---
title: "Muhammad Fahad Bashir (@mfahadbashir) | Hashnode"
description: "Software engineer by day, AI and ML explorer by night. Read the latest articles by Muhammad Fahad Bashir on Hashnode."
url: "https://hashnode.com/@mfahadbashir"
---

@mfahadbashir

# Muhammad Fahad Bashir

@mfahadbashir · Dera Ghazi Khan,Paksitan · Joined July 2024

Software engineer by day, AI and ML explorer by night

[Website](https://muhammadfahd.github.io/)

### [Q-Learning in Practice: Understanding the Update Equation with One Simple Example](https://ml-diaries-by-fahd.hashnode.dev/q-learning-in-practice-understanding-the-update-equation-with-one-simple-example?utm_source=hashnode&utm_medium=feed)

In the previous article, we built the intuition behind Q-Learning. We learned that an agent improves its decisions through trial and error, stores its experience in a Q-table, and gradually discovers

8 min read · [ml-diaries-by-fahd.hashnode.dev](https://ml-diaries-by-fahd.hashnode.dev/q-learning-in-practice-understanding-the-update-equation-with-one-simple-example?utm_source=hashnode&utm_medium=feed)

[Jul 22](https://hashnode.com/posts/q-learning-in-practice-understanding-the-update-equation-with-one-simple-example/6a6085b4d9225b63fb150e71)

### [Q-Learning: How an Agent Learns From Rewards — Intuition First, No Math](https://ml-diaries-by-fahd.hashnode.dev/q-learning-how-an-agent-learns-from-rewards-intuition-first-no-math?utm_source=hashnode&utm_medium=feed)

In the previous article of this series, Reinforcement Learning: The Big Picture, we explored how reinforcement learning differs from supervised and unsupervised learning. We discussed the interaction

10 min read · [ml-diaries-by-fahd.hashnode.dev](https://ml-diaries-by-fahd.hashnode.dev/q-learning-how-an-agent-learns-from-rewards-intuition-first-no-math?utm_source=hashnode&utm_medium=feed)

[Jul 6](https://hashnode.com/posts/q-learning-how-an-agent-learns-from-rewards-intuition-first-no-math/6a4b985bc9c3a0c19248f30f)

### [Reinforcement Learning: The Big Picture](https://ml-diaries-by-fahd.hashnode.dev/reinforcement-learning-the-big-picture?utm_source=hashnode&utm_medium=feed)

Reinforcement Learning: Agents learn via environment interaction, foundational concepts, and real-world applications

4 min read · [ml-diaries-by-fahd.hashnode.dev](https://ml-diaries-by-fahd.hashnode.dev/reinforcement-learning-the-big-picture?utm_source=hashnode&utm_medium=feed)

[Jan 19](https://hashnode.com/posts/reinforcement-learning-the-big-picture/696e4eff0c86a2770a7db384)

### [Apriori Algorithm — Learning Association Rules the Simple Way](https://ml-diaries-by-fahd.hashnode.dev/apriori-algorithm-learning-association-rules-the-simple-way?utm_source=hashnode&utm_medium=feed)

Apriori Algorithm finds patterns and associations in data for market basket analysis and recommendation systems in unsupervised learning

4 min read · [ml-diaries-by-fahd.hashnode.dev](https://ml-diaries-by-fahd.hashnode.dev/apriori-algorithm-learning-association-rules-the-simple-way?utm_source=hashnode&utm_medium=feed)

[Jan 16](https://hashnode.com/posts/apriori-algorithm-learning-association-rules-the-simple-way/6969b4cbb606e093bf696494)

### [PCA Explained Simply: Understanding Dimensionality Reduction](https://ml-diaries-by-fahd.hashnode.dev/pca-explained-simply-understanding-dimensionality-reduction?utm_source=hashnode&utm_medium=feed)

Principal Component Analysis (PCA) reduces dimensionality, simplifying high-dimensional data while retaining essential information

6 min read · [ml-diaries-by-fahd.hashnode.dev](https://ml-diaries-by-fahd.hashnode.dev/pca-explained-simply-understanding-dimensionality-reduction?utm_source=hashnode&utm_medium=feed)

[Jan 12](https://hashnode.com/posts/pca-explained-simply-understanding-dimensionality-reduction/69653f538a4ecede34eb537a)
