Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook provides an introduction to Recurrent Neural Networks (RNNs), explaining their architecture and use cases. Students will learn about the key components of RNNs, such as hidden states and backpropagation through time, and will implement a simple RNN model to understand its functionality. By the end, students will have a foundational understanding of how RNNs can be applied to sequence prediction tasks.

Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook provides an overview of supervised learning, focusing on key algorithms such as linear regression and decision trees. Students will learn how to apply these methods to datasets, understand their underlying principles, and evaluate model performance.

Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook provides an in-depth exploration of regularization techniques in machine learning, focusing on methods such as L1 and L2 regularization. Students will learn how these techniques help prevent overfitting by adding a penalty term to the loss function. By the end, students will understand the practical application of these methods in improving model generalization.

Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook provides an in-depth exploration of Principal Component Analysis (PCA), a key technique in data science for dimensionality reduction. Students will learn how to apply PCA to datasets, understand its mathematical foundations, and interpret the results. By the end, students will be able to use PCA to simplify complex datasets while retaining essential information.

Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook provides an in-depth exploration of model evaluation techniques, focusing on methods to assess the performance of machine learning models. Students will learn about key metrics such as accuracy, precision, recall, and F1-score, and understand how to apply these metrics to improve model performance.

Johanni Michael Brea

BIO-322

Julia

Demonstrations in class

English

This notebook provides an in-depth exploration of generalized linear regression models, focusing on their application and interpretation. Students will learn about the mathematical foundations, implementation techniques, and practical use cases of these models. By the end, students will understand how to apply generalized linear regression to various datasets and interpret the results effectively.

Johanni Michael Brea

BIO-322

Julia

Interactive textbook

English

This notebook provides an extensive overview of key machine learning concepts, including supervised learning, neural networks, and reinforcement learning. Students will learn about various algorithms such as PCA and gradient descent, and understand the importance of model evaluation and regularization techniques. By the end, learners will have a solid foundation in both theoretical and practical aspects of machine learning.

Johanni Michael Brea

BIO-322

Julia

Exercise worksheets

English

This notebook serves as an introduction to Jupyter Notebooks, explaining their structure and functionality. Students will learn how to create and execute cells, use Markdown for documentation, and integrate Python code. By the end, students will understand the basics of using Jupyter for data analysis and visualization.

Johanni Michael Brea

BIO-322

Julia

Demonstrations in class

English

This notebook provides an in-depth exploration of the gradient descent algorithm, a fundamental optimization technique used in machine learning. Students will learn how gradient descent works, implement it from scratch, and understand its application in minimizing cost functions. By the end, students will be able to apply gradient descent to optimize linear regression models.

Johanni Michael Brea

BIO-322

Julia

Demonstrations in class

English

This notebook introduces students to clustering techniques, focusing on methods such as k-means and hierarchical clustering. By the end, students will understand how to apply these algorithms to real-world datasets and interpret the results. Key concepts include distance metrics and cluster evaluation.