Hi, I’m Monte Zweben, and I'm happy you're here. Welcome to ML Minutes, where we solve big problems in little time. Every two weeks, we invite a different thought leader on the show to talk about a problem they’re solving with Machine Learning, with an exciting twist: our guest has only one minute to answer each question we throw at them. Let’s get started!
To show you what this looks like, I’ll be answering my own ML minute by explaining Machine Learning to you in a minute or less. Starting… now! *ticks*
Most computer programs are given a set of rules that tell the computer what to do in any given situation. Machine learning is about building computer programs that can learn to draw their own conclusions based on data they’re given. Machine learning models “train” on a set of data examples in order to make predictions on new data.
For example, imagine a computer that learns musical notes by analyzing classical songs. Each note in a melody is labeled with its corresponding note, like B flat or F sharp, and the computer is shown hundreds of thousands of songs. After this training, you give the computer a new melody, and it’s able to show you the correct musical notes as it plays. You never told it what the notes actually were. You just showed it examples, and it created an internal representation of sounds that it could compare to new examples. We call this inferring a model, and this is how machine, and some human, learning works!
If you like what you heard, check out our interviews with other thought leaders in this same structure. I’m Monte Zweben, and this was an ML Minute.