Part of the Learn a New Thing Every Day Series #3
Here is something I did not know….there are three general categories of learning that artificial intelligence (AI)/machine learning utilizes to actually learn. They are Supervised Learning, Unsupervised Learning and Reinforcement learning.
Supervised Learning: The machine has a “teacher” who guides it by providing sample inputs along with the desired output. The machine then maps the inputs and the outputs. This is similar to how we teach very young children with picture books. According to Yann LeCun, all of the AI machines we have today have used this form of learning (from speech recognition to self-driving cars).
Reinforcement Learning: Yann LeCun believes this plays a relatively minor role in training AI and is similar to training an animal. When the animal displays a desired behavior it is given a reward. According to the Wikipedia entry on Machine Learning, reinforcement learning is defined as “a computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle), without a teacher explicitly telling it whether it has come close to its goal. “
Unsupervised Learning: This is the most important and most difficult type of learning and would be better titled Predictive Learning. In this case the machine is not given any labels for its inputs and needs to “figure out” the structure on its own. This is similar to how babies learn early in life. For example they learn that if an object in space is not supported it will fall