Description

Scikit-learn is a popular open-source Python library that offers user-friendly and efficient versions of common machine learning algorithms. In this training, PhD student and machine learning instructor Michael Galarnyk will go over the various strengths and weaknesses of different supervised and unsupervised machine learning algorithms and then how to apply them to real-world situations (healthcare, finance, etc). Topics of the session include how to input and process data for machine learning, model validation strategies, choosing a model, linear regression, logistic regression, feature selection, support vector machines, decision trees, random forests, gradient boosting, visualizing decision trees, k-means clustering, hierarchical clustering, clustering metrics, dimensionality reduction, hyperparameter tuning, and regularization. Additionally, we will go over the use cases where scikit-learn is not the ideal tool such as in modern deep learning and natural language processing. By the end of the session, participants will understand the strengths and weaknesses of machine learning algorithms and learn how to quickly build better, more efficient machine learning models for various domains.

Instructor's Bio

Michael Galarnyk

Learning Instructor at LInkedin

Michael is currently a PhD Student at Georgia Institute of Technology researching machine learning for financial markets with an emphasis on how social media impacts financial returns. He has been teaching python and machine learning since 2015 at places like UCSD Extension, Stanford Continuing Studies, and LinkedIn Learning. He previously worked at Scripps Research Translational Institute working on the interpretation of wearable data for human health, with the goal of building models to improve patient outcomes.

Webinar

  • 1

    Training "Building Machine Learning Models with Scikit-Learn: A Practical Introduction"

UPCOMING LIVE TRAINING

Register now to save 30%