Non-Gaussian Information from weak lensing data via deep learning

Weak leasing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the leasing field. Here we train and apply a two-dimensional convolutional neural network to simulated noiseless leasing maps covering 96 different cosmological models over a range of {Omega(m), sigma(8)}. Using the area of the confidence contour in the {Omega(m), sigma(8)} plane as a figure of merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields approximate to 5x tighter constraints than the power spectrum, and approximate to 4x tighter than the leasing peaks. Such gains illustrate the extent to which weak leasing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as leasing peaks.