Consider a dataset with 5 numerical features: A, B, C, D and E. Can we train a deep learning/machine learning model which can learn constraints between (A,B) and (C,D,E) i.e I want to learn a function f, such that A,B = f(C,D,E) using the data samples in the data set.

  • 1
    $\begingroup$ Well, that's the purpose of supervised learning, isn't it? $\endgroup$
    – noe
    May 18, 2023 at 10:37

1 Answer 1


Yes, it is possible to train a deep learning/machine learning model to learn the relationship between (A, B) and (C, D, E). One approach could be to use a neural network architecture, such as a multi-layer perceptron (MLP) or a convolutional neural network (CNN), to learn the mapping between the input variables (C, D, E) and the output variables (A, B).

The training process involves feeding the model with labeled data samples and adjusting the model's parameters to minimize the difference between the predicted outputs and the true outputs. This process is commonly referred to as optimization or training.

It's worth noting that the success of the model depends on the quality and quantity of the training data and the chosen architecture and hyperparameters of the model.

I hope this answer helps!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.