Problem-Based Learning in the Construction Field

Problem-based learning Problem-based learning is a student-centered learning approach (Evans, 2006). This kind of learning attempts to expose students to situations unfamiliar to their students (Learning-Theories, 2013). Teachers take more counselor 's approach. It is basically aimed at teaching students, helping to keep on track, and suggesting materials that students can help solve problems. Simplifying this approach is to help students learn by experiencing problems and solving problems.

Machine learning is a field of computer science including research and construction technology that enables computers to self-learn based on input data to solve specific problems. Based on learning methods, machine learning techniques generally fall into three categories. Supervised learning, unsupervised learning, and semi supervised learning. Supervised learning is a form of learning where training data is marked. The machine "learns" from the marked pattern, constructs the classifier, and uses it to predict the label of the new data. By contrast, unsupervised learning is a type of learning where training data is not marked. In this format, the machine "learns" by analyzing the characteristics of the data and constructing a classifier. Semi supervised learning is a hybrid approach of supervised learning and unsupervised learning. In semi supervised learning, the input training data set contains both tagged and unlabeled data.

In the field of machine learning, there are mainly two types of tasks. It is supervised and unsupervised. The main difference between these two types is that supervised learning is done using the underlying facts, that is, we know in advance how the output value of the sample should be. Therefore, the purpose of supervised learning is to learn functions that best approximate the relationship between a given given data sample and the observable inputs and outputs at the expected output. On the other hand, unsupervised learning has no markup output, so its goal is to infer the natural structure that exists in the set of data points.

Machine learning (ML) is a field of artificial intelligence aimed at building and researching a system that can be learned from data. Learning under these circumstances means that you can identify complex patterns and make appropriate decisions based on previously viewed data. The main challenge of machine learning is how to provide a summary of knowledge gained from limited past experience to make useful decisions for new events that were not previously seen. In order to solve this problem, the machine learning field has developed a series of algorithms to discover knowledge from specific data and experience based on sound statistical and computational principles. Machine learning is based on concepts and results in various fields such as statistics, artificial intelligence, information theory, philosophy, cognitive science, control theory, biology etc.