AI algorithm families
Different families of algorithms solve different problems. We don't necessarily need to be experts in the details of each one, but having a grasp on what problems they can solve, and how they generally work, equips us with more tools when making decisions.
Traditional search algorithms are useful where several actions are required to achieve a goal, like finding a path through a maze. These algorithms evaluate possible states and attempt to find an optimal path . Typically, we have too many possible solutions to brute-force.
Biology-inspired algorithms are wondrous things happening all the time. The cooperation of ants in gathering food, the flocking of birds, estimating how brains work, and the evolution of organisms to produce strong offspring. These have inspired algorithms that are useful in AI.
Traditional machine learning algorithms leverages statistics to training models to learn from data. The umbrella of machine learning has a variety of algorithms that can be harnessed to improve understanding of relationships in data, to make predictions and decisions.
Deep learning algorithms are a broader family of approaches and algorithms that are used to achieve narrow intelligence and strive toward general intelligence. It attempts to solve general problems like vision, speech, and reasoning. It often leverages artificial neural networks.
Reinforcement learning algorithms are based on behavioural psychology and use feedback from actions performed to learn what sequences are more beneficial. Reinforcement learning is useful when you know what the goal is but don’t know what actions are reasonable to achieve it.
Create your own mental map of AI! If you enjoyed this thread, check out my book, Grokking Artificial Intelligence Algorithms: http://bit.ly/gaia-book, consider following me for more, or join my mailing list for infrequent knowledge drops in your inbox: https://rhurbans.com/subscribe.