The puzzle recognition
[ UUID ] 1731c392-dfe7-46e2-b919-4763e34350e3
[ Session Name ] The puzzle recognition [ Primary Space ] Youth Zone [ Secondary Space ] Privacy and Security
[ Submitter's Name ] Uriel Jurado [ Submitter's Affiliated Organisation ] UNAM
[ Other Facilitator 1's Name ] Paul Aguilar
[ Language ] Spanish English
[ Localisation Support Requested ] No, I can host the session myself
What will happen in your session?
Two teams will have to make the same puzzle,there will be a wall to separate each team,and to avoid that the can see what is the other team doing.One team will see a video about how the puzzle was made before by another teams.The other team will see nothing.Then both teams will start to make the puzzle.Then we will explain that in the same way the video helped to the first team to make the puzzle faster than the second team,that is how machine learning works. After each time the algorithm computer do the same thing it perfects it and learn how to recognise it faster and more accurate.
What is the goal or outcome of your session?
Our goal is that each person attending learns how your data is being processed when they use some some voice assistant.And that they learn the basics about machine learning for voice: In this case the video is our corpus,used as knowledge base,and the action of seen the video by the team is the data processing phase.The same happens with Mozilla Common Voice(MCV),how more videos (voice recording in this case) we have from different people doing the same puzzle,more accurate and faster our algorithms will be.Also we need to encourage the audience that MCV is an open base of data for voice recognition and it promotes diversity and inclusion for all languages.Currently all the other options from Google, Apple are closed.
If your session requires additional materials or electronic equipment, please outline your needs.
We will need two tables, and something like a wall between them.
Time needed
less than 60 mins