Microsoft Azure Artificial Intelligence (AI) Fundamentals - Topics

What is Artificial Intelligence?

"The ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings." - Encyclopedia Britannica

"Intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans." - Wikipedia

Machine Learning Models

Machine Learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.

  • Regression Model is a supervised machine learning technique used to predict numeric values.
  • Classification Model is a supervised machine learning technique used to predict categories or classes.
  • Clustering Model is an unsupervised machine learning technique used to group similar entities based on their features.
Anomaly Detection is a machine learning based technique that analyzes data over time and identifies unusual changes.

Computer Vision

Computer Vision is a service to analyze images and video, and extract descriptions, tags, objects, and text.

  • Image Classification involves training a machine learning model to classify images based on their contents.
  • Image Analysis is to extract information from images, including "tags" that could help catalog the image or even descriptive captions that summarize the scene shown in the image.
  • Object Detection machine learning models are trained to classify individual objects within an image, and identify their location with a bounding box.
  • Semantic Segmentation is an advanced machine learning technique in which individual pixels in the image are classified according to the object to which they belong. 
  • Face Detection is a specialized form of object detection that locates human faces in an image. This can be combined with classification and facial geometry analysis techniques to infer details such as age and emotional state
  • Optical Character Recognition (OCR) is a technique used to detect and read text in images. 
  • Form Recognizer service is used to extract information from scanned forms and documents.

Natural Language Processing

Natural Language Processing (NLP) is used to understand written and spoken language.

  • Text Analytics service is to analyze text documents and extract key phrases, detect entities (such as places, dates, and people), and evaluate sentiment (how positive or negative a document is).
  • Speech Service is to recognize and synthesize speech, and to translate spoken languages.
  • Translate Text and Speech service is to translate text between more than 60 languages.
  • Language Understanding Intelligent Service (LUIS) service is to train a language model that can understand spoken or text-based commands.

Conversational AI

Conversational AI, AI agents participate in conversations with humans. Most commonly, conversational AI solutions use bots to manage dialogs with users.

  • QnA Maker, this is a cognitive service enables you to quickly build a knowledge base of questions and answers that can form the basis of a dialog between a human and an AI agent.
  • Azure Bot Service provides a platform for creating, publishing, and managing bots. Developers can use the Bot Framework to create a bot and manage it with Azure Bot Service - integrating back-end services like QnA Maker and LUIS, and connecting to channels for web chat, email, Microsoft Teams, and others.

Responsible AI

Responsible AI software development is guided by a set of six principles.

  • Fairness: AI systems should treat all people fairly. No bias based on gender, ethnicity, or other factors that might result in an unfair advantage or disadvantage to specific groups of applicants.
  • Reliability and Safety: AI-based software application development must be subjected to rigorous testing and deployment management processes to ensure that they work as expected before release.
  • Privacy and Security: The machine learning models on which AI systems are based rely on large volumes of data, which may contain personal details that must be kept private. Even after the models are trained and the system is in production, it uses new data to make predictions or take action that may be subject to privacy or security concerns.
  • Inclusiveness: AI systems should empower everyone and engage people. AI should bring benefits to all parts of society, regardless of physical ability, gender, sexual orientation, ethnicity, or other factors.
  • Transparency: AI systems should be understandable. Users should be made fully aware of the purpose of the system, how it works, and what limitations may be expected.
  • Accountability: Designers and developers of AI-based solution should work within a framework of governance and organizational principles that ensure the solution meets ethical and legal standards that are clearly defined.