[Lecture 2] AI and Deep Learning: Logistic Regression (Theory)
Download as PPTX, PDF2 likes1,643 views
This document covers a lecture on logistic regression in the context of artificial intelligence and deep learning, drawing from various educational resources. It explains concepts related to neural networks, supervised learning, the importance of data and algorithms, and outlines how logistic regression is applied for binary classification. Additionally, it details the gradient descent method and the calculations involved in optimizing logistic regression functions.
![[Lecture 2] AI and Deep Learning: Logistic Regression (Theory)](https://image.slidesharecdn.com/lecture2-ink-180216131533/85/Lecture-2-AI-and-Deep-Learning-Logistic-Regression-Theory-17-320.jpg)
![[Lecture 2] AI and Deep Learning: Logistic Regression (Theory)](https://image.slidesharecdn.com/lecture2-ink-180216131533/85/Lecture-2-AI-and-Deep-Learning-Logistic-Regression-Theory-20-320.jpg)
![[Lecture 2] AI and Deep Learning: Logistic Regression (Theory)](https://image.slidesharecdn.com/lecture2-ink-180216131533/85/Lecture-2-AI-and-Deep-Learning-Logistic-Regression-Theory-25-320.jpg)
[Lecture 2] AI and Deep Learning: Logistic Regression (Theory)
- 1. Introduction to Artificial Intelligence & Deep Learning Lecture 2: Logistic Regression Dr. Kobkrit Viriyayudhakorn
- 2. Following slides are based on • Andrew Ng’s Coursera Deep Learning course. • Stanford CS231n: Convolutional Neural Networks for Visual Recognition course. • Goodwill’s Deep Learning Books • Prof. Thanaruk’s Introduction to Concepts and Techniques in Data Mining and Application to Text Mining Book. • Andreas’s Introduction to Machine Learning with Python Book. • Giancarlo Zaccone’s Getting Start with Tensorflow Book. • Justine Johnson’s Python Numpy Tutorial • ETC…
- 3. What is Neural Network (Regression)? Price Size of House
- 4. What is Neural Network (Classification)?Red-dish Round-dish
- 5. House Price Prediction with 4-3-1 NN Size (x1) #Bed Room (x2) Wealth (x4) Zip Code (x3) Price
- 6. Supervised Learning in Neural Network Input (X) Output (Y) Application House Features Price Real Estate Agent Patient conditions Disease Physician Assistant Image 10,000 Objects Photo Recognition CCTV Camera Footage Person Name / Car License Number Security / Robot Audio Text Transcript Speech Recognition, Subtitle Generation Text of Thai Language Text of English Language Machine Translation Radar Signal, Images Position of Obstacle Autonomous Driving
- 7. Neural Network Example Feed Forward Neural Network Convolutional Neural Network (CNN) Recurrent Neural Network (RNN)
- 8. Supervised Learning • Structure Data • Unstructured Data Sepal Length Sepal Width … Species 5.1 3.5 I. setosa 6.3 3.3 I. virginica Iris Flower Dataset
- 9. Why Deep Learning is so popular? Labelled data (m) Performance
- 10. • Data • Computation • Algorithm Why Deep Learning is taking off?
- 12. Binary Classification 1 (Flower) or 0 (Non-Flower)
- 13. 65 10 14 78 43 21 4 25 5 20 130 60 90 120 90 35 78 28 120 30 35 25 1 18 33 12 24 250 65 0 120 45 85 123 4 50 78 88 123 33 Binary Classification 1 (Flower) or 0 (Non-Flower) 255 245 91 128 123 1 244 255 55 80 120 45 85 123 44 39 88 88 123 33 Red Blue Green 64 64
- 14. Notations
- 16. Logistic Regression Cost Function Loss (error) function: 𝑦 = 𝜎 𝑤 𝑇 𝑥 + 𝑏 𝜎 𝑧 = 1 1 + ⅇ−𝑧 𝑥 ⅈ , 𝑦 ⅈ … , 𝑥1 𝑚 𝑦 𝑚 𝑦 ⅈ ≈ 𝑦 ⅈ , where Given want
- 18. Gradient Descent Want to find W, b that minimize 𝐽 W, 𝑏 𝑦 = 𝜎 𝑊 𝑇 𝑥 + 𝑏 𝜎 𝑧 = 1 1 + ⅇ−𝑧, where 𝐽 W, 𝑏 = 1 𝑚 𝑖=1 𝑚 ℒ 𝑦 𝑖 , 𝑦 𝑖 =− 1 𝑚 𝑖=1 𝑚 𝑦 𝑖 log 𝑦+ 𝑖 1 − 𝑦 𝑖 log 1 − 𝑦 𝑖 𝐽 W, 𝑏 𝑊 𝑏
- 22. Computing derivatives b = 3 a = 5 c = 2 u = bc v = a + u J = 3v 11 6 33
- 23. Computing derivatives b = 3 a = 5 c = 2 u = bc v = a + u J = 3v 11 6 33
- 24. Logistic Regression Gradient Descent 𝑧 = 𝑤 𝑇 𝑥 + 𝑏 𝑦 = 𝑎 = 𝜎 𝑧 ℒ 𝑎, 𝑦 = − 𝑦 log 𝑎 + 1 − 𝑦 log 𝑎
- 26. Logistic Regression Gradient Descent 𝑧 = 𝑤1 𝑥1 + 𝑤2 𝑥2 + 𝑏 𝑤1 𝑥1 𝑤2 𝑥2 𝑏 𝑎 = 𝜎 𝑧 ℒ 𝑎, 𝑦
- 27. Gradient Descent in 𝑚 examples
- 29. Algorithm for Logistic Regression