I am currently trying to learn about deep learning. I asked myself where deep learning outperforms SVM and Random Forest on regression?

Do you have any dataset for regression where deep learning outperforms SVM and Random Forest?

My main objective for asking this question, is to see on which kind of datasets deep learning outperforms SVM and Random Forests. Since I do not know what kind of datasets these are, I do not want to be too restrictive when asking about these datasets.

Update: From the answer given by tom, it gets clear to me, what kind of dataset I am looking for. So to be more specific: If you know a dataset with spatial/temporal structure at different levels of granularity which is known that for example convolutional deep networks outperform SVM and Random Forest on this dataset, then please share this dataset or a link to it.

Don't know why the question is still marked as on hold for being to broad, as I updated the question.

Thank you for your help.


closed as too broad by oW_, Stephen Rauch, Sean Owen Nov 22 '17 at 23:51

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.


As a general rule, convolutional deep networks will perform better than SVM and Random Forest models on data that has hierarchical spatial/temporal structure, so for example sound, images, video. Deep networks are very good at learning this spatial/temporal structure at different levels of granularity. For classic datasets like Iris uses for teaching ML, however, I seriously doubt deep networks would perform better than SVM or Random Forest.


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