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:DAYLIGHT DTSTART:20180311T020000 RDATE:20180311T020000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 TZNAME:PDT END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT CREATED;VALUE=DATE-TIME:20180926T155207Z DTEND;TZID=America/Los_Angeles;VALUE=DATE-TIME:20181010T200000 DTSTART;TZID=America/Los_Angeles;VALUE=DATE-TIME:20181010T180000 DTSTAMP;VALUE=DATE-TIME:20180926T155207Z LAST-MODIFIED;VALUE=DATE-TIME:20180926T155207Z UID:http://calagator.org/events/1250474331 DESCRIPTION:We'll have a short presentation on deep NLP and review the pa per "\;StarSpace: Embed All The Things!"\; \;\n \;\nThe ma jor vendors in cloud-based services are starting to provide machine lear ning as a service\, such as Google Cloud AutoML Natural Language and Azu re Language Understanding (LUIS). Jim Tyhurst will give a brief demonstr ation of IBM Watson Natural Language Classifier service (https://www.ibm .com/watson/services/natural-language-classifier/)\, which enables you t o build a custom classifier with no programming. Just create a new insta nce and submit training data. When the system has finished training\, yo u can submit a document through a web API. The system responds with JSON \, giving a list of some possible categories with a confidence score ass ociated with each category. We will discuss some of the advantages and d isadvantages of this service. \;\n \;\nStarSpace: Embed All The Th ings! - describes a general-purpose neural embedding model that can solv e a wide variety of problems: labeling tasks such as text classification \, ranking tasks such as information retrieval/web search\, collaborativ e filtering-based or content-based recommendation\, embedding of multi-r elational graphs\, and learning word\, sentence or document level embedd ings. https://arxiv.org/abs/1709.03856\n\nTags: deep leaning\, machine l earning\, natural language processing\, embeddings\n\nImported from: htt p://calagator.org/events/1250474331 URL:https://www.meetup.com/Portland-Deep-Learning/events/254853087/ SUMMARY: Wednesday\, October 10\, 2018 Peer mentoring\, NLP presentation and StarSpace Embedding paper review LOCATION:The Tech Academy: 310 SW 4th Ave Suite 230\, Portland OR 97204 u s SEQUENCE:1 END:VEVENT END:VCALENDAR