666
edits
(Shortened blog URL to https://mzl.la/smartkitchen) |
(taking out experiment details) |
||
| Line 57: | Line 57: | ||
* We are assuming that we can use image recognition to accurately identify some percentage of the contents of the kitchen | * We are assuming that we can use image recognition to accurately identify some percentage of the contents of the kitchen | ||
* We assume that people want recipes that they can make with their existing kitchen inventory | * We assume that people want recipes that they can make with their existing kitchen inventory | ||
=== Experiments === | <!--- === Experiments === | ||
* We believe that if we give a user an experiment device for identifying their inventory that we will be able to recognize 20% of items with our existing training to date. | * We believe that if we give a user an experiment device for identifying their inventory that we will be able to recognize 20% of items with our existing training to date. | ||
* If run a Facebook Ad describing our product, we expect a 2% response rate | * If run a Facebook Ad describing our product, we expect a 2% response rate | ||
* If we create a video that shows our product vision and advertise it, we expect a 2% response rate. | * If we create a video that shows our product vision and advertise it, we expect a 2% response rate. | ||
=== Experiment Details === | === Experiment Details === | ||
* Details on all experiments can be found [https://docs.google.com/spreadsheets/d/1DRdd8jV6d8WO9nrIg0O4-HEXb0txh19rDcTup3N7aRY/edit#gid=1110301338 here] | * Details on all experiments can be found [https://docs.google.com/spreadsheets/d/1DRdd8jV6d8WO9nrIg0O4-HEXb0txh19rDcTup3N7aRY/edit#gid=1110301338 here] ---> | ||
edits