Get in Touch

Course Outline

Current state of the technology

  • Existing technological applications
  • Potential future applications

Rules-based AI

  • Simplifying decision-making processes

Machine Learning

  • Classification techniques
  • Clustering methods
  • Neural Networks
  • Varieties of Neural Networks
  • Review of practical examples and group discussions

Deep Learning

  • Key terminology
  • Guidelines on when to utilize Deep Learning and when to avoid it
  • Assessing computational requirements and associated costs
  • A concise theoretical overview of Deep Neural Networks

Practical Deep Learning (primarily using TensorFlow)

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

Sample use cases

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

Requirements

Participants are expected to possess a programming background in any language along with engineering knowledge. However, no coding is required throughout the duration of the course.

 14 Hours

Related Categories