🤖What is Machine Learning?
<style type="text/css">iframe {
width: 100%;
aspect-ratio: 16 / 9;
}
</style>
<h1>Overview</h1>
<p>This project covers the fundamentals of machine learning, a branch of artificial intelligence that uses data and algorithms to train a machine to imitate intelligent human behavior.</p>
<p>Below is a list of just a few ways humans use machine learning. Can you think of any more?</p>
<ul>
<li>Facial recognition</li>
<li>Social media monitoring</li>
<li>Marketing and advertisement</li>
<li>Self-driving cars</li>
<li>Reading handwriting from phones</li>
<li>Virtual assistants (Siri, Alexa, etc)</li>
<li>Customer service chatbots</li>
<li>Planning out the fastest route to a destination</li>
<li>New song recommendations</li>
<li>Farmers checking out and diagnosing problems with crops</li>
<li>Clinical decision support and robotic assistance for medical procedures </li>
</ul>
<h1>How Does It Work?</h1>
<p>Check out the video below to see an example of Google's machine learning platform, Teachable Machine!</p>
<p style="text-align: center"><iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen="" frameborder="0" referrerpolicy="strict-origin-when-cross-origin" src="https://www.youtube.com/embed/T2qQGqZxkD0?si=Odfh8FGJQJUOgZAG" title="YouTube video player"></iframe></p>
<p>Let’s highlight the basic steps of machine learning.</p>
<ul>
<li><strong>Collecting Data</strong> – Machines learn from the data you give them. The quality of data you feed the machine will determine the accuracy. What could be a good source of data for training AI?</li>
<li><strong>Preparing the Data</strong> – You can do this by removing unwanted data, randomizing the data so the ordering does not affect the learning process, visualizing it so you better understand how the data is structured and being represented, and splitting the data between a training set and a testing set. The training set uses the samples your model learns from. The testing set is used to check the accuracy of your training model.</li>
<li><strong>Choosing a Model</strong> – This determines the output you get after running the training data. Scientists and engineers have developed various models suited for different tasks like speech recognition, image recognition, prediction, etc.</li>
<li><strong>Training the Model</strong> – This is when you pass the prepared data to your machine learning model to find patterns and make predictions. With more training and more data, the model gets better at predicting.</li>
<li><strong>Evaluating the Model</strong> – Test the performance of the model with entirely new, unseen data.</li>
<li><strong>Parameter Tuning</strong> – Parameters are the variables (changes) in the model that the programmer decides. Tuning the parameter’s values may increase the accuracy.</li>
<li><strong>Making Predictions</strong> – Apply your model to new data to predict the likelihood of a particular outcome. How accurate would the machine learning app you used be on data from your photos?</li>
</ul>
<h1>What's Next?</h1>
<p>In the following lessons, you will learn to implement machine learning steps in an open-source (free) software called PictoBlox. Happy learning!</p>