Neural Nets

Explore all articles, grouped by publish date.

2026

  1. Model Compression via Knowledge Distillation

    How knowledge distillation compresses teacher models into compact students by transferring behavior and using tailored training objectives for efficient models.

2025

  1. Low-Rank Adaptation (LoRA)

    Explore how Low-Rank Adaptation (LoRA) enables efficient fine-tuning of LLMs through low-rank matrix decomposition and adaptive scaling.

  2. Mixture of Experts - Mathematical Foundations and Scaling

    Explore how Mixture of Experts (MoE) architectures scale LLMs by routing tokens through specialized experts for greater efficiency and performance.

  3. The Equations That Changed The World

    Let us look at equations that shaped the world as we know of today.

  4. DNS Architecture And DNS Records

    In-depth exploration of the OSI model, with code snippets to illustrate each layer's function in networking.

  5. Activation And Loss Functions In Deep Learning

    In this article we explore various Loss and Activation functions in deep learning

  6. AI and the Art of Subtle Control

    Understanding the internal mechanics of LLMs involves exploring tokenization, attention mechanisms, transformers, training, and inference processes.

  7. Data Pipelines And Evolution of ETL vs ELT

    A technical exploration of data pipeline components, governance, and a comparison between ETL and ELT methodologies.

  8. Understanding the Internal Mechanics of LLMs

    Understanding the internal mechanics of LLMs involves exploring tokenization, attention mechanisms, transformers, training, and inference processes.

  9. Data Engineering on Google Cloud Platform (GCP)

    An exploration of the essential components and best practices for data engineering on Google Cloud Platform.