Generative Adversarial Networks (GANs) for Design Concept Generation
This work describes how automated data generation integrates in a big data pipeline. A lack of veracity in big data can result in models that are inaccurate, or biased by trends in the training data. This can lead to computational issues that are difficult to overcome as a big data pipeline matures. This work describes the use of a Generative Adversarial Network to generate human-readable image data (i.e., sketch data), such as those that might be used in a human verification task. These generated sketches are verified as recognizable using a crowdsourcing approach, and finds that the generated sketches were correctly recognized 43.8% of the time, in contrast to human drawn sketches which were 87.7% accurate. This method is scalable and can be used to generate realistic data in many domains and bootstrap a dataset used for training a big data model prior to deployment.
This work describes how automated data generation integrates in a big data pipeline. A lack of veracity in big data can result in models that are inaccurate, or biased by trends in the training data. This can lead to computational issues that are difficult to overcome as a big data pipeline matures. This work describes the use of a Generative Adversarial Network to generate human-readable image data (i.e., sketch data), such as those that might be used in a human verification task. These generated sketches are verified as recognizable using a crowdsourcing approach, and finds that the generated sketches were correctly recognized 43.8% of the time, in contrast to human drawn sketches which were 87.7% accurate. This method is scalable and can be used to generate realistic data in many domains and bootstrap a dataset used for training a big data model prior to deployment.
