Get in Touch
 Duration 14 hours

Course Outline

Current technological landscape

  • Existing implementations
  • Potential future applications

Rule-based AI

  • Simplifying decision-making processes

Machine Learning

  • Classification
  • Clustering
  • Neural Networks
  • Variations of Neural Networks
  • Demonstration of working examples and discussion

Deep Learning

  • Foundational terminology
  • Criteria for adopting or avoiding Deep Learning
  • Estimating computational resources and costs
  • Concise theoretical overview of Deep Neural Networks

Applied Deep Learning (primarily using TensorFlow)

  • Data preparation
  • Selecting an appropriate loss function
  • Choosing the suitable neural network architecture
  • Balancing accuracy against speed and resource usage
  • Training neural networks
  • Measuring efficiency and error rates

Practical use cases

  • Anomaly detection
  • Image recognition
  • ADAS (Advanced Driver Assistance Systems)

Requirements

Participants are expected to possess programming experience in any language and a solid engineering foundation. However, they are not required to write code during the course sessions.

Related Categories