In this post, we are going to answer a very elementary question, What is Machine Learning?
If you ask 10 different ML engineers to define machine learning, you might get 10 completely different answers. But all the definitions revolve around some specific key themes. So let's see a few of those definitions.
"Field of study that gives computers the ability to learn without being explicitly programmed" -Arthur Samual, IBM 1959(First person to coin the term Machine Learning)
let's try to get a little more concrete.
"Machine learning algorithms can figure out on their own, how to perform important tasks by generalizing from examples." University of Washington
So based on that portion from this definition, here's some aggregation of several definitions that I think makes things just a little bit more concrete and clear
Machine learning is fitting a function to examples and using that function to generalize and make predictions about new and unseen examples.
This hits on the fact that algorithm, or machine learning model, is based on the data that you feed it that's learning from examples(also known as training) and that the entire goal is to use that learned model(trained model) to make predictions about new examples. In other words, machine learning models learn from trans and past data to make predictions about future data. If you think about it, we all do this on a day to day basis. We learn from our past experiences to adjust our behavior or our views in the coming future. Keeping that definition in mind, an even simpler definition of machine learning is simply pattern matching. Let's look at a really simple example of machine learning.
So this is a very simple, single variable linear regression. So this plot is showing the number of umbrellas sold based on the amount of rainfall(mm).
So the model predicts how many umbrellas will be sold based on the amount of rainfall(mm). The model in this image is just represented by this red line, also known as best fit line. You might remember that the equation of a straight line is just y = mx+b . Where y is the thing that you're trying to predict(Target variable), which is umbrellas sold in this case, x is a thing that you're trying to use to predict it, that's rainfall in this case, m is the slope of your line, and b is the y-intercept. So this best fit line on this plot has an actual mathematical equation. The equation of that line is your model, or it's the function that is fit to this data.
So if we define Machine Learning again, a model learns from a pattern and data that was fed to it, fits a function to that pattern, and then uses that function to pick up on those patterns in future data to make predictions about it. In this case our function is simple straight line y=mx+b by using pattern in old data we are trying to find the best possible value of m and b
we have a function or a model that is fit to data, that's this line, now what does this model allow us to do or say, what purpose does it serve? Well, if it happens to rain 110 millimeters any day, even though I don't have any previous examples of days where it rained exactly 110 millimeters, I can say that based on my model, we could expect about 30 umbrellas to be sold on that day. So this is a very simple example of the machine learning model.
Our Other Post related to Machine Learning and Deep Learning:
- Top 5 Deep Learning Interview Questions
- A Complete Guide to Real-time Object Detection with TensorFlow
- How to use Google Colab( Free GPU for Deep Learning
- Data Analysis with one line of code in Python
- Why Numpy Arrays are faster
P.S: Please let us know in the comment box, About the topics that you want to learn