Xiangming Meng

activity

20152026

most citedUnitary Approximate Message Passing for Sparse Bayesian Learning

82 citations · 246 across the 24 of their papers we have counts for

collaborators

Showing 2020Show all

3 papers · 1 filter

cond-mat.dis-nn2020★ 1 cited

Structure Learning in Inverse Ising Problems Using $ℓ_{2}$ -Regularized Linear Estimator

Xiangming Meng, Tomoyuki Obuchi, Yoshiyuki Kabashima

The inference performance of the pseudolikelihood method is discussed in the framework of the inverse Ising problem when the $ℓ_{2}$ -regularized (ridge) linear regression is adopt…

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★ 16 cited

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…

Structure Learning in Inverse Ising Problems Using ℓ2​-Regularized Linear Estimator

Training Restricted Boltzmann Machines with Binary Synapses using the Bayesian Learning Rule

Training Binary Neural Networks using the Bayesian Learning Rule

Structure Learning in Inverse Ising Problems Using $ℓ_{2}$ -Regularized Linear Estimator