1 code implementation • NeurIPS 2019 • Ganlin Song, Zhou Fan, John Lafferty
When initialized with random parameters $\theta_0$, we show that the objective $f_{\theta_0}(x)$ is "nice'' and easy to optimize with gradient descent.
no code implementations • NeurIPS 2021 • Ganlin Song, Ruitu Xu, John Lafferty
In this paper we study the mathematical properties of the feedback alignment procedure by analyzing convergence and alignment for two-layer networks under squared error loss.
no code implementations • 26 May 2022 • Leon Lufkin, Ashish Puri, Ganlin Song, Xinyi Zhong, John Lafferty
Local patterns of excitation and inhibition that can generate neural waves are studied as a computational mechanism underlying the organization of neuronal tunings.
