{"id":6424,"date":"2023-06-08T22:00:00","date_gmt":"2023-06-08T22:00:00","guid":{"rendered":"https:\/\/modernsciences.org\/staging\/4414\/?p=6424"},"modified":"2023-05-28T16:22:53","modified_gmt":"2023-05-28T16:22:53","slug":"what-is-a-black-box-a-computer-scientist-explains-what-it-means-when-the-inner-workings-of-ais-are-hidden","status":"publish","type":"post","link":"https:\/\/modernsciences.org\/staging\/4414\/what-is-a-black-box-a-computer-scientist-explains-what-it-means-when-the-inner-workings-of-ais-are-hidden\/","title":{"rendered":"What is a black box? A computer scientist explains what it means when the inner workings of AIs are hidden"},"content":{"rendered":"\n
\n \n
\n You can\u2019t see inside any opaque box, but the color black adds an air of mystery.\n chingraph\/iStock via Getty Images<\/a><\/span>\n <\/figcaption>\n <\/figure>\n\nSaurabh Bagchi<\/a>, Purdue University<\/a><\/em><\/span>\n\n

For some people, the term \u201cblack box\u201d brings to mind the recording devices in airplanes that are valuable for postmortem analyses if the unthinkable happens. For others it evokes small, minimally outfitted theaters. But black box is also an important term in the world of artificial intelligence. <\/p>\n\n

AI black boxes<\/a> refer to AI systems with internal workings that are invisible to the user. You can feed them input and get output, but you cannot examine the system\u2019s code or the logic that produced the output. <\/p>\n\n

Machine learning is the dominant subset of artificial intelligence. It underlies generative AI systems like ChatGPT<\/a> and DALL-E 2<\/a>. There are three components to machine learning: an algorithm or a set of algorithms, training data and a model. An algorithm is a set of procedures. In machine learning, an algorithm learns to identify patterns after being trained on a large set of examples \u2013 the training data. Once a machine-learning algorithm has been trained, the result is a machine-learning model. The model is what people use. <\/p>\n\n

For example, a machine-learning algorithm could be designed to identify patterns in images, and training data could be images of dogs. The resulting machine-learning model would be a dog spotter. You would feed it an image as input and get as output whether and where in the image a set of pixels represents a dog.<\/p>\n\n

Any of the three components of a machine-learning system can be hidden, or in a black box. As is often the case, the algorithm is publicly known, which makes putting it in a black box less effective. So to protect their intellectual property, AI developers often put the model in a black box. Another approach software developers take is to obscure the data used to train the model \u2013 in other words, put the training data in a black box.<\/p>\n\n

\n