This paper presents methods and examples of analysis of plant measurements using the new neural network architecture of Input-Training Networks (IT-nets). These networks are a non-linear alternative to the linear technique of Principal Component Analysis (PCA) or Singular Value Decomposition (SVD). Starting from a large set of original variables (plant measurements), an IT-net is trained to determine a smaller set of latent variables and a (neural-network based) model for reproducing the original variables from the latent ones. IT-nets achieve this task through input training, in which each input pattern (containing values of the latent variables) is not fixed but adjusted along with internal network parameters to reproduce its corresponding output pattern (the values of the original variables). Once trained, the network can be used to determine the latent variables (as trained inputs) for any new pattern of measured variables. This type of dimensionality reduction with IT-nets is useful in a variety of plant-measurement analysis tasks. Here, we demonstrate IT-nets in comparison to PCA for reduction of data dimensionality and replacement of missing measurements and gross error detection. The representation of the process measurements in the lower-dimensional form of latent variables can be a prelude to other process engineering activities relying on process measurements.