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:20180309T052120Z DTEND;TZID=America/Los_Angeles;VALUE=DATE-TIME:20180314T203000 DTSTART;TZID=America/Los_Angeles;VALUE=DATE-TIME:20180314T180000 DTSTAMP;VALUE=DATE-TIME:20180309T052120Z LAST-MODIFIED;VALUE=DATE-TIME:20180309T052120Z UID:http://calagator.org/events/1250473395 DESCRIPTION:Inference\, Deep Neural Nets\, Hyper-Parameters\, Sign Langua ge and Visual Insights \;\n \;\nWelcome to TensorFlow Northwest. I t was exciting to have so many of you come out during February’s snow-ma geddon. This month\, we prepared a balanced agenda to have new contents\ , and to incrementally build on what you’ve learned. On the other hand\, we built the labs in a way that will allow those who couldn’t beat the storm to catch up quickly. \;\n \;\nAl Kari will begin with an int roduction and a technology update\, then he moves on to cover a key topi c in TensorFlow: Saving your models so you can use them to classify new data. The discussion will cover best practices and techniques to use you r trained models for inference and transfer learning. \;\n \;\nAl is Manceps’ Co-founder and CEO (www.manceps.com) where he helps enterpri se clients with their Digital Transformation and intelligent computing r oadmaps. \;\n \;\nNext\, Andrew Ferlitsch will take you on a code- along adventure via Colaboratory- An Introduction to Constructing Neural Networks and Hyper-parameter Tuning. \;\n \;\nYou’ve kicked the t ires with 5 digits hand signs last month. Now\, we progressively build l ayers of a neural network for the larger dataset of the American Sign La nguage hand gestures including all the letters of the alphabet. We will cover a fully connected neural network\, proceed to a deep neural networ k\, and then add dropout layers to tackle overfitting. Then we wrap up w ith the fundamentals of hyper-parameter tuning. \;\nThe lab requires a laptop with a modern browser and will be at a modest pace to provide s ufficient opportunity to ask questions and share insights. \;\n \; \nAs Chief Data Scientist at Manceps\, Andrew works on solving a diverse set of problems using Deep Learning and advanced analytics. \;\n \;\nFinally\, David Molina will demystify Neural Networks once and for a ll\, visually! \;\nWhat does bias do in a Neural Network? Why are wei ghts important? What happens when we select a high learning rate? How do we know how many inputs to select? How many hidden layers a model needs in order to predict accurately? How does a Neural Network work? These a re questions we ask when we begin studying Machine Learning as we encoun ter our first Neural Network. David will explore visually what’s behind the code\, and what happens inside a Neural Network when it runs. \;\ n \;\nDavid is an Industrial Engineer with five years corporate exper ience in building databases\, managing and analyzing large data sets\, a nd optimizing systems and processes. He is currently studying Machine Le arning and consulting for companies in his native country of Colombia.&# 13\;\n \;\nREMEMBER to bring your laptop \;\n \;\nPizza and dri nks sponsored by Intel. Links to the labs will be posted shortly. \;\ n \;\nHope you have a great time learning and networking.\n\nTags: te nsorflow\, Deep Learning\, machine learning\, Artificial Intelligence\, data science\, Digital Transformation\, python\n\nImported from: http:// calagator.org/events/1250473395 URL:http://bit.ly/tfnw-3 SUMMARY:TensorFlow Northwest User Group LOCATION:Vacasa: 926 NW 13th Ave #200\, Portland OR 97209 us SEQUENCE:1 END:VEVENT END:VCALENDAR