AI can be leveraged to add intelligence and capabilities to any number of robotics, IoT, and automation projects. However, we are often using AI with our most confidential, personal, and protected data - so we don’t always want to send this data out to a large corporation. Running our own on-premise AI infrastructure is an option that is becoming more practical, but can incur large up-front costs and sometimes underperform. Cloud providers offer dedicated GPU instances, but the costs for these services add up quickly. Can we leverage serverless AI to find a good balance of performance and cost?
Join Viam’s Principal Developer Advocate Matt Vella to learn about:
- Choosing when to use local or serverless AI solutions
- How to integrate AI with your hardware and smart machine projects
- How to deploy end-to-end AI assistants