Our 3rd virtual event and we were excited to have Naomi Freeman talking about "AI: Intro to Explainability" This was streamed live on Youtube (this is our first time).
Thanks to Naomi Freeman for calling all the way from Norway, to all who joined us, and also to Mick for assisting on relaying questions, and other emergencies that happened right before the event went live. It was a fun Tuesday afternoon (not). 😣
Setup for @PyLadiesDub this evening, had a panic moment when my capture device hung zoom, OBS... fingers crossed for our first time streaming to Youtube. 30 mins to go! #PyLadies #ai twitter.com/PyLadiesDub/st…16:57 PM - 21 Jul 2020PyLadiesDub @PyLadiesDubA couple of hours to go till #PyLadies Dublin on "#AI: Intro to Explainability" by @naomi_freeman at 18:30. Will be live-streaming. Details: https://t.co/eXgsXHsTYd https://t.co/o0ATbgihpu
But it all went well in the end, lots of lessons learnt. 💪
Mary Loftus@marloft
Great talk this evening with @Naomi_Freeman on AI EXplainability #AIX hosted by @PyLadiesDub - thanks all! twitter.com/PyLadiesDub/st…18:34 PM - 21 Jul 2020PyLadiesDub @PyLadiesDubAnd our first live #PyLadies Dublin stream now on Youtube, come join us and @Naomi_Freeman this evening, bring a cup of coffee/tea, sit back and enjoy. https://t.co/WHnEvZ5vHc
PyLadiesDub@pyladiesdubThings learnt from this evening’s livestream:
- Even tho mirrored image is ok on Zoom, it’s mirrored again on Youtube! 😓
- Test run with the image in the BG next time
- Live chat somehow doesn’t update when Naomi pasted links into it
- Where’s livechat after livestream?18:56 PM - 21 Jul 2020
Now onward with more about the talk details...
Talk Description:
Neural networks are all the rage - input data, output magic results! In between is a black box of magic. In many use cases - from finance to healthcare - this black box is actually a challenge preventing AI adoption. Enter Explainability! Using one extra layer, we can also have our AI explain how it arrived at the decision.
We'll take a look at how to implement this layer of explainability using a Python-based toolbox and a Google Tensorflow AI model.
About Naomi Freeman:
Naomi is a software engineer and entrepreneur. Formerly CTO/co-founder of an AI company. Two-time nominated Woman of Influence for Royal Bank of Canada's Women Entrepreneur award. Currently a 2020/21 Women Who Code Fellow (Data Science & Blockchain).
http://www.naomifreeman.com
📓 Post-talk links & references
- Tensorflow: https://bit.ly/3jqU3tX
- Sample 1 Jupiter notebook:
- Try https://bit.ly/3eLbVvX and if that link doesn't
- work, try this one: https://hub.gke.mybinder.org/user/summerspirit-plx-ec1rvtt9/notebooks/Untitled1.ipynb
📢 Call for speakers
Interested in speaking at our upcoming meetups, please submit talk details to: https://pyladiesdublin.typeform.com/t...
🤔 Questions?
- PyLadies Dublin, email: dublin@pyladies.com
- Ping Naomi about her talk via contact page
🗓 Next PyLadies Dublin]
- When: Tue Aug 18 (18:30 - 21:00)
- Details: https://www.meetup.com/PyLadiesDublin/events/271722192
Top comments (0)