Deep learning models are representative of what is also known as inductive learning. The objective for inductive-learning algorithms is to infer a mapping from a set of training examples. For instance, in cases of classification, the model learns mapping between input features and class labels. In order for such a learner to generalize well on unseen data, its algorithm works with a set of assumptions related to the distribution of the training data. These sets of assumptions are known as inductive bias.

The inductive bias or assumptions can be characterized by multiple factors, such as the hypothesis space it restricts to and the search process through the hypothesis space. Thus, these biases impact how and what is learned by the model on the given task and domain.

Inductive transfer techniques utilize the inductive biases of the source task to assist the target task. This can be done in different ways, such as by adjusting the inductive bias of the target task by limiting the model space, narrowing down the hypothesis space, or making adjustments to the search process itself with the help of knowledge from the source task. This process is depicted visually in the following diagram:

Apart from inductive transfer, inductive-learning algorithms also utilize Bayesian and hierarchical transfer techniques to assist with improvements in the learning and performance of the target task.