Artifical Intelligence (AI) Flashcards
(12 cards)
machines that can perform tasks that require human intelligence
artificial intelligence (AI)
developing algorithms and models that can allow computers to perform tasks without explicit instructions; primary focus is working with and learning from data
machine learning (ML)
a computational model featuring a collection of nodes organized into layers
neural network
occurs when you train your model on input data and output data (called labels); useful for classification tasks
supervised learning
matrix used to evaluate the performance of a supervised learning model
confusion matrix
the four entries in the confusion matrix
true positives (TP); true negatives (TN); false positives (FP); false negatives (FN)
correctly identified something as positive
true positive
correctly identified something as negative
true negative
incorrectly identified something as positive
false positive (type 1 error)
incorrectly identified something as negative
false negative (type 2 error)
we do not provide our model any labels; our model can learn properties about the data on its own; great for associations and clustering
unsupervised learning
one or more agents learn to make decisions as they interact with the environment; they receive rewards and penalties; respond to this feedback; new actions will maximize their rewards over time
reinforcement learning