AI Controlled Cat Flap

Inventor Ben Hamm has created a cat flap which uses an AI to block entry if the cat is carrying prey.

Ben used machine learning software to allow the system to learn when his cat is trying to enter with prey (mouse, bird etc) When it detects an attack it activates the flaps 15 minute lock-down. Mr Hamm unveiled his invention at an event in Seattle.

Mr Hamm used two of Amazon’s tools to achieve his goal: DeepLens (a video camera specifically designed to be used in machine-learning experiments) and Sagemaker (a service that allows customers to either buy third-party algorithms or to build their own, then train and tune them with their own data, and finally put them to use)

He stated that the most time consuming part was supplying the database used by the AI with more than 23,000 photos so that the AI can learn. Each image had to be hand-sorted to display different states.

Image showing how the pictures were sorted.