The effect of Leaky ReLUs on the training and generalization of overparameterized networks

no code implementations • 19 Feb 2024 • Yinglong Guo, Shaohan Li, Gilad Lerman

We investigate the training and generalization errors of overparameterized neural networks (NNs) with a wide class of leaky rectified linear unit (ReLU) functions.

An Unpooling Layer for Graph Generation

1 code implementation • 4 Jun 2022 • Yinglong Guo, Dongmian Zou, Gilad Lerman

Since this unpooling layer is trainable, it can be applied to graph generation either in the decoder of a variational autoencoder or in the generator of a generative adversarial network (GAN).

Generative Adversarial Network Graph Generation

Gene set proximity analysis: expanding gene set enrichment analysis through learned geometric embeddings

1 code implementation • 31 Jan 2022 • Henry Cousins, Taryn Hall, Yinglong Guo, Luke Tso, Kathy Tzy-Hwa Tzeng, Le Cong, Russ Altman

Gene set analysis methods rely on knowledge-based representations of genetic interactions in the form of both gene set collections and protein-protein interaction (PPI) networks.