Description
In this course, you will learn :
- The distinction between regression and classification, train a Linear Regression model to predict values, and use Logistic Regression to predict states.
- Learn about the perceptron as a neural network building component and the perceptron algorithm for classification.
- Recursively train Decision Trees to forecast states and use Entropy to build decision trees.
- Learn the Bayes rule and use it to predict spam messages using the Naive Bayes algorithm. Train models with Bayesian Learning and finish a natural language processing exercise with Bayesian Learning.
- Learn how to train a Support Vector Machine to segregate data in a linear fashion. To train SVMs on data that is not linearly separable, use Kernel Methods.
- Create excellent data visualisations and presentations for quantitative and categorical data. Create pie charts, bar charts, line charts, scatter charts, histogram charts, and boxplot charts.
- To assess the performance of your models, compute accuracy, precision, and recall.
- Scikit-learn is used to train and test models. Using assessment techniques like as cross-validation and grid search, select the best model.
Syllabus :
- Regression
- Perceptron Algorithms
- Decision Trees
- Naive Bayes
- Support Vector Machines
- Ensemble of Learners
- Evaluation Metrics
- Training and Tuning Models
- Course Project: Find Donors for CharityML