Chapter 21: Multitarget Learning
This chapter introduces multitarget learning techniques.
-
Chapter 21.01: Introduction
In this chapter we emphasize the practical relevance of multi-target prediction problems. In addition, we name some special cases of multi-target prediction and establish the differences between transductive and inductive learning problems.
-
Chapter 21.02: Loss functions
In this chapter we introduce loss functions for multi-target prediction problems, explain the differences between instance-wise and decomposable losses and introduce the risk minimizer for both the hamming and 0/1 subset losses.
-
Chapter 21.03: Methods for Multi-target Prediction 1
In this chapter we introduce the concepts of independent models for targets, mean regularization, stacking and weight sharing in DL.
-
Chapter 21.04: Methods for Multi-target Prediction 2
In this chapter we introduce the Kronecker kernel ridge regression, graph relations in targets, probabilistic classifier chains and low-rank approximations.