BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:America/Los_Angeles X-LIC-LOCATION:America/Los_Angeles BEGIN:DAYLIGHT TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260417T190156Z LOCATION:West Building\, Rooms 101-102 DTSTART;TZID=America/Los_Angeles:20250812T134000 DTEND;TZID=America/Los_Angeles:20250812T144000 UID:siggraph_SIGGRAPH 2025_sess542_ind_164@linklings.com SUMMARY:Building ML Pipelines in Houdini DESCRIPTION:This presentation shows you how to build supervised ML pipelin es in Houdini 21.\n\nWe give an overview of many of the ML nodes that are available in Houdini, where special attention is given to nodes and featur es that have been added with Houdini 21.\nThese ML nodes are designed to b oth leverage and enhance Houdini's proceduralism.\nFully automated end-to- end ML pipelines that include data generation, training and inference can be built entirely inside Houdini.\n\nHoudini's ML nodes can be used to per form sub-tasks that are common to a variety of machine learning applicatio ns. This can save you a lot of work when you're creating your own machine learning pipeline. Among other things, the ML nodes support example genera tion, preprocessing, saving & loading data sets, neural-network training, and inference.\n\nWe show how the ML nodes were used to build ML applicati ons that are being released as part of Houdini 21. These applications incl ude a volume upresser that can be applied to pyro sims and an improved cha racter deformer.\n\nInterest Area: New Technologies, Production & Animatio n, Research & Education\n\nKeyword: Animation, Artificial Intelligence/Mac hine Learning, Dynamics, Pipeline Tools and Work, Simulation\n\nRegistrati on Category: Full Conference, Experience, Exhibits Only, Tuesday\n\n END:VEVENT END:VCALENDAR