Machine Learning - ML Archives - A.R. ZERINA.R. ZERIN

AI Machine Learning - ML Statistics

Gaussian Distribution Made Simple: A Beginner-Friendly Guide for Anomaly Detection

August 20, 2026

A Gaussian distribution is also called: Gaussian Distribution = Normal Distribution = Bell-Shaped Distribution They all mean the same thing. 1. What Is a Gaussian Distribution? A Gaussian distribution describes data where: Most values are close to the average, while values become less common as we move farther away from the average. For example, imagine […]

AI LLM Machine Learning - ML

From SFT to GRPO: A Practical Guide to Modern LLM Fine-Tuning, Alignment, PEFT, LoRA and QLoRA

ZERIN

August 20, 2026

DPO, Fine Tuning, GRPO, Lora, PEFT, PPO, QLora, SFT

Large Language Models do not become specialized, aligned, or reasoning-focused through a single training technique. When working with models such as Qwen, Llama, Mistral, or other open-weight LLMs, we encounter terms such as: SFT, DPO, PPO, GRPO, PEFT, LoRA, and QLoRA. At first, these can look like competing fine-tuning methods. They are not. Some define […]

AI Machine Learning - ML

TensorFlow Activation Functions

ZERIN

August 7, 2026

Activation Functions

The Most Important Memory Rule Memorize this: Hidden layers → ReLU Binary classification → Sigmoid Multiclass classification → Softmax Multilabel classification → Sigmoid Regression → Linear An even easier memory sentence is: ReLU inside, Sigmoid for yes/no, Softmax for one-of-many, Sigmoid for many-of-many, Linear for numbers. 1. ReLU: The Default Choice for Hidden Layers ReLU […]

AI Machine Learning - ML NLP

Which Activation Function Should You Use in NLP? A Practical Guide from Text Classification to LLM Text Generation

ZERIN

August 7, 2026

Choosing the correct activation function in NLP can be confusing because different NLP problems produce very different kinds of outputs. A sentiment classifier, a spam detector, a named entity recognition model, and a large language model may all process text, but they do not necessarily use the same output activation. The easiest way to remember […]

AI Machine Learning - ML

How to Detect Overfitting, Underfitting, and Good Fitting from Machine Learning Graphs

ZERIN

August 7, 2026

accuracy, loss graph, overfitting, underfitting

How to Detect Overfitting, Underfitting, and Good Fitting from Machine Learning Graphs

Training a machine learning model is not only about achieving high accuracy. A model can reach 99% training accuracy and still perform badly on new data. To evaluate a model professionally, you need to understand the relationship between: Training accuracy Validation accuracy Training loss Validation loss Test accuracy These metrics help determine whether the model […]

Machine Learning – ML

Categories

Recent Posts