Made for ITI event AI tools for POs for a general overview of Azure’s AI services

AI Methodologies

Machine Learning

• Dataset: A collection of data used to train or evaluate a machine learning model
• Training: The process of teaching a machine learning model using a dataset
• Feature: A property or characteristic of the data used as input to a model (e.g., color, size)
• Label: Tag that identifies the correct output or category for data points in a dataset
• Data labeling: Process of identifying raw data and adding one or more meaningful and informative labels to provide context so that a machine learning model can learn
• Ground truth: A properly labeled dataset that you use as the objective standard, or like the accuracy of your trained model will depend on the accuracy of your ground truth
• Machine Learning (ML): Algorithms that learn from data to make predictions or decisions, used for tasks like classification, regression, and clustering
• Supervised machine learning: A type of machine learning where the model is trained on labeled data, meaning the input data comes with the correct output
• Unsupervised Learning: A type of machine learning where the model is trained on data without labels, and it finds hidden patterns or structures on its own
• Classification: Process of finding a function to divide a labeled dataset into classes/categories
  • Examples: Classify emails as spam or not, classify medical images as healthy or diseased, etc..
• Regression: Process of finding a function to correlate a labeled dataset into a continuous variable/number
  • Examples: Predict weather, forecast sales, etc..
• Clustering: Process of grouping unlabeled data based on similarities and differences
  • Example: Group animals into clusters based on characteristics like habitat, diet, or physical traits (e.g., mammals, reptiles, birds)

Natural Language Processing

• Natural language processing (NLP): Machine learning that can understand context of a text which enables you to analyze and interpret text, email messages, sentiment analysis, translation, voice assistance, etc..
• Text Summarization: Creating a brief summary of a longer text while preserving its key points and overall meaning