Transfer Learning Types. When learning in one situation facilitates learning in another situation it is known as positive transfer. Transfer learning is not a machine learning model or technique.
In psychology when a skill learned in one task influences the learning of another task we call it to transfer of learning. On the basis of magnitude or quality it is of three types positive zero and negative. Image classification with a data availability constraint.
All knowledge acquired by models trained on one task will be applied to a new one but not all knowledge will be transferred beneficially and this difference is the source of negative and positive transfer.
When learning in one situation facilitates learning in another situation it is known as positive transfer. Proactive transfer a skill learnt in the past affects a skill currently being learnt or to be learnt in the future retroactive transfer learning a new skill affects a. In this view a dataset on which the machine was trained is different from the target dataset a. Types positive transfer negative transfer zero transfer lets understand them positive transfer of learning.