MLforKids’s avatarMLforKids’s Twitter Archive

292 tweets

Recent:

  1. Make a AI-powered traffic camera game in #Scratch, where you have to train a #machinelearning model to recognise if there are passengers in the car. Full instructions at machinelearningforkids.co.uk/worksheets
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood 0
  2. A new feature was added to @MLforKids this week by @all_about_code - integration with EduBlocks! 🎉🎊 This will let students create machine learning Python projects in the browser, by dragging and dropping blocks on a canvas. dalelane.co.uk/blog/?p=4899
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood -1 🙁
  3. Creating projects based on real-world applications of #machinelearning is an effective way to open up students' eyes to the fact that AI systems are all around them, and impact their lives in countless ways machinelearningforkids.co.uk/stories/invisible-ai/
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  4. Make a #machinelearning-powered "I Spy" game in #Scratch, where you have to guess what the AI has recognised in a photo Full instructions at machinelearningforkids.co.uk/worksheets
    oh my god twitter doesn’t include alt text from images in their API
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood 0
  5. School students are able to engage in debates about the ways that artificial intelligence tech is used. This can be helped giving them a hands-on chance to experiment with the tech and see for themselves how bias can be introduced. machinelearningforkids.co.uk/stories/bias
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  6. Some of the most effective #machinelearning lessons are when something goes a bit wrong. The discussions this enables really helps students understand how ML behaves. Here's one example of how that can go... machinelearningforkids.co.uk/stories/testing-with-data-not-represented-in-training
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  7. Allowing students to experiment in a child-friendly sandbox can help them to understand how #MachineLearning doesn't always learn what we wanted it to learn! Here are a couple examples of how I've seen this go... machinelearningforkids.co.uk/stories/learning-the-wrong-thing
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  8. The flexibility of #Scratch provides students with opportunities to explore the behaviour of #MachineLearning models in creative ways - such as how to deal with machine learning tech being a black box. machinelearningforkids.co.uk/stories/black-box-challenge
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +4 🙂
  9. Students can learn a lot about the role of confidence scores through playing and experimenting with their own simple #machinelearning models - some of the ways children will describe this are fantastic machinelearningforkids.co.uk/stories/confidence-scores
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +6 🙂
  10. The experiences students get by making their own #machinelearning projects helps them understand the behaviours and motivations of big tech companies. This is one of my favourite examples: machinelearningforkids.co.uk/stories/adding-errors-to-training
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +5 🙂
  11. Sentiment analysis projects are a nice way to show students that machine learning can learn to recognize a variety of types of patterns in text, not just the meaning or intent of the text. machinelearningforkids.co.uk/stories/not-just-intents
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +3 🙂
  12. Making simple #machinelearning projects introduces students to the idea of keeping training and test data separate machinelearningforkids.co.uk/stories/separation-of-training-and-test-data
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood 0
  13. letting students try each other's #machinelearning projects allows them to notice for themselves how ML models trained with a wider variety of training examples perform better machinelearningforkids.co.uk/stories/variety-of-training-data
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  14. Students can see for themselves why crowd-sourcing and gamification are used to help create training data for #machinelearning projects machinelearningforkids.co.uk/stories/crowdsourcing-and-gamification
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂
  15. Giving students freedom to experiment with their own machine learning model lets them learn for themselves the relationship between the quantity of training data and the accuracy of machine learning models. machinelearningforkids.co.uk/stories/correlation-of-quantity-with-accuracy
    Permalink On twitter.com Twitter logo MLforKids’s avatar Mood +2 🙂

Popular:

  1. Make a AI-powered traffic camera game in #Scratch, where you have to train a #machinelearning model to recognise if there are passengers in the car. Full instructions at machinelearningforkids.co.uk/worksheets
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 64 Retweets ❤️ 177 Favorites Mood 0
  2. Train a #machinelearning model to recognise questions Teach kids about NLP by making a chatbot in #Scratch Full instructions at machinelearningforkids.co.uk/worksheets
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 45 Retweets ❤️ 74 Favorites Mood 0
  3. Use a #machinelearning model that can recognise faces Teach kids about face detection by making a video face filter in #Scratch that turns their face into a cartoon Full instructions at machinelearningforkids.co.uk/worksheets
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 38 Retweets ❤️ 72 Favorites Mood 0
  4. Machine Learning for Kids: helping kids learn about ML by letting them train models & make things with them Info at machinelearningforkids.co.uk/#!/about
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 36 Retweets ❤️ 67 Favorites Mood +2 🙂
  5. Use a #machinelearning model that can recognise faces Teach kids about face detection by making a live emoji mask in #Scratch Full instructions at machinelearningforkids.co.uk/worksheets
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 33 Retweets ❤️ 52 Favorites Mood 0
  6. It's easy for teachers to prepare machine learning projects for students to work on together: just click on "Share" next to the project. Then students can all contribute training examples for a class machine learning model.
    Permalink On twitter.com Twitter logo MLforKids’s avatar ♻️ 28 Retweets ❤️ 78 Favorites Mood +2 🙂

I’ve retweeted other tweets 70 times (24.0%)

Most Retweeted

  1. dalelane 40 retweets
  2. MLforKids 3 retweets
  3. DevoxxUK 2 retweets
  4. RaspberryPi_org 1 retweet
  5. cintichuEF 1 retweet
  6. HLC_education 1 retweet
  7. halfstackconf 1 retweet
  8. HelloWorld_Edu 1 retweet
  9. KariLawler 1 retweet
  10. doc_pavan 1 retweet

Most Retweeted (Last 12 months)

  1. dalelane 2 retweets
  2. RaspberryPi_org 1 retweet
  3. cintichuEF 1 retweet
  4. HLC_education 1 retweet

Replies and Mentions

18.2% of my tweets are replies (×53)

Most Replies To

  1. Cleo_Qc 3 replies
  2. BehnamFaghih 2 replies
  3. wendy03729904 2 replies
  4. computingdawn 2 replies
  5. FutureAdvocacy 2 replies

Most Replies To (Last 12 months)

  1. amit_petro 1 reply
  2. KaySawbridge 1 reply

I’ve sent someone a mention 0 times (0.0%)

79.1% of the links I’ve posted are using the https: protocol (155 of 196)

100.0% of the links I’ve posted in the last 12 months are using the https: protocol (19 of 19)

Top Domains

  1. machinelearningforkids.co.uk 102 tweets
  2. github.com 21 tweets
  3. youtu.be 18 tweets
  4. dalelane.co.uk 17 tweets
  5. twitter.com 12 tweets
  6. raspberrypi.org 4 tweets
  7. ibm.com 4 tweets
  8. bluemix.net 3 tweets
  9. youtube.com 3 tweets
  10. facebook.com 1 tweets

Top Hosts

  1. machinelearningforkids.co.uk 102 tweets
  2. github.com 21 tweets
  3. youtu.be 18 tweets
  4. dalelane.co.uk 17 tweets
  5. twitter.com 12 tweets
  6. console.bluemix.net 3 tweets
  7. www.youtube.com 3 tweets
  8. cloud.ibm.com 3 tweets
  9. projects.raspberrypi.org 3 tweets
  10. www.raspberrypi.org 1 tweets

My tweets have been given about ♻️ 1,382 retweets and ❤️ 2,894 likes

Top 5 Emoji Used in Tweets

  1. 🎉 used 1 times on 1 tweets
  2. 🎊 used 1 times on 1 tweets
  3. 😁 used 1 times on 1 tweets
  4. 👍 used 1 times on 1 tweets
  5. 🤔 used 1 times on 1 tweets

9 unique emoji on 5 tweets (2.3% of all tweets***)

Top 5 Hashtags

  1. machinelearning used 73 times
  2. scratch used 68 times
  3. artificialintelligence used 6 times
  4. hourofcode used 4 times
  5. ai-powered used 2 times

163 hashtags on 163 tweets (73.4% of all tweets***)

Top 5 Swear Words

0 swear words on 0 tweets (0.0% of all tweets***)

***: does not include retweets