0:0011:03

Explain Machine Learning as to a kid

Precious Kolawole 11:03 2021

Why a child who avoids a hot stove is doing machine learning

A toddler touches a candle flame, cries, and two days later ignores a glowing stovetop. That small moment, says machine learning engineer Precious Kolawole of Lendsqr, is machine learning in miniature, and it separates learning from patterns from simply following instructions. For anyone hearing AI buzzwords without a clear picture, the question is how a computer turns labelled examples into its own rules.

Learn the core idea of machine learning and a clear first-steps path from Python to models

Watch on YouTube

In short

Precious Kolawole, a data scientist and machine learning engineer at Lendsqr, explains machine learning in the simplest terms, using a child who learns from a candle flame and a cat image classifier. She contrasts learning from labelled data with explicit programming and, in the Q&A, outlines a beginner path from Python through data analysis to machine learning.

“Machine learning is a large subset of artificial intelligence that allows computers to learn from data.”
“Let's now say this young child, he ignored the stovetop because his parents warned him against it. Then that would be explicit programming and not machine learning.”

What you will learn

  • Explain machine learning to a non-technical person using a simple everyday analogy.
  • Distinguish machine learning, which learns patterns from labelled examples, from explicit programming, which follows written instructions.
  • Describe how training on labelled data produces a model that predicts on new inputs, using the Y equals f(X) idea.
  • Recognise the kinds of hard, data-heavy decisions where machine learning is most useful.
  • Plan a beginner learning path from Python to data analysis, data science and then machine learning.

Key takeaways from the speaker

  • NA
  • Machine Learning for beginners

Details

Level
Beginner
Format
Lightning talk
Technical depth
Introductory technical
For
Student, Early career, Career changer
Length
11:03
Published
June 2021

Questions this talk answers

What is machine learning in simple terms?

It is a large subset of artificial intelligence that lets computers observe patterns in data, learn from them and use what they learn to make predictions.

How is machine learning different from traditional programming?

In explicit programming a developer writes instructions for the computer to follow, while in machine learning you give the computer inputs and their labels and it creates the mapping, the model, on its own.

What does training a model look like in practice?

For a cat detector you supply labelled images of cats and non-cats, the computer learns a function mapping each image to its label, and after training it predicts true or false for new images.

How should a beginner get started in machine learning?

Learn Python first, then move into data analysis, visualisation and data science, and once comfortable go into machine learning, model building, deployment and deep learning.

Can you do machine learning without code?

She says some ready-made platforms, such as tools on Microsoft Azure, let you build and use models without coding, but most of the time you need to know how to write code.

About this talk

Machine Learning programs today can learn to identify objects in images, videos, translate between languages, even master arcade and board games. In some cases, like DeepMind’s AlphaGo program, the AI even exceeds top humans at the task at hand! However, Machine Learning and AI are nothing more than buzz words. Let's learn it here together in its simplest form.

Topics

Related talks

Browse the library