AI Lesson 21 – Introduction to Machine Learning | Dataplexa

AI Course

I. AI Foundations
1. Introduction to AI 2. History of AI 3. AI vs ML vs DL 4. Search Algorithms 5. Intelligent Agents 6. Informed & Uninformed Search 7. Constraint Satisfaction 8. Adversarial Search 9. Logic in AI 10. Planning in AI 11. Knowledge Representation 12. Probabilistic AI 13. Bayesian Networks 14. Markov Models 15. AI Ethics 16. AI Applications 17. Intro to PyTorch 18. Intro to TensorFlow 19. AI Workflows 20. Data for AI
II. Machine Learning
21. Introduction to ML 22. ML Workflow 23. Supervised Learning 24. Unsupervised Learning 25. Reinforcement Learning 26. Linear Regression 27. Logistic Regression 28. SVM 29. Decision Trees 30. Random Forest 31. Gradient Boosting 32. XGBoost 33. K-Means 34. Hierarchical Clustering 35. Dimensionality Reduction 36. Feature Engineering 37. Feature Selection 38. Model Evaluation 39. Overfitting vs Underfitting 40. Cross Validation
III. Deep Learning
41. Intro to Deep Learning 42. Neural Networks 43. Activation Functions 44. Backpropagation 45. Loss & Optimizers 46. Regularization 47. CNN Basics 48. CNN Architectures 49. RNN, LSTM, GRU 50. Seq2Seq 51. Transformers 52. Attention 53. Positional Encoding 54. Training DL 55. Hyperparameter Tuning 56. Transfer Learning 57. Autoencoders 58. GAN Basics 59. GAN Applications 60. Model Serving
IV. Natural Language Processing
61. Intro to NLP 62. Text Processing 63. Tokenization 64. Stopwords & Lemmatization 65. BoW & TF-IDF 66. Word Embeddings 67. Sentence Embeddings 68. NLP Classification 69. Sequence Modeling 70. RNN in NLP 71. Transformers in NLP 72. BERT Basics 73. BERT Fine-tuning 74. RoBERTa & DistilBERT 75. Sentiment Analysis 76. NER 77. Machine Translation 78. Text Generation 79. NLP Evaluation 80. NLP Use Cases
V. Computer Vision
81. Intro to CV 82. Image Processing 83. Filters & Edges 84. Convolutions 85. Object Detection 86. Object Tracking 87. Image Segmentation 88. Face Recognition 89. Feature Detection 90. OCR 91. Image Augmentation 92. Generative Vision 93. Vision Transformers 94. Multimodal Models 95. CV Use Cases
VI. LLM Engineering
96. Intro to LLMs 97. Tokenization 98. LLM Architecture 99. Pretraining 100. Fine-tuning 101. RLHF 102. Prompt Engineering 103. Embedding Models 104. Vector Databases 105. LLM Agents 106. Guardrails & Safety 107. AI in Production 108. End-to-End Project

Introduction to Machine Learning

Artificial Intelligence becomes truly powerful when systems can learn automatically from data instead of being explicitly programmed. This ability to learn is called Machine Learning.

In this lesson, you will understand what Machine Learning really is, why it exists, how it differs from traditional programming, and how machines actually learn from data in real-world systems.

What Is Machine Learning?

Machine Learning (ML) is a subset of Artificial Intelligence that focuses on building systems that improve their performance by learning from data.

Instead of writing rules manually, we provide examples, and the system discovers patterns on its own.

  • Traditional programming uses fixed rules
  • Machine Learning learns rules from data
  • The model improves as more data is provided

Traditional Programming vs Machine Learning

In traditional software development, developers write explicit instructions.

In Machine Learning, developers define the learning process, and the system figures out the logic.

  • Traditional: Rules + Data → Output
  • Machine Learning: Data + Output → Rules (Model)

Real-World Connection

Think about a recommendation system on Netflix or YouTube.

No engineer manually writes rules for every user. Instead, the system learns patterns from millions of viewing histories and automatically predicts what each user might like.

This is Machine Learning working at scale.

How Machines Learn from Data

Machine Learning models learn by identifying relationships between inputs and outputs.

During training, the model makes predictions, measures how wrong it is, and adjusts itself to reduce errors.

This process is repeated many times until the model reaches acceptable performance.

A Simple Learning Example

Below is a very simple example showing how a machine can learn a pattern from data. 


# Simple example of learning from data
data = [(1, 2), (2, 4), (3, 6)]

def predict(x):
    return x * 2

for x, y in data:
    print(predict(x), "expected:", y)
2 expected: 2 4 expected: 4 6 expected: 6

In this example, the system follows a pattern. Real Machine Learning models automatically discover such patterns instead of hardcoding them.

Key Components of Machine Learning

Every Machine Learning system is built using three core components.

  • Data: Examples used for learning
  • Model: Mathematical representation of patterns
  • Learning Algorithm: Method used to update the model

Together, these components allow machines to generalize from examples.

Why Machine Learning Is Needed

Many real-world problems cannot be solved using fixed rules.

  • Speech recognition
  • Image classification
  • Fraud detection
  • Autonomous driving

Machine Learning allows systems to adapt to changing data and environments.

Machine Learning in Real Applications

Today, Machine Learning powers:

  • Email spam filters
  • Search engine ranking
  • Voice assistants
  • Medical diagnosis support

These systems continuously learn and improve over time.

Practice Questions

Practice 1: What is the ability of systems to learn from data called?



Practice 2: What is the most important input for Machine Learning?



Practice 3: What do Machine Learning models learn from data?



Quick Quiz

Quiz 1: Machine Learning is best described as?





Quiz 2: What represents learned patterns in ML?





Quiz 3: Why is ML useful?





Coming up next: Machine Learning Workflow — understanding how ML projects move from data to deployment step by step.

← Previous Course Index Next →