BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//FutureCite - ECPv6.17.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://futurecite.com
X-WR-CALDESC:Events for FutureCite
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Edmonton
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20180311T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20181104T080000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20190310T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20191103T080000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:20200308T090000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:20201101T080000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Edmonton:20190306T183000
DTEND;TZID=America/Edmonton:20190306T203000
DTSTAMP:20190306T004824Z
CREATED:20190306T004824Z
LAST-MODIFIED:20190306T004824Z
UID:13700-1551897000-1551904200@futurecite.com
SUMMARY:Data Science Meet-Up
DESCRIPTION:Startup Edmonton \nWednesday\, March 6 at 6:30 PM \n• “Cost-Sensitive Classifier Evaluation Using Cost Curves” – Professor Robert Holte (CS @ UofA)\n• “Figuring out the limits of human vision with deep learning” – Navaneeth Kamballur Kottayil (Machine Learning Researcher at BorealisAI) \nPizza will be provided before presentations and after presentations we will head to a pub for networking! \nThe meetup is sponsored by AltaML (http://altaml.com/). \nAbstracts: \nCost-Sensitive Classifier Evaluation Using Cost Curves\n(co-author: Chris Drummond)\nThe evaluation of classifier performance in a cost-sensitive setting is straightforward if the operating conditions (misclassification costs and class distributions) are fixed and known. When this is not the case\, evaluation requires a method of visualizing classifier performance across the full range of possible operating conditions. This talk outlines the most important requirements for cost-sensitive classifier evaluation\, and introduces a technique for classifier performance visualization – the cost curve – that meets all these requirements. This talk should be of interest to anyone who works in areas that use classifiers\, for example\, machine learning\, pattern recognition\, biometrics\, and diagnosis.\nRelated papers:\nhttp://dx.doi.org/10.1007/s10994-006-8199-5\nhttps://webdocs.cs.ualberta.ca/~holte/Publications/kdd2000.pdf \nFiguring out the limits of human vision with deep learning\nIn this talk\, I present a part of my PhD thesis done in collaboration with Telecom Paristech. In this work\, we explored methods to derive the human perceptual limit to see changes in an image. We proposed a new method to solve the problem with convolutional neural network. Our solution involved using deep learning in conjunction with traditional methods in psychophysics. Our method derives the human error detection threshold by solving an alternative problem of image quality assessment. We tested our method on publicly available databases for measuring human visual thresholds and show state of the art results.\nRelated papers:\nhttps://arxiv.org/abs/1712.07269\nhttps://www.researchgate.net/publication/327994999_Learning_Local_Distortion_Visibility_from_Image_Quality \nEdmonton Data Science meetup is a place to learn about data science and network with fellow Data Scientists. The presentations for the upcoming meetup…
URL:https://futurecite.com/event/data-science-meet-up-2/
LOCATION:Startup Edmonton HQ\, 301\, 10359 - 104 Street\, Edmonton\, AB\, Canada
CATEGORIES:Entrepreneurs,Human Talent,Industry,Research,Robotics,Science,Technology
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Edmonton:20190306T183000
DTEND;TZID=America/Edmonton:20190306T203000
DTSTAMP:20190306T004824Z
CREATED:20190306T004824Z
LAST-MODIFIED:20190306T004824Z
UID:7462-1551897000-1551904200@futurecite.com
SUMMARY:Data Science Meet-Up
DESCRIPTION:Startup Edmonton \nWednesday\, March 6 at 6:30 PM \n• “Cost-Sensitive Classifier Evaluation Using Cost Curves” – Professor Robert Holte (CS @ UofA)\n• “Figuring out the limits of human vision with deep learning” – Navaneeth Kamballur Kottayil (Machine Learning Researcher at BorealisAI) \nPizza will be provided before presentations and after presentations we will head to a pub for networking! \nThe meetup is sponsored by AltaML (http://altaml.com/). \nAbstracts: \nCost-Sensitive Classifier Evaluation Using Cost Curves\n(co-author: Chris Drummond)\nThe evaluation of classifier performance in a cost-sensitive setting is straightforward if the operating conditions (misclassification costs and class distributions) are fixed and known. When this is not the case\, evaluation requires a method of visualizing classifier performance across the full range of possible operating conditions. This talk outlines the most important requirements for cost-sensitive classifier evaluation\, and introduces a technique for classifier performance visualization – the cost curve – that meets all these requirements. This talk should be of interest to anyone who works in areas that use classifiers\, for example\, machine learning\, pattern recognition\, biometrics\, and diagnosis.\nRelated papers:\nhttp://dx.doi.org/10.1007/s10994-006-8199-5\nhttps://webdocs.cs.ualberta.ca/~holte/Publications/kdd2000.pdf \nFiguring out the limits of human vision with deep learning\nIn this talk\, I present a part of my PhD thesis done in collaboration with Telecom Paristech. In this work\, we explored methods to derive the human perceptual limit to see changes in an image. We proposed a new method to solve the problem with convolutional neural network. Our solution involved using deep learning in conjunction with traditional methods in psychophysics. Our method derives the human error detection threshold by solving an alternative problem of image quality assessment. We tested our method on publicly available databases for measuring human visual thresholds and show state of the art results.\nRelated papers:\nhttps://arxiv.org/abs/1712.07269\nhttps://www.researchgate.net/publication/327994999_Learning_Local_Distortion_Visibility_from_Image_Quality \nEdmonton Data Science meetup is a place to learn about data science and network with fellow Data Scientists. The presentations for the upcoming meetup…
URL:https://futurecite.com/event/data-science-meet-up/
LOCATION:Startup Edmonton HQ\, 301\, 10359 - 104 Street\, Edmonton\, AB\, Canada
CATEGORIES:Entrepreneurs,Human Talent,Industry,Research,Robotics,Science,Technology
END:VEVENT
END:VCALENDAR