Given a set of objects , this ML engine “imagines” never seen before objects , each with several different and several similar characteristics.
To explain this in non-technical terms, imagine a website developer that needs to add images of people to a site: but not real people so as to avoid any type of claim. So, an AI model is provided with a man’s picture and the expected output is a picture of an imaginary person who looks similar but is much taller. If the AI Model has learned the ‘height’ dimension independently, then this can be adjusted accordingly to get a picture of a similar-looking but taller person.
Similarly, Microsoft and IBM’s face-analysis services performed near perfectly when identifying pictures of white males but not as good when analyzing images of black women, reflecting a bias in the training picture set. The result is a game called “Speedgate”, imagined and created by the AI. It mixes soccer, rugby, and frisbees in a new game that was never thought of or played before. More on this in thisWith Speedgate, two opposing teams of six players pass, kick, and/or throw a ball through 3 gates at either end of a field, but excluding the middle one .
대한민국 최근 뉴스, 대한민국 헤드 라인
Similar News:다른 뉴스 소스에서 수집한 이와 유사한 뉴스 기사를 읽을 수도 있습니다.
출처: hackernoon - 🏆 532. / 51 더 많은 것을 읽으십시오 »