Skip to main content

Filed under

Machine Learning

11 entries

  1. Research 8 min read

    From RouteLLM to Contextual Bandits: How Research Papers Shaped My Model Router

    How I went from naive round-robin model selection to a five-stage routing pipeline backed by RouteLLM, TOPSIS, and LinUCB research. The failures that led to each improvement.

  2. Ethics 20 min read

    Building a Privacy-First AI Lab: Deploying Local LLMs Without Sacrificing Ethics

    Build privacy-first AI lab with local LLMs—run models up to 34B on RTX 3090 (24GB VRAM) with network isolation, traffic monitoring, and real privacy controls.

  3. Robotics 9 min read

    From Claude in Your Terminal to Robots in Your Workshop: The Embodied AI Revolution

    Deploy Vision-Language-Action models for embodied AI robots—integrate physical world interaction with security considerations for homelab automation.

  4. Machine Learning 17 min read

    Fine-Tuning LLMs in the Homelab: A Practical Guide

    Fine-tune LLMs on homelab hardware with QLoRA and 4-bit quantization. Train Llama 3 8B models on RTX 3090 with dataset prep and optimization strategies.

  5. Privacy 6 min read

    Securing Your Personal AI/ML Experiments: A Practical Guide

    Secure personal AI experiments with model isolation and network segmentation—protect LLM deployments using privacy controls and threat modeling.

  6. Raspberry Pi 15 min read

    Privacy-Preserving AI Training Across My Homelab: Federated Learning with Granular-Ball Computing

    Training an image classifier across four homelab devices without sharing raw images—what granular-ball federated learning actually costs in bandwidth, accuracy, and the privacy guarantees it does not give you.

  7. Edge Computing 14 min read

    Running LLaMA 2 on a Raspberry Pi: Memory-Efficient Edge AI with PIPELOAD

    Run LLaMA 2 on Raspberry Pi with PIPELOAD pipeline inference—achieve 90% memory reduction and deploy 7B models on 8GB edge devices at 2.5 tokens/sec.

  8. Research 14 min read

    Multimodal Foundation Models: Capabilities, Challenges, and Applications

    Build multimodal AI systems with GPT-4 Vision and CLIP—process text, images, and audio together for next-generation foundation model applications.

  9. Edge Computing 45 min read

    AI Learning in Resource-Constrained Environments

    Train AI models on resource-constrained hardware with quantization, pruning, and distillation—run GPT-3 capabilities 100x faster through compression.

  10. Machine Learning 16 min read

    Retrieval Augmented Generation (RAG): Enhancing LLMs with External Knowledge

    Build RAG systems with vector databases and semantic search—eliminate LLM hallucinations and ground responses in verified knowledge for trustworthy AI.

  11. Machine Learning 15 min read

    The Transformer Architecture: A Deep Dive

    Master transformer architecture with self-attention and positional encoding—understand the foundation of GPT-4, BERT, and modern language models.