Deep Learning and Neural Networks, the sixth lab of the Machine Learning and Deep Learning Series introduces participants to the fundamentals of deep learning and neural networks, focusing on their architecture and functionality. Attendees will explore how neural networks work, from input layers to output layers, and the role of activation functions. The session will also cover backpropagation, optimization techniques like SGD and Adam. Participants will gain hands-on experience by building a simple feedforward neural network for classification tasks.

Advanced Machine Learning - Ensemble Methods and Model Optimization, the fifth lab of the Machine Learning and Deep Learning Series covers advanced machine learning techniques to enhance model performance. Participants will dive into ensemble methods like random forests and gradient boosting algorithms such as XGBoost and LightGBM. The session will also introduce hyperparameter tuning strategies, including GridSearchCV to optimize model parameters effectively. To ensure robust model evaluation, participants will learn cross-validation techniques and how to interpret their results.

Unsupervised Learning, the fourth lab of the Machine Learning and Deep Learning Series, participants will learn to work with unlabeled data using unsupervised learning techniques. The lab will explore clustering methods, including k-Means and hierarchical clustering, to uncover patterns in datasets. Participants will also learn dimensionality reduction techniques like Principal Component Analysis (PCA) to simplify high-dimensional datasets.

Regression, the third lab of the Machine Learning (ML) and Deep Learning Series will cover ML models for regression tasks. The session begins with the fundamentals of linear regression and progresses to polynomial regression and regularization methods such as Lasso and Ridge regression. In addition, decision trees, support vector machines and K-nearest neighbors (KNN) will be introduced to demonstrate their effectiveness in regression tasks.

Classification, the second lab of the Machine Learning and Deep Learning Series, shifts the focus to classification models for predicting categorical outcomes. Participants will explore a range of classification algorithms, starting from logistic regression and decision trees to more advanced models like support vector machines (SVMs), and k-nearest neighbors (KNN). Naive Bayes and other classifiers will also be covered to provide a comprehensive understanding of classification methods.

The first open lab of the Machine Learning and Deep Learning Series, this event sets the stage for understanding machine learning by providing a foundational overview of its core concepts and applications. Participants will explore the different types of machine learning—supervised, unsupervised, and reinforcement learning—and their use cases. This session is designed for those new to the field, with no coding experience required. It will also highlight how machine learning drives modern technological advancements and introduce the field of deep learning.

Data Science is an interdisciplinary field that uses the scientific method, processes, algorithms and systems to extract valuable meaning and insights from data. In this kickoff session, the ASU Library's Unit for Data Science and Analytics team will provide details of our upcoming events and opportunities to get involved in data science and analytics. Everyone is welcome to attend!

Presenters: Kerri Rittschof, Namig Abbasov and Abi Mercado Rivera. 

Subscribe to ASU Library