HOW DO MACHINES LEARN⠀? ⠀
⠀
Machine learning is a subfield of artificial intelligence. The purpose of AI is to make an intelligent machine that thinks as good as or even better than a human.⠀ ⠀
At its heart, machine learning is the task of making computers more intelligent without explicitly teaching them how to behave. It does so by identifying patterns in data.⠀ ⠀
Machine learning algorithms build a mathematical model based on sample date, known as training data, in order to make predictions or decisions. Usually, more data means better predictions.⠀ ⠀
3 of them most widely adopted machine learning methods are:⠀
- Supervised learning⠀
- Unsupervised learning⠀
- Reinforcement learning⠀ ⠀
Today, supervised learning is the most common method of ML. When training a supervised learning algorithm, the training data will consist of inputs paired with the correct outputs. Data is labeled by humans.⠀ ⠀
In unsupervised learning, data is unlabeled, so the learning algorithm is left to find patterns among its input data. Also, since you don’t know what the outcomes should be, determining accuracy is really difficult.⠀ ⠀
Reinforcement learning is learning best actions based on reward or punishment. In RL, you teach a machine how to behave in an environment by telling it how good it’s doing.⠀ ⠀
An algorithm may be fed data with images of dogs labeled as dog and images of cats labeled as cat. By being trained on this data, the algorithm should be able to later identify unlabeled dog and cat images.⠀ ⠀