In this paper, the problem of determining the capacity of a communication channel is formulated as a cooperative game, between a generator and a discriminator, that is solved via deep learning techniques. The task of the generator is to produce channel input samples for which the discriminator ideally distinguishes conditional from unconditional channel output samples. The learning approach, referred to as cooperative channel capacity learning (CORTICAL), provides both the optimal input signal distribution and the channel capacity estimate. Numerical results demonstrate that the proposed framework learns the capacity-achieving input distribution under challenging non-Shannon settings.

翻译：本文将通信信道容量的确定问题建模为一个生成器与判别器之间的协作博弈，并通过深度学习技术求解。生成器的任务是生成信道输入样本，使得判别器能够理想地区分条件信道输出样本与无条件信道输出样本。这种学习方法被称为协作信道容量学习（CORTICAL），它既能提供最优输入信号分布，又能估计信道容量。数值结果表明，所提出的框架能够在具有挑战性的非香农设定下学习达到信道容量的输入分布。