Photo from wikipedia
In this paper, based on Wirtinger calculus, we introduce a quasi-Newton method for training complex-valued neural networks with analytic activation functions. Using the duality between Wirtinger calculus and multivariate real… Click to show full abstract
In this paper, based on Wirtinger calculus, we introduce a quasi-Newton method for training complex-valued neural networks with analytic activation functions. Using the duality between Wirtinger calculus and multivariate real calculus, we prove a convergence theorem of the proposed method for the minimization of real-valued complex functions. This lays the theoretical foundation for the complex quasi-Newton method and generalizes Powell’s well-known result for the real-valued case. The simulation results are given to show the effectiveness of the method.
Journal Title: Neural Processing Letters
Year Published: 2017
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!