Category: My Blog



Machine learning : 


Arthur Samuel already said back in 1959 that "Machine learning is about giving computers "the ability to learn without being explicitly programmed." And this means, for us that we can, for example, create a machine learning model that can detect the difference between a cat and a dog although, we will not explicitly tell our model how this is done.


Machine learning tasks are typically classified into two broad categories, depending on whether there is a learning "signal" or "feedback" available to a learning system:

Another categorization of machine learning tasks arises when one considers the desired output of a machine-learned system

Among other categories of machine learning problems, learning to learn learns its own inductive bias based on previous experience. Developmental learning, elaborated for robot learning, generates its own sequences (also called curriculum) of learning situations to cumulatively acquire repertoires of novel skills through autonomous self-exploration and social interaction with human teachers and using guidance mechanisms such as active learning, maturation, motor synergies, and imitation.

What kind of problems can we actually solve with machine learning?

 Sentiment analysis, handwriting recognition, and scene classifications are really just three examples. You always have an input that we, as humans can easily interpret, but for a computer program, that's a lot harder. But with already existing machine learning models, we can solve these problems by preparing an input, like an image on the right and pass it througha classifier and get a prediction of what kind of a scene is displayed in that image.

This is also just a small amount of the possibilities that machine learning opens for modern applications. Things like face detections, speaker identification or text prediction is no longer something that only big companies like Apple can do. This is now possible for every developer who uses the Apple ecosystem. Now, you've seen what machine learning offers us.

So with iOS 11, Apple introduced three frameworks that are related to machine learning.Vision, NLP, and Core ML. All of them can be used by your application. And vision is a framework that does everything related to computer vision and images. NLP is all about text processing, natural language processing. You can use it to do things like language identification, tokenization and more. And with Core ML, you can integrate trained machine learning models into your app.