Machine Learning For Kids

Joined today by the world’s youngest machine learning engineer! She was inspired by “Age of Ultron” But how does machine learning actually work? We followed up this podcast with the Teachable Machine project based on a new library called deeplearn.js, which makes it easier for any web dev to get into machine learning. ML relies on specific representation of data, a set of features that are understandable for a computer. If we’re talking about text it should be represented through the words it contains or some other characteristics such as length of the text etc. All ML tasks can be classified in several categories, the main ones are: • Supervised ML • Unsupervised ML • Reinforcement learning. Supervised ML relies on data where the true label/class was indicated. This is easier to explain using an example. Let us imagine that we want to teach a computer to distinguish pictures of cats and dogs. We can ask some of our friends to send us pictures of cats and dogs adding a tag Cat or Dog. Follow-up questions: • Why did they want better machines? • How do you imagine and build something that doesn’t exist yet?