feat: Add "What is Machine Learning" page to the handbook (#84)

* adding introduction

* Context added to the introduction to ML page

* fix: replace special character on line 35 in word there's with an apostrophe

* Update index.md

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

* Update docs/disciplines/Machine_Learning/index.md

Co-authored-by: mtran <[email protected]>

---------

Co-authored-by: Katy Scott <[email protected]>
Co-authored-by: mtran <[email protected]>
Co-authored-by: Jermiah Joseph <[email protected]>

docs/disciplines/Machine_Learning/index.md

@@ -1,4 +1,62 @@
+# What is Machine Learning?
 
-# Introduction
+**Machine Learning (ML)** is an approach of using computers to find patterns in data and make predictions or decisions without being explicitly programmed for specific tasks. It uses algorithms to analyze and learn from data to improve performance over time.
+
+## Why Do We Use Machine Learning?
+
+Machine Learning is used because traditional programming methods, which rely on explicitly defining rules for every scenario, are often inefficient or impossible for complex problems. For example, recognizing faces, predicting stock prices, or diagnosing diseases involves patterns too intricate for manual rule-based systems.
+
+Before ML, we relied on statistical methods, manual rule-based algorithms, or human judgment, which had limited scalability and adaptability.
+
+### Advantages of Machine Learning
+- **Scalability**: ML handles large and complex datasets better than manual methods.
+- **Adaptability**: Models improve automatically as they process more data.
+- **Automation**: ML can automate repetitive tasks, saving time and resources.
+
+### Limitations of Machine Learning
+- **Data Dependency**: Requires large amounts of quality data to perform well.
+- **Black Box Models**: Some ML models lack interpretability, making them hard to trust.
+- **Bias and Errors**: ML can amplify biases present in the data.
+- **High Costs**: Requires computational resources and expertise.
+
+## Where Does Machine Learning Fit in Science?
+
+Machine Learning is an interdisciplinary field at the intersection of:
+
+- **Computer Science**: Provides algorithms and computational power.
+- **Statistics**: Forms the mathematical foundation for analyzing and interpreting data.
+- **Artificial Intelligence (AI)**: ML is a subset of AI focused on learning from data.
+- **Deep Learning (DL)**: A specialized branch of ML that uses neural networks to process large amounts of data.
+
+ML integrates concepts from these fields to solve diverse problems in areas like biology, finance, healthcare, and engineering.
+
+## When Should We Use Machine Learning?
+
+### Appropriate Use Cases
+- When there's a need to analyze large datasets for complex patterns.
+- When the problem requires automation or decision-making without explicit programming.
+
+### When We Should Avoid Machine Learning
+- When data is insufficient or of poor quality.
+- When simpler, rule-based systems can solve the problem more effectively.
+- When interpretability is critical, and black-box methods aren't acceptable.
+
+## Categories and Branches of Machine Learning
+
+ML is broadly divided into three main categories:
+
+1. **Supervised Learning**:
+
+    - Models are trained on labeled data (input-output pairs).
+    - Examples: Linear regression, support vector machines (SVMs).
+
+2. **Unsupervised Learning**:
+
+    - Models learn patterns from unlabeled data.
+    - Examples: Clustering (e.g., k-means), dimensionality reduction (e.g., PCA).
+
+3. **Reinforcement Learning**:
+
+    - Models learn by interacting with an environment and receiving rewards or penalties.
+    - Examples: Markov decision process (MDP), Deep Q Networks (DQN).
 
-TODO:: Add a short description here