Digital Thinking and Innovation: Machine Learning

Machine Learning

• Machine learning is a method of data analysis that automates analytical model building.

• It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns, and make decisions with minimal human intervention.

• Examples of machine learning include:

  • Virtual Personal Assistants
  • Predictions while Commuting
  • Videos Surveillance
  • Social Media Services
  • Email Spam and Malware Filtering
  • Online Customer Support
  • Search Engine Result Refining

  ARTIFICIAL NEUTRAL NETWORK

• A computer program inspired by certain presumed organizational principles of a real neural network (such as your brain)

• A series of algorithms that try to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.

EXAMPLES OF ARTIFICIAL NEUTRAL NETWORK

•Modular Neural Networks.

•Feedforward Neural Network – Artificial Neuron.

•Radial basis function Neural Network.

•Kohonen Self-Organizing Neural Network.

•Recurrent Neural Network(RNN)

•Convolutional Neural Network.

•Long / Short-Term Memory.

Frontiers of Artificial Intelligence

• AI Research Areas and Development include:
  • Robotics
  • Computer Vision
  • Speech Recognition
  • Natural Language Processing (NLP)

Robotics

• It involves building machines that are capable of performing physical tasks.
• Examples include:
  • ElliQ: a robot that can hold conversations with patients, remind them to take their medications, and lead them in light physical activities.

Computer Vision

• Primarily focused on equipping computers with the ability to interpret visual images.
• Examples include:
  • AmazonGo Stores: cameras track items taken off the shelves and identify returned items.
  • Facebook: uses facial recognition ("DeepFace") to automatically tag photos posted to a user's profile.

Speech Recognition

• The process of converting speech signals into digital data.
• Examples include:
  • Siri/Google Assistant/Galaxy: allows users to command the system to perform tasks or ask questions.

Artificial Intelligence

• Artificial Intelligence (AI): the concept of creating computer programs or machines capable of behavior we would regard as intelligent if exhibited by humans.

• An important truth: AI will impact many aspects of life, from livelihoods to a sense of self.

  Artificial Natural processing

• •Deals with the interaction between computers and humans using the natural language

  •Predictive Text: An input technology that facilitates typing on a mobile device by suggesting words the end user may wish to insert in a text field

  •Google Search (RankBrain): All of our Google search queries are being run through RankBrain

  –Learnt which search results we like

  –Find pages that might not have the exact words we searched for but that we would find interesting and relevant to what we are looking for

  Expert System

• A system that employs human knowledge captured in a computer to solve problems that ordinarily require human expertise.

• ES imitates an Expert's reasoning processes to solve specific problems.

• Keyword: problem-solving through Thinking + Perception + Action.

Why Use Expert Systems

• To preserve knowledge
• To help when expertise is scarce, expensive, and unavailable
• To help under time and pressure constraints (e.g., medical emergencies)
• To train new employees (e.g., CBT)
• To improve worker productivity (e.g., Ask the Expert)