We present Deep Generalized Canonical Correlation Analysis (DGCCA) -a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other. While methods for nonlinear twoview representation learning (Deep CCA, We present the DGCCA formulation as well as an efficient stochastic optimization algorithm for solving it. We learn and evaluate DGCCA representations for three downstream tasks: phonetic transcription from acoustic & articulatory measurements, recommending hashtags, and recommending friends on a dataset of Twitter users.