From the course: Artificial Intelligence Foundations: Machine Learning
Unlock the full course today
Join today to access over 23,200 courses taught by industry experts.
Exploring learning algorithms for classification
From the course: Artificial Intelligence Foundations: Machine Learning
Exploring learning algorithms for classification
- [Narrator] Let's solve a classification problem using the logistic regression learning algorithm. If you recall, logistic regression is used for classification problems to predict probability using binary values, like zero or one, true or false, or yes or no, based on a set of independent variables. The output values lie between zero and one. The closer the value is to one, the more confident the prediction. We'll train a public safety model that predicts crime by answering the question will this stop lead to an arrest? The publicly available dataset is comprised of stop-and-search data from the UK. We'll take features from stop-and-search data, like location, gender, age, ethnicity, time of day, and more, to predict whether or not a stop will lead to an arrest. After processing the raw dataset, imputing missing values using KNN, K Nearest Neighbors, one-hot encoding of categorical data, removing outliers, and…
Contents
-
-
-
-
-
-
(Locked)
Understanding learning algorithms and model training4m 8s
-
(Locked)
Exploring learning algorithms for classification4m 27s
-
(Locked)
Reviewing learning algorithms for regression5m 23s
-
(Locked)
Examining additional learning algorithms4m 25s
-
(Locked)
Training a custom machine learning model5m 2s
-
(Locked)
Demo: Training a custom machine learning model7m 39s
-
(Locked)
-
-
-