AI Lesson 48 – Popular CNN Architectures (VGG, ResNet) | 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

Decision Trees

A Decision Tree is a supervised machine learning algorithm that makes decisions by splitting data into smaller and smaller parts based on certain conditions. It looks like a tree structure where each decision leads to another decision until a final outcome is reached.

Decision Trees are easy to understand, interpret, and visualize, which makes them very popular in real-world applications.

Real-World Connection

Think about how you decide to buy a phone. You may first ask: Is it within budget? If yes, does it have a good camera? If yes, does it support fast charging? Each question leads you closer to a decision. This step-by-step questioning is exactly how a decision tree works.

How a Decision Tree Works

A Decision Tree splits data based on features. At each split, it chooses the feature that best separates the data into meaningful groups.

  • Root Node: first split
  • Decision Nodes: internal conditions
  • Leaf Nodes: final prediction

Key Concepts in Decision Trees

  • Splitting: dividing data based on feature values
  • Impurity: how mixed the data is
  • Depth: number of levels in the tree

Gini Impurity and Entropy

To decide the best split, decision trees use measures like Gini Impurity or Entropy. These metrics tell the tree how pure or mixed a node is.

Lower impurity means better separation.

Simple Decision Tree Example


from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)

model = DecisionTreeClassifier(max_depth=3)
model.fit(X, y)

print(model.score(X, y))
0.97

The model learns decision rules that classify flower species based on input features.

Decision Tree for Regression

Decision Trees can also be used for regression problems where the output is a numeric value. 


from sklearn.tree import DecisionTreeRegressor
import numpy as np

X = np.array([[1], [2], [3], [4], [5]])
y = np.array([1, 4, 9, 16, 25])

model = DecisionTreeRegressor(max_depth=2)
model.fit(X, y)

print(model.predict([[6]]))
[20.]

The tree predicts values by averaging outcomes in each leaf node.

Advantages of Decision Trees

  • Easy to interpret
  • No feature scaling required
  • Works with numerical and categorical data

Limitations of Decision Trees

  • Prone to overfitting
  • Unstable with small data changes
  • Can grow very large

Practice Questions

Practice 1: Which algorithm makes decisions using if-else conditions?



Practice 2: What node gives the final prediction?



Practice 3: Which metric measures impurity?



Quick Quiz

Quiz 1: Decision Trees can be used for?





Quiz 2: A major drawback of Decision Trees is?





Quiz 3: The first split in a decision tree is called?





Coming up next: Random Forest — combining multiple decision trees for better performance.

← Previous Course Index Next →