PDF download Download Article PDF download Download Article

Artificial intelligence is the science of making machines or programs that can emulate human processes. It is being used in many industries and fields. Have you ever wondered what all the fuss is about? In this article, you will learn how to create one of these programs.

Part 1
Part 1 of 5:

Understanding What AI is

PDF download Download Article
  1. One definition of AI is that AI is a branch of computer science focused on building programs that can perform tasks and solve problems, like the human mind can. AI doesn’t necessarily have to use computers, but usually it does. [1] .
    • Artificial Intelligence has been dreamed about since the days of Ancient Greece [2] , but the modern version of the field was introduced by Alan Turing, with his paper “Computing Machinery and Intelligence.”
    • AI can perform many tasks, such as text generation, converting text to audio, recognizing images, and even creating art. In the modern day, AI is created in many different ways. For example, ChatGPT uses Reinforcement Learning from Human Feedback, where human trainers create theoretical conversations between an AI assistant and a human for the AI to learn from. After that, the model’s responses were ranked by humans.
    • Usually, AI is created using libraries (pieces of code programmers share with each other), like TensorFlow and PyCharm. These libraries obscure away some of the complexity of making AI, allowing programmers to focus on the bigger picture. In this article, you will use a program called Teachable Machine to create your own AI. Teachable Machine uses TensorFlow, but abstracts away the details even further, allowing you to make an AI without even writing a single line of code! The drawback is that you can only create certain types of AI, unlike TensorFlow, which is much more versatile.
  2. Advertisement
Part 2
Part 2 of 5:

Planning the AI

PDF download Download Article
  1. Your AI doesn't have to solve a problem, but more people will use it if it does.
    • For example, does it help someone identify dangerous plants? Or does it help someone identify water that is unsafe to drink ?
    • The problem can be anything, it doesn't have to be serious. You could create an AI that can tell the difference between someone exercising or someone relaxing.
  2. Every AI has to have an interface, so people can more easily use it.
    • For example, people use Google Lens through a camera based interface [3] , and Siri via a microphone based interface.
    • You probably don't have the resources or education to create a complex AI like ChatGPT. [4]
    • Look up new advancements in AI using websites like Google or arXiv.
  3. Even if your AI has good intentions, it might still be able to be used for doing illegal things. [5]
    • Does your AI do anything illegal? If so, you may want to think about changing your idea to avoid serious consequences, like fines or jail. [6]
    • What unwanted biases could your AI have, and how can you remedy them?
  4. You can write it anywhere or anyway you want, as long as you can read and access it.
    • This will help you remember what your plan is. You can't be forgetting import
  5. Advertisement
Part 3
Part 3 of 5:

Collect Training Data

PDF download Download Article
  1. Training data is information you use to teach an AI. What type of data you should collect depends on what you want your AI to do [7] .
    • For example, if you want to make an AI that can tell the difference between cats and dogs, look online for images of dogs and cats, and sort the images.
    • You can use a dataset search engine like Google Dataset Search to find training data.
    • If you are creating a sound model, ignore this part, because you cannot upload sounds that were not recorded using Teachable Machine. [8]
  2. Try collecting the data in the places your AI will be used.
    • This could be anything from asking family members to take pictures of their pets or recording bird sounds.
    • Remember, don't trespass on people's property to collect training data.
  3. Advertisement
Part 4
Part 4 of 5:

Making the AI

PDF download Download Article
  1. Go to the Teachable Machine website . Select the type of model that makes the most sense for the AI you want to make.
    • Choose image project if your AI classifies images.
    • Choose pose project if your AI classifies poses.
    • Choose audio project if your AI classifies sounds.
    • Teachable Machine only supports these types of projects [9] , so if you want to make an AI that doesn't classify one of those things, you can't use Teachable Machine. Tensorflow or ml5.js are good options, but they require programming.
    • Click on the 'Add a class' button to do this.
    • If your AI classifies cats and dogs, you need 2, the default. Don't add anything if this is the case. If it classifies cats, dogs, and pigs, you need 3, so press the button once. [10]
    • With sound models, remember, one of the classes is for background noise.
    • You don't have to name your classes, but you might get confused if you don't.
    • You can upload the training data, or add it using your microphone, or any combination of the two!
    • While you wait, remember that your AI is getting better by the second!
    • This probably won't take much time, unless you added extra training cycles.
    • If it isn't working well, try collecting more training data. [11]
    • Add more training cycles by clicking on 'Advanced', and upping the number of epochs to your liking. It will take more time, but your AI will be better.
    • Use data you didn't train your AI on for testing. [12]
    • Ask other people to test your AI!
  2. Advertisement
Part 5
Part 5 of 5:

Exporting your AI

PDF download Download Article
  1. 1
    Click on the 'Export Model' button.
    • If you want to get a link to share with friends, click on 'Upload my model'.
    • If you want to get a code snippet, scroll and copy and paste the text box you see.

Expert Q&A

Ask a Question
      Advertisement

      Tips

      Submit a Tip
      All tip submissions are carefully reviewed before being published
      Thanks for submitting a tip for review!
      Advertisement

      About This Article

      Thanks to all authors for creating a page that has been read 43,225 times.

      Is this article up to date?

      Advertisement