Students will be required to finish three related homework projects, including 1) developing a machine learning classifier, 2) designing adversarial attacks against the built classifier, and 3) developing defenses to improve the robustness of the trained classifier against designed attacks. Students will learn to analyze current interactions between attackers and defenders on machine learning and therefore develop an understanding of the principles on trustworthy machine learning which is an emerging and important topic. The lessons are reinforced via a series of topic-driven lectures, coding assignments, related paper readings, exams and in-class discussions. Students will explore topics including basic machine learning foundations (e.g., linear regression and PCA), adversarial attacks against different learning algorithms, differential privacy, data valuation, and different categories of defenses. Prepares students to understand the security and privacy problems in machine learning and educates students to propose different attack strategies to identify the vulnerabilities of a range of learning algorithms and understand different defense approaches towards trustworthy machine learning systems. Prerequisite: CS 225 and CS 361.ĬS 442 Trustworthy Machine Learning credit: 3 or 4 Hours. Application areas include computer vision, natural language, interpreting accelerometer data, and understanding audio data. The course will focus on tool-oriented and problem-oriented exposition. Techniques of machine learning to various signal problems: regression, including linear regression, multiple regression, regression forest and nearest neighbors regression classification with various methods, including logistic regression, support vector machines, nearest neighbors, simple boosting and decision forests clustering with various methods, including basic agglomerative clustering and k-means resampling methods, including cross-validation and the bootstrap model selection methods, including AIC, stepwise selection and the lasso hidden Markov models model estimation in the presence of missing variables and neural networks, including deep networks. CS 441 Applied Machine Learning credit: 3 or 4 Hours.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |