Can anyone explain me how incremental learning differs from transfer learning with example? Also does Transfer learning limited to neural networks?
Transfer Learning: for example you want to predict price of article normally we use previous data based on that we design model .while new data came still we use that model for prediction here we are transferring the same model for new task or in general When you learn how to drive a car, you learn a generic skill and you will use these similar set of skills if you want to drive a truck. This transfer of your knowledge is called transfer learning.
continuous learning:for example In face recognition or image classification system, first we train our model with some data,if new person is came our model can't recognize the person in this case we train our model only with new data and attached that weight into our model. in general If you have learnt any new skills while driving a truck, you will continuously update your knowledge and use that for improving your driving skill. This is called incremental learning (or) continuous learning (or) online learning.