The world is full of black-box functions: Protein design, Hyperparameter tuning, Supply line optimization, and many more. What if I told you there was a way to optimize them all while still being extremely efficient. In comes Bayesian Optimization(BO), an excellent algorithm used to optimize many black-box functions that are expensive to evaluate.

A black-box function is a function where you can only see the inputs and corresponding outputs. …


Few people in this world have done things that are extraordinary. When asked who are extraordinary people like Elon Musk, Steve Jobs, Albert Einstein would come to mind. All of these people have one thing in common. They are not satisfied with how things are right now, and they want to build a better future for all of us.

“You shouldn’t do things differently just because they’re different. They need to be… better.” — Elon Musk

What is Complacency?

According to the dictionary complacency is: “a feeling of quiet pleasure or security, often while unaware of some potential danger, defect, or the…

One of the biggest obstacles with machine learning is access to data. Now imagine that you could get some sample data and then replicate other similar data, so it looks like it's coming from the same distribution; however, it is not identical. This could be game-changing and could be used in many different fields such as health care, automotive, manufacturing, where there is not enough data — specifically, image data.

So how does it work?

You are given a data set X; nothing else. You will need to infer that there is some imaginary latent space (Z) that has given you X. …

(An Introduction To Fusion Energy)

By the year 2050, the earth is projected to be in turmoil. It is estimated that global greenhouse gas emissions will increase by approximately 50%, and the accelerated polar ice melt will result in numerous cities becoming submerged. These effects and much more will all occur because of climate change. And the leading contributor to climate change is the consumption of fossil fuels.

Fossil Fuels Generating Greenhouse Gases

This is why we need to change. We need a better way to power the earth. One that is healthier for the environment and one that is able to work all the…

(A Quick Introduction)

The Future is going to be an exciting place. There are so many new technologies that are ready to change the world. One of the technologies that I personally think will have a huge impact on the future is robotics. In this article, I want to share with you some of the types of robots that currently exist and describe the different parts that are used in their construction.

The Boring Ones

First, we have the Pre-programmed Robots. Frankly, they are not that interesting, but they are still critical to the operation of many companies. …

(An Introduction to Reinforcement Learning: Part 1)

Reinforcement Learning is going to be the future of AI. We have already seen huge advancements in the field with Self-driving cars and Alpha Go in 2016. However, before we can understand how these great innovations happened, we must first look at Reinforcement Learning's very basics. The Markov Decision Processes.

Some Quick Terminology

  • Agent: The algorithm that we are trying to create
  • Environment: The environment is the setting that you are in. This includes rewards, actions, and states
  • Actions: Actions are all the possible things that an Agent can do in an environment
  • Reward: The reward…

(A Deep Dive Into Reinforcement Learning)

It’s 20–20, and the first player to 21 wins. “ I’m going to beat you, Daniel,” says your little brother. You serve. And you lose. This is the reality for many people, including myself. So I decided to make an AI agent that could win for me.

In this project, I decided to replicate what Google DeepMind did on their Reinforcement Learning Paper from 2015. …

(Q-Learning and Deep Q-Learning)

A quick note before we start. If there are any terms that are new or confusing to you, I highly recommend taking the time to Google them so that you will be able to understand the content at a much deeper level

In the future, Artificial Intelligence will be omnipresent. In 2019 spending on AI reached around $37 billion. According to the International Data Corporation(IDC), spending on AI systems will reach $97.9 billion by 2023. One of the growing subfields in AI that I find fascinating is Reinforcement Learning. Right now, Reinforcement is used for the creation of self-driving cars…

(A Quick Introduction)

When most people hear the term Artificial Intelligence, they immediately think of futuristic, Terminator-style robots who are ready to take over the world. This is not the case! Artificial Intelligence is already here, and it has been for decades.

How Long Has AI Really Been Around?

Contrary to most people’s beliefs, the concept of AI has been around for centuries. AI-first appeared in Greek Mythology with the giant, animated, bronze warrior protector named Talos, whose purpose was to protect the island of Crete. Obviously, nobody knows if this protector actually existed, but the concept of AI was present centuries ago.

A little about me

My name is Marko Youngson, and I am 16. I live in Ottawa, Ontario, and I go to Glebe Collegiate Institute. I am very interested in emerging technologies and how they will have an impact on the world in the future. Currently, I am looking into AI and how to use Python to create neural networks. Hence the title I am an Innovate at The Knowledge Society (TKS), and I am just beginning my journey.

To start, what is TKS

TKS is a 10-month human accelerator for teens. It a place where you learn how to use exponential technologies to impact billions of people. It…

Marko Youngson

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store