AI in the Family: how to teach machine learning to your kids

By Matthew T.

DearingAs we collectively experience the increasing pervasiveness of machine learning algorithms that drive so many services and functions in our society, it is clear to us that a new workforce of specialized programmers and computer scientists exist behind this reality.

You may even be one of these wunderkinds who expanded your early coding education to include the development of learning algorithms for enhancing existing software applications or creating entirely new deep learning systems.

Or, you may be an “older-kinder” who quickly circled back to catch the wave of AI excitement to coral it into your well-honed development tool kit.

Either way, while the current generation of programmers is running with machine learning trends, the next round of professionals who will fill our shoes – those young ones who are learning PowerPoint and Common Core math in grade school today – are experiencing AI as something that is… just already something normal.

AI-powered digital voice assistants are commonplace in homes, and kids are thrilled to ask what the weather is today repeatedly or to have the device tell a joke.

There are people behind this magic, of course, and the fad of learning this trade could become just that if we don’t consider how to ensure a pipeline of future machine learning developers to carry our torch.

As a parent, aunt, uncle, cousin or any immediate relative to a young one in the family, sharing our professional excitement and skills in machine learning with our kids is a wildly effective way to inspire and establish the future generation of AI developers.

But, our education into machine learning may have been through graduate-level course work, hundreds of hours pouring over Python code, studying tutorials or exploring the latest published literature.

Bringing all this technical know-how to kids may appear as something that would be easier left to, “hey, kid, you’ll find out when you’re older.

”Many tools currently exist that support the introduction and early education of computer science and programming to kids.

The JavaScript framework Blockly created by Google is the foundation for the kid-friendly interface from the MIT Media Lab called Scratch.

A boon for millions of young coders around the world, learning to code with Scratch overcomes initial conceptual and technical hurdles when being first introduced to the world of computer science.

The Hour of Code movement thoroughly leverages Scratch-based interfaces to bring entertaining and educational online coding experiences for learners as young as second grade.

Two organizations are broadening the success of Scratch and its accessibility for learners by building extensions of machine learning teaching platforms to provide guided online environments for training models to perform useful functions and interactive games.

Machine Learning for Kids, developed by Dale Lane in 2017, calls on the power of IBM Watson to support the backend algorithms that kids can tap directly into through visual blocks of logic and commands.

The Dalton Learning Lab has a beta release of another educational platform built on Scratch demos with integrated machine learning capabilities to teach AI principals to kids.

With designed lessons plans and tutorials for building chatbots, Flappy Bird-style games, and image classification demos, the world of machine learning is opening up to the youngest of curious minds.

Scratch is an excellent programming interface for learners of any age.

But, for those of you who bring any level of machine learning expertise to the table, it’s likely you already put in the heavy lifting at home to set up your personal AI development environment.

Finally, this is your opportunity to show off your wheelhouse of tools and digital learning gadgetry to the family!Presenting your latest Jupyter notebook trials and experimentation might seem a bit tough for the grade-schooler in your household.

However, many kids heading into middle school are already being introduced to Python programming at school or in local coding clubs.

So, showing-and-telling your way through Python-based machine learning routines is now entirely reasonable!The only remaining catch is that your code is so messy.

It’s not straightforward and always a work in progress.

To make your family machine learning session easier, Google’s online educational resources for developers is extensive and includes ready-to-roll machine learning notebooks you can use to present solid examples without any prep work.

Let’s check out a simple yet sophisticated example right now that you can run through with any young one at home.

Figure 1.

Let’s train our model together!Of course, to a novice or first-timer staring at this syntax, it will look like a meaningless foreign language.

But this is where you – the machine learning craftsperson – swoop in as the crucial learning partner!.Your one-on-one time talking through each step and describing what is happening behind the scenes will be straightforward for you, and with the immediate gratification of seeing real results within minutes can spark genuine new interest in your young padawan.

Figure 2.

Visualizing how the image of a dog is processed through the classification of features in deep learning.

After watching real code process real learning right before their eyes, the kid in your family might be ready to jump into more AI exploring.

Then, you will have successfully played your small part in keeping the profession all in the family.

Bio: Matthew T.

Dearing is an applications developer who supports STEM educational opportunities and keeps a pulse on the latest as a top-rated editor of scientific and technical publications from clients around the world.

Resources:Related: var disqus_shortname = kdnuggets; (function() { var dsq = document.

createElement(script); dsq.

type = text/javascript; dsq.

async = true; dsq.

src = https://kdnuggets.



js; (document.

getElementsByTagName(head)[0] || document.


appendChild(dsq); })();.. More details

Leave a Reply