This summarizes an academic paper that proposes a new adaptive beamforming technique using neural networks trained by a novel optimization method called Mutated Boolean PSO (MBPSO). The technique aims to steer antenna array main lobes toward desired signals, place nulls toward interference signals, and achieve low side lobe levels. The MBPSO is applied to training cases to estimate antenna excitation weights, which are then used to train a neural network. The trained neural network can then be applied to new cases to generate radiation patterns, which are shown to have advantages over patterns from MBPSO and MVDR beamforming techniques.