{"id":7458,"date":"2023-09-12T16:00:28","date_gmt":"2023-09-13T00:00:28","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=7458"},"modified":"2025-04-24T17:14:10","modified_gmt":"2025-04-24T17:14:10","slug":"human-in-the-loop-machine-learning","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/human-in-the-loop-machine-learning\/","title":{"rendered":"Human-in-the-Loop Machine Learning"},"content":{"rendered":"\n\n\n\n\n
\n
\n
\n
\n
\"\"<\/figure>
<\/picture><\/div>
Inca Knot Writing Quipu-Image Source<\/a><\/figcaption><\/figure>\n

Is it necessary for humans to take part in the machine learning cycle?<\/h2>\n

Contrary to what the movies we watch show us, today\u2019s artificial intelligence (AI) cannot do everything and learn everything on its own. It primarily, and to a large extent, needs the feedback it receives from people.<\/p>\n

I would guess that almost 80% of machine learning (ML) applications today consist of supervised learning models. However, applications cover a wide range of uses. For example, autonomous vehicles are trained with many data points such as \u2018pedestrian,\u2019<\/em> \u2018moving vehicle,\u2019<\/em> \u2018lane markings\u2019<\/em> so they can transport you safely. Your device understands you even when you command your home device to \u2018volume up\u2019<\/em> or say it in different languages to a machine translation app. ML models must be trained with maybe thousands of hours, millions of data, to reach this kind of performance.<\/p>\n

Annotation and active learning are the first step and cornerstones of the human-in-the-loop approach in AI\/ML.<\/p><\/blockquote>\n

Human-in-the-loop (HITL) is a cycle that allows people to develop ML approaches that make life easier. You need to know how to get training data from people and get human feedback on all your data. But when you don\u2019t have the budget or time for that, you must find different ways to determine the correct data.<\/p>\n

Transfer learning, one of these methods, ensures that we do not exceed a difficult point by adapting the existing ML models to our new task instead of starting from the beginning. Transfer learning has been popular for a while, so I won\u2019t go without mentioning it towards the end of the article. However, we will start with the issue of labeling, in which humans are included in the cycle.<\/p>\n

Before we get into the labeling\/annotation issue, let\u2019s look at the principles for humans to be in the ML cycle.<\/p>\n

\n
\n
\"\"<\/figure>
<\/picture><\/div>\n<\/div>\n
Human-in-the-loop ML benefits<\/a><\/figcaption>\n<\/figure>\n

Human-in-Loop Fundamentals for ML<\/h1>\n

When humans and ML interact to solve one or more of the following processes, what we call a HITL begins to happen:<\/p>\n