Yaniv Yacoby
Assistant Professor of Computer Science
Links
I'm an interdisciplinary researcher working at the intersection of machine learning (ML) and mental health.
I lead the Model-Guided Uncertainty (MOGU) Lab at Wellesley, where we enable effective and responsible uses of expressive (deep) ML models in safety-critical domains, like precision healthcare. Our research specifically focuses on developing methods to help us better understand, predict, and prevent suicide and related behaviors. We do this by developing new paradigms for clinician/patient-AI collaboration.
I see both my teaching and research as social endeavors. My teaching and research both require a social context to meaningfully center ethics, and require supportive classroom/lab cultures to support holistic growth. I'm therefore excited about creating classroom and mentorship experiences that emphasize community building and interrogation of socio-technical systems and cultures.
Outside of work, I enjoy spending time with my two cats and dog, playing and listening to folk music, trying out new food, and watching reality TV.
For my CV, as well as information about my research, teaching, and service, see my website.
Education
- B.A., Harvard University
- M.M., New England Conservatory of Music
- Ph.D., Harvard University
Current and upcoming courses
Data Structures
CS230
An introduction to techniques and building blocks for organizing large programs. Topics include: modules, abstract data types, recursion, algorithmic efficiency, and the use and implementation of standard data structures and algorithms, such as lists, trees, graphs, stacks, queues, priority queues, tables, sorting, and searching. Students become familiar with these concepts through weekly programming assignments using the Java programming language.
To enroll in CS 230, students need an explicit authorization of concept mastery from faculty of one of the following courses CS 111, CS 111M, CS 111X, or CS 112; or have taken CS 200. Students who did not take CS 111 or equivalent at Wellesley complete a placement questionnaire.
Once the course fills, students can add themselves to the waitlist by filling out this form.
-
Probabilistic Foundations of Machine Learning
CS245
In recent years, Machine Learning (ML) has been used in novel applications—from generating new art and music to systems that accurately and reliably predict outcomes of medical interventions in real-time. Faster computing hardware, large datasets, and the probabilistic paradigm of ML, which frames advances like neural networks within statistical learning, have enabled these developments. In this course, we introduce the foundational concepts behind the probabilistic paradigm of predictive ML: statistical model specification and learning. We will focus on connecting theory with real-world applications. Students will get hands-on experience building models for specific tasks, most taken from healthcare contexts, using probabilistic programming languages. While expanding our methodological toolkit, we will simultaneously introduce critical perspectives to examine the ethics of ML within sociotechnical systems. This course lays the foundation for advanced study and research in ML. Topics include: directed graphical models, deep regression/classification, frequentist learning, and model evaluation. For more information, see the course website: https://mogu-lab.github.io/cs245/. . Enrollment in this course is by permission of the instructor. Students interested in taking this course should fill out this Google Form.