Figure 1:

The framework of Deep IDA. Classes are represented by shapes and views are represented by colors. The deep neural networks (DNN) are used to learn nonlinear transformations of the D views, the outputs of the DNN for the views (f^d) are used as inputs in the optimization problem, and we learn linear projections A_d, d = 1, …, D that maximally correlate the nonlinearly transformed views and separate the classes within each view.