The term "nonlinear transformations" is correct and usable in written English.
You can use it in a sentence to describe the process of changing a certain variable or mathematical equation. For example: "The nonlinear transformations of the equation helped to simplify it and make it more intuitive."
In the case of nonlinear transformations, the transformed model equations can be deduced following the same procedure.
Nonlinear transformations are applied to (i) transform the input space, (ii) transform the output space and (iii) transform both input and output spaces.
Since DNNs are powerful in transforming features through many layers of nonlinear transformations, it is common to splice the input features with a long context window to learn the temporal dynamic information automatically.
Neural networks construct a hierarchical representation where inputs are transformed into (potentially) nonlinear features that can undergo further nonlinear transformations.
PLSDA-softmax could overcome the class overlapping by nonlinear transformations.
Comparisons between model and measurements suggest possible mechanisms of spatial receptive-field organization and of nonlinear transformations.
Reducible diffusions (RDs) are nonlinear transformations of analytically solvable Basic Diffusions (BDs).
With only one of the TE of nonlinear transformations fluctuating around the TE of original series, the TE of others all have increased with different degrees.
This study is concerned with the enhancements of performance of associative memories by nonlinear transformations (mappings) of spaces of data to be associated.
The component non-Gaussian processes are obtained as nonlinear transformations of a vector of stationary, mutually correlated, Gaussian random processes and are thus, mutually dependent.
Belonging to the class of deep learning techniques, KDSNs are based on artificial neural network architectures that involve multiple nonlinear transformations of the input data.
