Image classification
a form of computer vision in which a model is trained with images that are labeled with the main subject of the image (in other words, what it’s an image of) so that it can analyze unlabeled images and predict the most appropriate label - identifying the subject of the image.
Object detection
a form of computer vision in which the model is trained to identify the location of specific objects in an image. returns bounding box coordinates
semantic segmentation
an advanced form of object detection where, rather than indicate an object’s location by drawing a box around it, the model can identify the individual pixels in the image that belong to a particular object
Generative AI
a branch of AI that enables software applications to generate new content; often natural language dialogs, but also images, video, code, and other formats.
language model
trained with huge volumes of data - often documents from the Internet or other public sources of information, used to generate content
Speech recognition
the ability of AI to “hear” and interpret speech. Usually this capability takes the form of speech-to-text
Speech synthesis
the ability of AI to vocalize words as spoken language. Usually this capability takes the form of text-to-speech
optical character recognition
The basis for most document analysis solutions, can identify the location of text in an image, more advanced models can also interpret individual values in the document
Supervised machine learning
general term for machine learning algorithms in which the training data includes both feature values and known label values. used to train models by determining a relationship between the features and labels in past observations, so that unknown labels can be predicted for features in future cases.
Regression
a form of supervised machine learning in which the label predicted by the model is a numeric value
Classification
a form of supervised machine learning in which the label represents a categorization, or class
binary classification
he label determines whether the observed item is (or isn’t) an instance of a specific class. binary classification models predict one of two mutually exclusive outcomes
Multiclass classification
extends binary classification to predict a label that represents one of multiple possible classes
Unsupervised machine learning
involves training models using data that consists only of feature values without any known labels. determine relationships between the features of the observations in the training data.
clustering
most common form of unsupervised machine learning. clustering algorithm identifies similarities between observations based on their features, and groups them into discrete clusters.
Deep learning
an advanced form of machine learning that tries to emulate the way the human brain learns
neural network
simulates electrochemical activity in biological neurons by using mathematical functions
loss function
used to compare the predicted ŷ values to the known y values and aggregate the difference (which is known as the loss)
Azure Machine Learning
a cloud service for training, deploying, and managing machine learning models. It’s designed to be used by data scientists, software engineers, devops professionals, and others to manage the end-to-end lifecycle of machine learning projects.
Automated machine learning (AutoML)
makes it easy to run multiple training jobs with different algorithms and parameters to find the best model for your data.
Tokenization
LLMs break down their vocabulary into tokens. Tokens include words, but also sub-words (like the “un” in “unbelievable” and “unlikely”), punctuation, and other commonly used sequences of characters
vector
an array of multiple numeric values, like [1, 23, 45], each vector has multiple numeric elements or dimensions, and we can use these to encode linguistic and semantic attributes of the token to help provide a great deal of information about what the token means and how it relates to other tokens, in an efficient format.
embeddings
optical character recognition
provides the ability to detect and read text in images.
