EECE 5645 — Parallel Processing for Data Analytics

4 semester hoursGraduateLectureusually offered: falltypical days: TBostonTraditional

Covers the fundamentals of parallel machine-learning algorithms, tailored specifically to learning tasks involving large data sets. Reviews methods for dealing with both large and high-dimensional data sets, emphasizing distributed implementations. Beyond covering the theory behind statistical data analysis, the course also offers a hands-on approach, using Spark as a development platform for parallel learning. Topics include, Apache Spark fundamentals, multithreaded/cluster execution, resilient distributed data structures, map-reduce operations, using key-value pairs, joins, convex optimization, gradient descent, linear regression, Gauss-Markov theorem, ridge and lasso regularization, feature selection, cross validation, variance vs. bias trade-off, classification, logistic regression, ROC curves and AUC, matrix and tensor factorization, graph-parallel algorithms and sparsity, Perceptron algorithm, and deep neural networks.

Prerequisites

Offering history

TermSectionsEnrolledCapacityFullOpen seats/section
Fall 20231334869%15.0
Fall 20241304567%15.0
Spring 20261166027%44.0

Snapshots from scheduled scrapes — not live seat availability. "Full" can exceed 100% when sections over-enroll.

Meeting times

Share of recent sections by weekday: M 0% · T 100% · W 0% · Th 0% · F 0%

Common patterns: T (100% of sections) — in patterns, R means Thursday

Professors

Fall

Spring

Percentages are each professor's average share of the season's enrolled students in recent terms.

Links

Official catalog (EECE course descriptions) · Student reviews on RateMyHusky · All EECE courses · Plan it at numap.app