AI Lesson 47 – CNN Basics(Convolutions Nets) | 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

Regularization

Regularization is a technique used to prevent machine learning models from becoming too complex. It helps control overfitting by discouraging the model from relying too heavily on any single feature.

When a model becomes too flexible, it starts memorizing training data instead of learning general patterns. Regularization adds a penalty that keeps the model simpler and more stable.

Why Regularization Is Needed

Complex models can fit training data extremely well but fail on new data. Regularization limits this behavior and improves generalization.

  • Prevents overfitting
  • Improves generalization
  • Controls model complexity
  • Stabilizes learning

Real-World Connection

Think of studying for an exam. If you memorize every question exactly, you may fail when questions change slightly. Regularization is like focusing on core concepts instead of memorization.

How Regularization Works

Regularization adds an extra term to the loss function that penalizes large model weights. This forces the model to keep weights small and balanced.

L1 Regularization (Lasso)

L1 Regularization adds the absolute value of weights to the loss function. It can reduce some weights to zero, effectively performing feature selection. 


from sklearn.linear_model import Lasso
import numpy as np

X = np.array([[1, 1], [2, 2], [3, 3]])
y = np.array([1, 2, 3])

model = Lasso(alpha=0.1)
model.fit(X, y)

print(model.coef_)
[0.85 0. ]

One feature weight becomes zero, meaning it is removed from the model.

L2 Regularization (Ridge)

L2 Regularization adds the squared value of weights to the loss function. It shrinks weights but does not remove them completely. 


from sklearn.linear_model import Ridge

model = Ridge(alpha=1.0)
model.fit(X, y)

print(model.coef_)
[0.45 0.45]

Both features are retained but their influence is reduced evenly.

L1 vs L2 Regularization

  • L1 removes irrelevant features
  • L2 reduces feature influence smoothly
  • L1 produces sparse models
  • L2 improves numerical stability

Elastic Net Regularization

Elastic Net combines both L1 and L2 regularization. It is useful when there are many correlated features. 


from sklearn.linear_model import ElasticNet

model = ElasticNet(alpha=0.1, l1_ratio=0.5)
model.fit(X, y)

print(model.coef_)
[0.62 0.28]

Elastic Net balances feature selection and weight shrinkage.

When to Use Regularization

  • When dataset is small
  • When model overfits
  • When features are highly correlated
  • When interpretability matters

Practice Questions

Practice 1: What technique prevents overfitting by penalizing complexity?



Practice 2: Which regularization removes features completely?



Practice 3: Which regularization shrinks weights but keeps all features?



Quick Quiz

Quiz 1: Regularization mainly helps reduce?





Quiz 2: Which model uses L1 regularization?





Quiz 3: Which regularization combines L1 and L2?





Coming up next: Decision Trees — how models learn decisions step by step.

← Previous Course Index Next →