activity
20172025
most citedHardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks

2 citations · 4 across the 6 of their papers we have counts for

collaborators

6 papers

math.ST2025

Self-Normalized Concentration Inequalities of Marginal Mean with Sample Variance Only

Zihao Yuan

(This is the third version of a working paper.) We develop a family of self-normalized concentration inequalities for marginal mean under martingale-difference structure and $ϕ/\ti…

math.ST2022

Exponential Inequalities for Some Mixing Processes and Dynamic Systems

Zihao Yuan, Holger Dette

Many important dynamic systems, time series models or even algorithms exhibit non-strong mixing properties. In this paper, we introduce the general concept of $\mathcal{C}_{p,\math…

math.ST2022★ 1 cited

Bernstein-type Inequalities and Nonparametric Estimation under Near-Epoch Dependence

Zihao Yuan, Martin Spindler

The major contributions of this paper lie in two aspects. Firstly, we focus on deriving Bernstein-type inequalities for both geometric and algebraic irregularly-spaced NED random f…

econ.EM2018★ 1 cited

An Note on Why Geographically Weighted Regression Overcomes Multidimensional-Kernel-Based Varying-Coefficient Model

Zihao Yuan

It is widely known that geographically weighted regression(GWR) is essentially same as varying-coefficient model. In the former research about varying-coefficient model, scholars t…

econ.EM2018

A Nonparametric Approach to Measure the Heterogeneous Spatial Association: Under Spatial Temporal Data

Zihao Yuan

Spatial association and heterogeneity are two critical areas in the research about spatial analysis, geography, statistics and so on. Though large amounts of outstanding methods ha…

cs.CV2017★ 2 cited

Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks

Ji Li, Zihao Yuan, Zhe Li +5

Recently, Deep Convolutional Neural Networks (DCNNs) have made unprecedented progress, achieving the accuracy close to, or even better than human-level perception in various tasks.…