Classify stuff with Machine Learning…
You’re starting a new venture firm MACHINES ARE SMART, that specializes in machine learning. You are going to pitch a new project to venture capital investors, and you need a proof of concept. Use teachable machine to build a model that does one of the following:
- An app that rejects drinks that aren’t coffee.
Reflect on the following question: You’ll have to think about how to train the machine. What kind of data did you include in your training dataset and why? What other kind of data could have been helpful but maybe you couldn’t get in the short-term/for free? Your group may, in some cases, search for photograph sets. One possibility to get large data sets is to convert YouTubes into clips. Did your model work well for what you wanted? In what instances might your model not work very well? Include the link to your project.
- The type of data we included was 25 pictures of coffee for sample one and 25 pictures of other drinks that are not coffee for sample two. This was to see if we imported a different picture that was not used in either of the samples and if it could tell the difference between coffee and non-coffee drinks. Probably more drinks that are not coffee could have been helpful to add to our sample. The model worked well for the most part but had a hard time knowing the difference between coffee and other brown drinks such as tea and hot chocolate. A chocolate shake came back as 88% not coffee which is interesting, I think this is because two other samples of shakes were included in the non-coffee sample.