Artificial Intelligence (AI) is often used to refer to Machine Learning (ML). To create an ML algorithm, it is commonly thought that a large labeled dataset is necessary. However, understanding the process better reveals that big data is not as necessary as it first seems. A dataset is a collection of objects labeled by a human so that the algorithm can understand what it should look for. During training, the algorithm is shown the labeled data with the expectation that it will learn how to predict labels for objects, find universal dependencies and be able to solve the problem on data that it has not seen. Overfitting is a common challenge in training such algorithms and can be combatted by collecting more data, as long as the dataset is representative.
Related Posts
