INFO 6106 — Neural Modeling Methods and Tools

4 semester hoursGraduateLectureusually offered: fall, springtypical days: M/WBostonTraditional

Uses a graph theoretic approach to build models representing dependencies of model components instead of using analytical functions in statistics to interpolate observations, build data models, and estimate model parameters. The interpolation is still parametric, but the parameters are graph related and do not involve analytic functions. Discusses how to explain neural models and not fear them; when it is appropriate to use neural models; and how to interact with machines that use neural models in the same way one would trust a friend, so that trust between humans and machines is enhanced rather than diminished. These so-called neural models mirror in some regard how biological brains build models to make sense of the world and do predictions.

Prerequisites

Offering history

TermSectionsEnrolledCapacityFullOpen seats/section
Fall 20231155030%35.0
Spring 20241155030%35.0
Fall 20241255050%25.0
Spring 20251145028%36.0
Fall 20251135026%37.0
Spring 202614508%46.0

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 83% · T 0% · W 83% · Th 0% · F 0%

Common patterns: MW (65% of sections), W (17% of sections), M (17% 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 (INFO course descriptions) · Student reviews on RateMyHusky · All INFO courses · Plan it at numap.app