What is Machine Learning?
It’s a part of artificial intelligence that gives a machine the ability to access data and use it to learn on their own.
How does a machine learn?
There are many different forms of learning and areas for thought. But, in short, learning is achieved by supplying examples of data fed by humans. Then, a machine learning model is trained on this data, and that allows the machine to make decisions based on that.
Where do we get the dataset from?
We were inspired by Google’s Quick Draw dataset and planned on using the sketches made by people as our primary dataset, with found-images and COCO dataset being our secondary source.
We designed a three-part system consisting of the app client, the Machine Learning Model, and the Database. The client-side is imagined as a tablet/web app that takes Text, Voice, and Pen as the input. The ML Model then gathers this data for pre-processing. It is processed through different models and trained with several storyboarding assets such as images, scripts, sketches, etc. It is then deployed and tested on real data. For the Database, we plan on using the Sketch-RNN dataset, COCO Dataset, and voice recognition models.
