1 citations · 1 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020
Training Restricted Boltzmann Machines with Binary Synapses using the Bayesian Learning Rule
Xiangming Meng
Restricted Boltzmann machines (RBMs) with low-precision synapses are much appealing with high energy efficiency. However, training RBMs with binary synapses is challenging due to t…
cs.LG2020
Training Binary Neural Networks using the Bayesian Learning Rule
Xiangming Meng, Roman Bachmann, Mohammad Emtiyaz Khan
Neural networks with binary weights are computation-efficient and hardware-friendly, but their training is challenging because it involves a discrete optimization problem. Surprisi…