Machine Learning by Prakash Jyoti Das

Exoplanet Discoveries: Beyond Our Solar System

prakashjyotidas10 — 2025-03-25 16:35:29 UTC

Reinforcement Learning: The AI learns by trial and error in an environment, getting rewards or penalties based on its actions. It’s less about being told what to do and more about figuring out how to maximize the reward over time. Picture training a dog with treats. Examples: teaching a robot to walk, playing chess against itself.

Introduction

prakashjyotidas10 — 2025-03-25 16:35:29 UTC

Machine learning (ML) is a subset of artificial intelligence (AI) that enables systems to learn from data and make decisions or predictions without being explicitly programmed. Since you’re already working on robotics, deep learning, and RL-based chatbots.

Basics of Machine Learning

prakashjyotidas10 — 2025-03-25 16:35:29 UTC

1) Supervised Learning

prakashjyotidas10 — 2025-03-25 16:35:29 UTC

Supervised Learning: The AI is trained on labeled data, where it’s given both inputs and the correct outputs. It learns to make predictions or decisions by finding patterns that connect the inputs to the outputs. Think of it like a teacher guiding a student with a answer key. Examples: spam email detection, predicting house prices.

2) Unsupervised Learning

prakashjyotidas10 — 2025-03-25 16:35:29 UTC

Unsupervised Learning: The AI gets no labels or guidance—just raw data. It tries to figure out patterns or structures on its own, like grouping similar items or finding hidden relationships. It’s like exploring a messy room without a map. Examples: clustering customers for marketing, detecting anomalies in data.