Quick, Draw!
In this experiment you are asked to draw given objects in a short time. While you draw, an algorithm tries to guess what you want to represent. Machine learning is used to compare your drawing with thousands of drawings to determine what should be represented.
How does "Quick, Draw!" work?
The game is based on a neural network - a machine learning model - that analyzes data and identifies patterns. The neural network was trained with thousands of drawings to make connections between lines, shapes and the respective terms.
Why is big data important?
The accuracy and efficiency of a machine learning model often depend on the quality and quantity of data used to train it. Large amounts of data allow the model to recognize multiple patterns and nuances. This is critical because in the real world, rarely are two data points exactly the same. Large data sets provide a wide variety of examples and variations, allowing the model to generalize better and respond more accurately to new, unknown data.
Is there such a thing as 'too much' data?
A common problem is overfitting. If a model is fitted "too well" to the training data, it may have difficulty coping with new, unknown data. It has then learned the specifics of the training data so precisely that it is no longer flexible enough to identify general patterns in new data.
Despite careful control of the content, we assume no liability for the content of external links. The operators of the linked pages are solely responsible for their content.