0:0011:04

Explain Machine Learning as to a kid

Precious Kolawole 11:04 2021

A burned hand at a candle explains machine learning better than jargon

A toddler touches a candle flame, cries, and two days later refuses to reach toward a red, bright stovetop. That small moment is machine learning: a pattern learned from one experience and used to predict the next. Precious Kolawole, a machine learning engineer at Lendsqr, uses it to cut through the buzzwords for newcomers. So what really separates a learned model from a program told exactly what to do?

Learn how models turn labeled examples into predictions, plus a beginner path from Python to ML

Watch on YouTube

In short

Precious Kolawole, a data scientist and machine learning engineer at Lendsqr, explains machine learning in its simplest form using a child who learns from a candle flame and a cat-image classifier. She contrasts learning from data with explicit programming, explains what a model is, and in the Q&A lays out a beginner path from Python to data science to machine learning.

“To be clear, this is just machine learning because this young child learned pattern from the candle flame to make predictions on the stovetop.”
“And the ultimate goal of machine learning is to simplify large amount of data into a single decision or a prediction.”

What you will learn

  • Explain machine learning to a non-technical person with a simple everyday analogy.
  • Distinguish a model that learns patterns from data from a program built on explicit instructions.
  • Describe how a classifier learns a function Y = f(X) from labeled examples during training.
  • Recognise the kinds of data-heavy decisions where machine learning adds the most value.
  • Plan a beginner learning path from Python through data analysis and data science to 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
11:04
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 learn from data: it observes patterns, learns from them and uses what it learns to make predictions.

How is machine learning different from explicit programming?

In explicit programming a developer writes instructions and the computer produces output. In machine learning you give the computer inputs and their outputs, such as images and labels, and it creates the model on its own.

What kinds of decisions is machine learning good for?

Decisions that are almost impossible to make without data, such as which stock to invest in or whether a borrower will pay back or default on a loan.

How should a complete beginner get started in machine learning?

Learn Python first, then move into data analysis and visualization, then data science, and finally machine learning topics such as model building, deployment and deep learning.

Can you do machine learning without writing code?

Some ready-made platforms, which she believes are available on Microsoft Azure, let you build and use models with little code, but in most cases you must 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