Machine learning uses various terms to describe its components:
- Labels: These are the target variables that the model should predict. Example: Construction cost (e.g., in dollars), duration of construction work (e.g., in months).
- Features: These are independent variables that serve as inputs to the model. In a prediction model, they are used to predict labels. Examples: Site area (in square meters), number of floors of a building, total building area (in square meters), geographic location (latitude and longitude), type of materials used in construction. The number of characteristics also determines the dimensionality of the data.
- Model: This is a collection of different hypotheses, one of which approximates the target function to be predicted or approximated. Example: A machine learning model that uses regression analysis techniques to predict the cost and timing of construction.
- Learning Algorithm: This is the process of finding the best-fitting hypothesis in a model that accurately fits the target function using a training data set. Example: A linear regression, KNN or random forest algorithm that analyzes cost and construction time data to identify relationships and patterns.
- Training: During machine learning training, the algorithm analyzes the training data, finding patterns that correspond to the relationship between input attributes and target labels. The result of this process is a trained machine learning model that is ready for prediction. Example: A process in which an algorithm analyzes historical construction data (cost, time, facility characteristics) to create a predictive model.
Machine learning involves the use of labels (target variables) and features (input data) to create models that are trained on the data through algorithms to predict outcomes.
The primary human goal in machine learning is to endow computers with the ability to learn knowledge automatically without human intervention or assistance and adjust their actions accordingly.
Thus, in the future, the human's role will only be to provide the machine with cognitive capabilities - where they will set the conditions, weights and parameters , and the machine learning model does the rest.
