of infrared thermal imaging for anti-drowning systems: effective for 24/7 perimeter detection in prohibited areas but unsuitable for continuous swimmer tracking.

AI Chip Ecosystem: Analysis and Future Outlook

Analysis of the AI chips ecosystem: technical, commercial, and strategic factors shaping developer affinity, multi?generation platform continuity, and ecosystem influence.

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.

Monocular Vision Methods for Vehicle Distance Estimation

Review of monocular ranging algorithms and imaging geometry for forward collision warning, covering camera pose, lane-width distance estimation and accuracy metrics.

Change Detection in Remote Sensing Using Foundation Models

Time-Traveling Pixels integrates SAM into remote sensing change detection, using low-rank fine-tuning and a Time-Travel Activation Gate to mitigate spatial-semantic domain shift.

Key Factors of Compute for Large AI Models

Concise technical overview of GPU concepts, architecture and GPU vs CPU differences, parallel processing and performance factors for graphics and AI inference.

Benchmarks for Harmlessness Evaluation in the LLM Era

Overview of FFT benchmark: a 2,116-instance evaluation of LLM harmlessness assessing factuality, fairness, and toxicity to reveal model harms and mitigation gaps.

Key Factors in Designing an AI Chip

Review of neural network quantization and numeric formats, covering floating vs integer, block floating point, logarithmic systems, and inference vs training trade-offs.

Future Directions in Lightweight Deep Learning

Review of lightweight deep learning for resource-constrained devices: TinyML, quantization, architectures and deployment strategies for efficient inference.

Machine Learning Algorithms Implemented with NumPy

Detailed review of a 30k-line NumPy machine learning repository implementing 30+ models with explicit gradient computations, utilities, and test examples.

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.