Get in Touch

Course Outline

Current state of the technology

  • Existing applications
  • Potential future uses

Rules based AI 

  • Simplifying decision processes

Machine Learning 

  • Classification
  • Clustering
  • Neural Networks
  • Categories of Neural Networks
  • Review of working examples and discussion

Deep Learning

  • Foundational terminology 
  • Criteria for using Deep Learning versus alternatives
  • Estimating computational resource requirements and costs
  • Brief theoretical overview of Deep Neural Networks

Deep Learning in practice (mainly using TensorFlow)

  • Data preparation
  • Selecting loss functions
  • Choosing the appropriate neural network architecture
  • Balancing accuracy against speed and resource usage
  • Training neural networks
  • Evaluating efficiency and error rates

Sample usage

  • Anomaly detection
  • Image recognition
  • ADAS

Requirements

Participants are expected to possess a background in engineering and prior programming experience in any language. However, no hands-on coding is required during the course sessions.

 14 Hours

Number of participants


Price per participant

Upcoming Courses

Related Categories