Intro to Machine Learning
Recap
Objectives
Potential Problems with Linear Regression
Linear Models
Then why do we need extensions?
Additive: A Noisy Ferrari vs. A Noisy Kia
Interaction
Finding Interaction Terms
Example – Interaction between TV and Radio
Example – Interaction between TV and Radio
Example (2)
Example (3)
Interactions
Interaction between quantitative and qualitative variables -1
Interaction between quantitative and qualitative variables -2
Non-linearity (1)
Non-linearity (2)
Non-linearity (3)
In General
Polynomial Regression (1)
Polynomial Regression (2)
Classification
Linear vs. Non-linear
Example
What if we treat the problem as follows?
Now, Can we use Linear Regression?
This is what we want
Logistic Regression (1)
Logistic Regression (2)
Parameter Estimation
Logistic Regression Cost Function (1)
Logistic Regression Cost Function (2)
Logistic Regression Cost Function (3)
Logistic Regression Cost Function (4)
Logistic Regression Cost Function (5)
Parameter Estimation
Doing Logistic Regression for Our Example
Predictions (1)
Predictions (2)
Multiple Logistic Regression
Interpreting the results of Logistic Regression
So How to Interpret the Results?
Interpreting the results of Logistic Regression
Multiclass Classification (1)
Multiclass Classification (2)
Multiclass Classification (3)
Classification Metric
When Accuracy is Not Good Enough?
Some Simple Requirements for Good Classifier
An Example Where We Need More than Just Accuracy – Recall and Precision
Confusion Matrix
Precision (1)
Recall (1)
High Recall Low Precision
High Precision Low Recall
F-score
Did we achieve today’s objectives?
6.52M
Категория: ЭлектроникаЭлектроника
Похожие презентации:
Health Care systems using machine learning algorithms
Health Care systems using machine learning algorithms
The machine of LED
The machine of LED
Parallel Architecture Intro
Parallel Architecture Intro
Electrick chock machine
Electrick chock machine
Washing Machine as an invention of manking
Washing Machine as an invention of manking
Auto teller machine, mostly referred to as “ATM”
Auto teller machine, mostly referred to as “ATM”
SF1626SC Automatic feed cutting machine
SF1626SC Automatic feed cutting machine
Washing Machine. Model:N09. Service Manual
Washing Machine. Model:N09. Service Manual
Reinforcement learning of fuzzy logic controllers
Reinforcement learning of fuzzy logic controllers
Distributed processing environment (DPE)
Distributed processing environment (DPE)

Intro to machine learning

1. Intro to Machine Learning

Lecture 3
Adil Khan
[email protected]

2. Recap

• What is linear regression?
• Why study linear regression?
• What can we use it for?
• How to perform linear
regression?
• How to estimate its
performance?
• T-statistics, F-statistics, p-value,
R-squared

3. Objectives

• Extension of linear regressions
• Interaction
• Polynomial
• Classification
• Logistic Regression
• Confusion Metric

4. Potential Problems with Linear Regression

• Recall from last class
Non-linearity of
English     Русский Правила