BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//American Young Coder - ECPv6.10.1.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:American Young Coder
X-ORIGINAL-URL:https://www.ayclogic.com
X-WR-CALDESC:Events for American Young Coder
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260520T190000
DTEND;TZID=America/Los_Angeles:20260520T200000
DTSTAMP:20260524T224920
CREATED:20260521T034953Z
LAST-MODIFIED:20260521T040109Z
UID:33607-1779303600-1779307200@www.ayclogic.com
SUMMARY:7 PM – AI/ML – Darin
DESCRIPTION:Today’s Activities:\n\n\n\nFinished the Single Digit Classifier project.\n\nHomework:\nFor Rexford\, choose the dataset for your project (has to be multiclass\, and catch up the below) \n\nHW 1: \n\nChoosing what you want to classify — Can be anything in real life\, the only thing is you have to make sure the data exists on Kaggle. \nThe project has to be able to classify at least 5 different categories. \nWhat we did last week: \n\nSet up the labelling function\nVerify Dataloader works with .show_batch() (reference old code for how to do this\, it will depend on how you extract labels\, whether its via path or filename)\nRun training with a vision_learner.\n\nWhat you have to do next week: \n\nUse the proper imports (fast ai 2.7.19)\nUse lr.find() to get the proper learning rate\, then run finetuning with the discovered value (you must only call fine_tune once!)\nAdd the following into the vision learner to ensure lr_find works!:\npath=Path(“/kaggle/working”)\,\nmodel_dir=”models”\,\nExport the file as a .pt file onto your computer!\n\n\nHW 2: \nDownload the following CSV file: https://drive.google.com/file/d/1kP6A9y0UBssOg3Exunv9Mnmilb0657Sh/view \nThen do the following in a new notebook called WED-7PM-PandasHW1: \n\nLoad the data \nShow only the Channel and Subscribers columns \nFind channels with more than 2000 subscribers\nFor this you can use something like this:  \ndf[df[“Math”] > 80]\,but of course for this data. \n \nAdd a new column Subs_per_Video \nAnswer the question in Markdown\, which channel is the most efficient?\n\n\nNotes:\nYou can reach me at ddjapri@ayclogic.com. \nAll class notes can be found here.
URL:https://www.ayclogic.com/event/7-pm-ai-ml-darin-28/
CATEGORIES:AI/ML,Python Class
END:VEVENT
END:VCALENDAR