B P2 C 11 Artificial Intelligence in Cardiovascular Medicine Flashcards
_____ is the process of improving the ability to complete a task based on experience.
As the task is repeated, ML improves by getting feedback (via an error or loss function) and changing the way it performs the task (by changing with weights and biases of the mathematical functions that comprise the “neurons” in a neural network, for example), until the feed- back is that the task is done correctly, or at least above a certain standard.
Learning
_____ learning is the most commonly used form of ML.
Supervised learning
Supervised learning requires labeled data (images and captions, ECGs and their rhythm description),with labels often provided by human experts.
In _____ learning, the **task revolves around the structure of the data* itself.
Unsupervised learning
One most common form of unsupervised learning is _____, in which the model clusters data based on its characteristics, instead of based on labels during the training stage.
Clustering
The model is fed only unlabeled data, and clusters samples based on similarity, using each sample’s distance (Euclidian or other) from other samples.
_____ learning is a method used to apply supervised learning to problems for which the datasets available to train a network are relatively small.
Transfer learning
In this method, a network is developed to solve a problem that has enough labeled samples (the “primer”),and then it is retrained to solve a similar task with a much smaller dataset.
_____ learning develops the optimal strategy for an agent in an environment with known rules and rewards.An example would be a chess player—learning chess by playing against itself, without labels or recorded human games
Reinforced learning
The use of the 12-lead ECG to identify left ventricular dysfunction (present asymptomatically in 3% to 9% of people) is undergoing prospective evaluation in a large cluster-design pragmatic trial
EAGLE Trial
