Whittemore Library: Student and Faculty Guide to Artificial Intelligence : Machine Learning

ML

Image created using ChatGPT from OpenAI, February 2025

Machine Learning (ML) is a branch of computer science that focuses on enabling computers to learn new behaviors from an empirical basis. One of the most important elements of ML is to design algorithms that will allow the computer to learn from past experience. Success in ML will cut down on the amount of human involvement and intervention in AI technologies.

Media Resources

Linked Resources

Automated tools for systematic review screening methods
A study that uses ML to develop comprehensive and accurate sexual orientation and gender identity measures in order to quantify and address disparities in health.
AI and ML approaches in sports: Concepts, applications, challenges, and future perspectives
A study that presents the current state of AI and ML in sports science, including uses in injury prediction, performance enhancement, and rehabilitation.
Automated tools for systematic review screening methods
A study that uses ML to develop comprehensive and accurate sexual orientation and gender identity measures in order to quantify and address disparities in health.
Estimating Substance Use Disparities Across Intersectional Social Positions Using Machine Learning
A study that introduces a ML model with hierarchical regularization to assess intersectional differences in the prevalence of substance abuse.
Foundations of Cost-Sensitive Machine Learning and Its Application in Psychology
A paper that presents the mathematical foundations for cost-sensitive ML models, as well as a comparison between typical ML models and cost-sensitive models.
Interpretable ML model for prediction of overall survival in laryngeal cancer
A study that compares the predictive performances of DeepTables with various ML models to explore laryngeal cancer patients' chances of survival.
Machine Learning Potential for Identifying and Forecasting Complex Environmental Drivers of Infections in the U.S.
A study that examines how ML was used to assess the predictive potential to forecast Vibrio vulnificus infections based on environmental data.
Machine learning with multiple modalities of brain magnetic resonance imaging data
A study that strives to improve ML classification of Bipolar Disorder by combining information from structural, functional, and diffusion-weighted imaging.
Prediction of Perceived Exertion Ratings in National Level Soccer Players Using Wearable Sensor Data and ML Techniques
A study that attempts to identify relationships between external and internal load parameters with perceived exertion ratings, and use those relationships to evaluate various ML models.
Reevaluating feature importances in ML models for schizophrenia and bipolar disorder
A paper that examines the distinction between factors that ML models consider important and actual associations, as well as the biases at play with ML models.
The application of machine learning for treatment selection of unruptured brain arteriovenous malformations
A study about a team of clinicians who determined the best first-line treatment for bAVMs, which was used to train a an automated ML model.
Use of ML Models to Predict Microaspiration Measured by Tracheal Pepsin A
An analysis in which ML models were used to examine the Pepsin A levels in adults who were receiving mechanical ventilation.