By Daniel Glass
Originally Posted on LinkedIn
Generally speaking, the goal of machine learning (ML) is to approximate functions. But what is a function?
Let's think of it as an operation that transforms input and produces output. A literal function could be `y = 2x + 5`. `x` is the input, `y` is the output, and `2x + 5` is the operation that transforms the input and produces the output.
That's great and all, but how is this useful to us? Well, we need to think of functions in a more abstract way. Let's use labor management as an example. Let's say that we want to be able to predict how long a warehouse task should take given characteristics of that task. The input could be the characteristics of the task, the output could be how many seconds it should take to complete the task, and the operation is ...? Well, we don't know what the operation is. It probably isn't `2x + 5`.
Predicting how long a warehouse task should take is a real-world example where we can use ML to approximate a function that we don't know. In the next post, we are going to talk about how we can use ML to approximate functions like this one.
In the meantime, check out how Cellaware has implemented real world applications for ML/AI in the warehousing and distribution industry. Schedule your free demo today!
Comments