Timezone: »

Top-Down Regularization of Deep Belief Networks
Hanlin Goh · Nicolas Thome · Matthieu Cord · Joo-Hwee Lim

Fri Dec 06 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor

Designing a principled and effective algorithm for learning deep architectures is a challenging problem. The current approach involves two training phases: a fully unsupervised learning followed by a strongly discriminative optimization. We suggest a deep learning strategy that bridges the gap between the two phases, resulting in a three-phase learning procedure. We propose to implement the scheme using a method to regularize deep belief networks with top-down information. The network is constructed from building blocks of restricted Boltzmann machines learned by combining bottom-up and top-down sampled signals. A global optimization procedure that merges samples from a forward bottom-up pass and a top-down pass is used. Experiments on the MNIST dataset show improvements over the existing algorithms for deep belief networks. Object recognition results on the Caltech-101 dataset also yield competitive results.

Author Information

Hanlin Goh (-)
Nicolas Thome (Conservatoire national des arts et métiers (Cnam))
Matthieu Cord (Sorbonne University)
Joo-Hwee Lim (Institute for Infocomm Research, Singapore)

More from the Same Authors