BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230329T170709Z UID:8FF17434-8CF1-4CC5-841C-F8D354215244 DTSTART;TZID=America/Los_Angeles:20230328T173000 DTEND;TZID=America/Los_Angeles:20230328T183000 DESCRIPTION:Modern machine learning has origins in human learning\, taking cues from human perception to build\, train and evaluate machine learning models. As machine learning (ML) has begun to outperform humans in many ch allenging tasks\, the focus has shifted from modeling humans to simply imp roving the performance of these ML models. We focus instead on what can be learned from human perception to improve these models and make them more transparent and understandable. With many applications of machine learning having real-world impacts on humans\, we consider explainability essentia l for these models. In this talk\, I will detail our approaches to explain able attribute recognition\, prominent feature recognition\, and face reco gnition. With each problem\, we will highlight our influences from human p erception.\n\nSpeaker(s): Emily Hand\, Ph.D.\, \n\nVirtual: https://events .vtools.ieee.org/m/352153 LOCATION:Virtual: https://events.vtools.ieee.org/m/352153 ORGANIZER:upalmahbub@yahoo.com SEQUENCE:5 SUMMARY:Using Human Perception to Inform Machine Perception URL;VALUE=URI:https://events.vtools.ieee.org/m/352153 X-ALT-DESC:Description: <br /><p><span style="font-weight: 400\;">Modern ma chine learning has origins in human learning\, taking cues from human perc eption to build\, train and evaluate machine learning models. As machine l earning (ML) has begun to outperform humans in many challenging tasks\, th e focus has shifted from modeling humans to simply improving the performan ce of these ML models. We focus instead on what can be learned from human perception to improve these models and make them more transparent and unde rstandable. With many applications of machine learning having real-world i mpacts on humans\, we consider explainability essential for these models. In this talk\, I will detail our approaches to explainable attribute recog nition\, prominent feature recognition\, and face recognition. With each p roblem\, we will highlight our influences from human perception.</span></p > END:VEVENT END:VCALENDAR