Re:A Beginner’s Guide to Restricted Boltzmann Machines
by teraflop on Thursday August 06, 2015 @05:30PM
(#10019590)
You can think of deep learning as a way to automate feature extraction on very high-dimensional data, where the features are complex enough that they're difficult or impossible to specify by hand. This includes things like:
- objects in an image/video
- phonemes in raw audio
- events in multidimensional time series
- grammatical/semantic structures in unstructured text
- strategic features in a board game position (e.g. Go)
These kinds of inputs are difficult to handle with traditional ML techniques. But if your data already looks more like rows in a table, with simple, semantically meaningful features, deep learning isn't likely to buy you that much.
- objects in an image/video
- phonemes in raw audio
- events in multidimensional time series
- grammatical/semantic structures in unstructured text
- strategic features in a board game position (e.g. Go)
These kinds of inputs are difficult to handle with traditional ML techniques. But if your data already looks more like rows in a table, with simple, semantically meaningful features, deep learning isn't likely to buy you that much.