Geometric deep learning: AI beyond text & images
Discover how Geometric Deep Learning revolutionizes AI by processing complex, non-Euclidean data structures, enabling breakthroughs in drug discovery, 3D modeling, and network analysis.
Home
Kevin Vu
Selecting the right model to maximize AI training efficiency
Unlock AI training efficiency: Learn to select the right model architecture for your task. Explore CNNs, RNNs, Transformers, and more to maximize performance.
5 tips for fine-tuning LLMs
Master LLM fine-tuning with expert tips on data quality, model architecture, and bias mitigation. Boost performance and efficiency in AI development.
How to accelerate prototyping in manufacturing product design
Discover strategies to accelerate prototyping in manufacturing product design. Learn about AI integration, optimized hardware, 3D printing, and AR/VR technologies for efficient product development.
Chain of Thought prompting for LLMs
Explore chain-of-thought prompting for LLMs, its impact on problem-solving, and how it improves AI performance in math and reasoning tasks.
How to improve the performance of a RAG model
Optimize Retrieval-Augmented Generation (RAG) models by enhancing vectorization, utilizing multiple data sources, and choosing the right language model for improved performance.
History and Future of LLMs
LLMs are marvels of modern technology. They’re complex in their function, massive in size, and enable groundbreaking advancements. Go over the history and future of LLMs.
Why the newest LLMs use a MoE (Mixture of Experts) architecture
Mixture of Experts (MoE) architecture is defined by a mix or blend of different “expert” models working together to complete a specific problem.
How Retrieval Augment Generation (RAG) makes LLMs smarter than before
By feeding LLMs the necessary domain knowledge, prompts can be given context and yield better results. RAG can decrease hallucination along with several other advantages.
Quantization and LLMs – Condensing models to manageable sizes
The scale and complexity of LLMs The incredible abilities of LLMs are powered by their vast neural networks which are made up of billions of… Read More »Quantization and LLMs – Condensing models to manageable sizes