An Amazon employee has built a system based on artificial intelligence to help train
cats. This invention was revealed at an event in Seattle last month. He used
machine-learning to train the infrastructure to recognise when his cat was
approaching with a rodent or a bird in its mouth. When it detected this, the
computer attached to the flap’s lock triggered and it barred entry to the
animal for fifteen minutes.
Ben Hamm who developed the system used two of Amazon’s tools
to achieve his goal. One of these is Deep
Lens: a video camera that is specifically designed to be utilised in
machine learning experiments. The other one is Sagemaker. This allows
customers to either buy third-party algorithms or to build their own, to
customise them with their own data and to put them to use.
To build this system, he had to input more than 23,000
photos to it. This was the most time-consuming task of the process according to
Hamm. Each of those pictures had to be hand-sorted to determine whether the cat
was in view, whether it was coming and if it was carrying a prey. He used a technique called supervised
learning in which the computer is trained to recognise patterns in
images or other supplied data via labels given to the examples. One it has enough
information to work on, it will be able to apply the labels to new cases.
Ben
Hamm has implemented an AI-based system for cat training
Comments
Post a Comment