Deep Adversarial Belief Networks

no code implementations • 13 Sep 2019 • Yuming Huang, Ashkan Panahi, Hamid Krim, Yiyi Yu, Spencer L. Smith

We present a novel adversarial framework for training deep belief networks (DBNs), which includes replacing the generator network in the methodology of generative adversarial networks (GANs) with a DBN and developing a highly parallelizable numerical algorithm for training the resulting architecture in a stochastic manner.

Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximations

no code implementations • 7 Jun 2019 • Stephen L. Keeley, David M. Zoltowski, Yiyi Yu, Jacob L. Yates, Spencer L. Smith, Jonathan W. Pillow

We demonstrate that PAL estimators achieve fast and accurate extraction of latent structure from multi-neuron spike train data.

Variational Inference