Get in Touch
 Duration 21 hours

Course Outline

Introduction to On-Device AI

  • Core principles of machine learning on local devices
  • Benefits and hurdles associated with Small Language Models
  • Hardware limitations in mobile and IoT contexts

Optimizing Models for On-Device Use

  • Techniques for model quantization and pruning
  • Using knowledge distillation to create smaller, faster models
  • Selecting and adjusting models for optimal local performance

Platform-Specific AI Tools and Frameworks

  • Getting started with TensorFlow Lite and PyTorch Mobile
  • Applying platform-specific libraries for local AI tasks
  • Strategies for deploying across different platforms

Real-Time Inference and Edge Computing

  • Methods for achieving rapid, efficient inference on hardware
  • Harnessing edge computing capabilities for on-device AI
  • Case studies showcasing real-time AI use cases

Power Management and Battery Optimization

  • Tuning AI apps for maximum energy efficiency
  • Striking a balance between performance and power usage
  • Extending battery life in AI-enabled devices

Security and Privacy in Local AI

  • Protecting data integrity and user privacy
  • Handling data locally to maintain privacy
  • Secure protocols for model updates and maintenance

User Experience and Interaction Design

  • Crafting intuitive AI interactions for end-users
  • Integrating language models seamlessly into user interfaces
  • Testing and gathering feedback on on-device AI features

Scalability and Long-Term Maintenance

  • Managing model updates on already deployed devices
  • Building scalable solutions for on-device AI
  • Monitoring performance and analyzing deployed AI systems

Project and Assessment

  • Building a prototype in a chosen field and preparing it for specific hardware
  • Presenting the developed on-device AI solution
  • Evaluation focusing on efficiency, innovation, and practical utility

Wrap-up and Future Directions

Requirements

  • A solid grasp of machine learning and deep learning principles
  • Proficiency in Python programming
  • Foundational understanding of hardware limitations in AI deployment

Target Audience

  • Machine learning engineers and AI developers
  • Embedded systems engineers exploring AI integrations
  • Product managers and technical leaders overseeing AI initiatives

Number of participants


Price per participant (excl. VAT)

Upcoming Courses

Related Categories