BEGIN:VCALENDAR PRODID;X-RICAL-TZSOURCE=TZINFO:-//Calagator//EN CALSCALE:GREGORIAN X-WR-CALNAME:Calagator METHOD:PUBLISH VERSION:2.0 BEGIN:VTIMEZONE TZID;X-RICAL-TZSOURCE=TZINFO:America/Los_Angeles BEGIN:STANDARD DTSTART:20181104T020000 RDATE:20181104T020000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT CREATED;VALUE=DATE-TIME:20181102T172711Z DTEND;TZID=America/Los_Angeles;VALUE=DATE-TIME:20181108T200000 DTSTART;TZID=America/Los_Angeles;VALUE=DATE-TIME:20181108T180000 DTSTAMP;VALUE=DATE-TIME:20181102T172711Z LAST-MODIFIED;VALUE=DATE-TIME:20181102T172711Z UID:http://calagator.org/events/1250474519 DESCRIPTION:DetailsSame place\, still looking for speakers. If you have a nything you would like to present\, let me know! If you need parking\, t here's a parking deck below Safeway. Agenda: 6:00 p.m.: Food\, beverage\ , and networking 6:40 p.m.: Welcome message by Karl Fezer 6:45 p.m: Spea ker 1: "\;Transfer Learning\, or How to Stand on the Shoulders of Gi ants"\; - James DiPadua7:30 p.m: Speaker 2: "\;Quantum Mechanics for Modeling Composite Semantic Spaces"\; - Connor Favreau8:15 p.m. - 8:30: Project Ideas. Pitch your Project Ideas to this meetup group 8:3 0: End Speaker 1 Details: Abstract: There's been a mountain of research into Deep Neural Networks' practical applications in image\, audio and t ext processing. But these deep networks are often built on large corpuse s of data (such as ImageNet or Wikipedia). But that may not apply direct ly to your domain. Gathering data specific to your problem space may not only be a lengthy process but an expensive one too. That makes the busi ness win a hard sell. Transfer Learning can dramatically eliminate many of those problems\, quickly. In 'How to stand on the shoulders of giants \,' we'll discuss the research background into Transfer Learning and how to implement the process in either Keras or PyTorch. The goal is for li steners to feel comfortable with the concept and prepared to begin resea rching an application in their workspaces. Bio: James is a wanderer\, ti nkerer\, and ponderer. Not one to be pinned down\, he's more comfortable in the abstract than in the known. He embraces ambiguity with a bearhug . That's a trick of course. He bear hugs the ambiguity into little mathe matical boxes and then says "\;Dance!"\; and\, oh\, how that amb iguity dances! James currently hangs his hat at Vacasa where he works as a Senior Data Scientist tackling a myriad of growth-objectives with eng ineering and machine learning. Speaker 2 Details: Five years ago\, Word2 Vec offered a leap forward for the average data scientist to perform eff icient algorithms in Natural Language Processing. From a body of text\, Word2Vec generates a semantic space\, in which the trained word vectors are often highly associated with their meaning. The next leap\, a semant ic space for phrases and sentences\, proves tougher both computationally and in faithfully representing a composite meaning over multiple words. Surprisingly\, quantifying particle interactions a la quantum mechanics shares close mathematical similarity to quantifying the meaning of word s\, phrases\, and sentences. In this talk\, I will provide an overview o f current techniques in modeling language past word vectors\, as well as point out the quantum mechanical aspects of these techniques. Emphasis will be placed on the “Compositional Distributional Semantics” model for the task of identifying word ambiguity."\;\n\nTags: meetup:event=ld wlhqyxpblb\, meetup:group=Portland-Machine-Learning-Meetup\, Artificial Intelligence\, natural language processing\, machine learning\, predicti ve analytics\, Deep Learning\n\nImported from: http://calagator.org/even ts/1250474519 URL:https://www.meetup.com/Portland-Machine-Learning-Meetup/events/254338 888/ SUMMARY:Portland Machine Learning Meetup - PDX ML LOCATION:Uncorked Studios: 811 SE Stark St.\, Portland or 97214 us SEQUENCE:1 END:VEVENT END:VCALENDAR