Common AI Workloads Flashcards
What features and capabilities does Azure Machine Learning provide?
Automated Machine Learning
Azure Machine Learning designer
Data and compute management
Pipelines
What is labelling?
The process of identifying raw data (images, text files, audio, etc.) and adding one or more meaningful and informative labels to provide context for machine learning.
What is unsupervised learning?
Unsupervised learning is a subcategory of ML defined by its use of unlabelled datasets to train models that discover hidden patterns or data groupings without human intervention.
What is supervised learning?
Supervised learning is a subcategory of ML defined by its use of labelled datasets to train models that classify data or predict outcomes precisely.
What are two examples of supervised learning models?
Classification and Regression.
What is an example of unsupervised learning models?
Clustering.
What is a dataset?
A collection of data.
What’s the difference between unsupervised ML labelling and supervised ML labelling?
With supervised ML, labelling is prerequisite to produce training data and each piece of data will generally be labelled by a human.
With unsupervised ML, labelling is produced by the computer and may not be human readable.
What is regression?
A form of machine learning that is used to predict a numeric label based on an item’s features.
What is time series forecasting?
Regression with a time-series element, that predicts numeric values at a future point in time.
What is classification?
A form of machine learning that is used to predict which category, or class, an item belongs to.
What is clustering?
A form of machine learning that is used to group similar items into clusters based on their features.
What is a ground truth?
A properly labelled dataset used as the objective standard to train and assess a given model.
The accuracy of the trained model is dependant on the accuracy of the ground truth.
What are the stages of the ML pipeline and what are they for?
Pre-processing - preparing data and feature engineering before passing the data to an ML model for training or inference.
Post processing - translating the output of a ML model back into a human readable format
Training - the process of training the model
Serving - the process of deploying the model to an endpoint to be used for inference
Inference - Invoking a ML model by sending a request and expecting back a prediction.
What is data cleaning?
The process of correcting errors within a dataset.
What is data reduction?
Reducing the volume of data, or applying dimensionality reductions to reduce the dimensions of inputted vectors