Detecting Synchrony Among Multiple Neurons

These are the codes for a recent paper on detecting multiway synchrony among neurons: MultiWaySynchrony.zip

Split Hamiltonian Monte Carlo (Split HMC)

We have recently proposed a new approach to improve the Hamiltonian Monte Carlo (HMC) algorithm. Our approach is based on``splitting'' the Hamiltonian such that much of the movement around the state space is performed at low computational cost. Here are the corresponding R programs and data sets: SplitHMC.zip.

NONLINEAR MODELS USING DIRICHLET PROCESS MIXTURES

We introduced a new nonlinear method based on modeling the joint distribution of response and covariates using the Dirichlet process mixtures of linear models.

These are the computer programs we used for simulations studies: dpmSim1.m and dpmSim2.m.

These two files are demos for nonlinear regression and nonlinear classification: dpRegDemo.m and dpMNLDemo.m.

HIERARCHICAL CLASSIFICATION

These are some files related to my work on classification models when classes have a hierarchical structure.

MNL.m: This is a simple Bayesian multinomial model (i.e., taking classes as unrelated entities)

treeMNL.m: This models hierarchical classes using nested multinomial logit models.

corMNL.m: This is our proposed method that takes the hierarchy as a prior.

makeTree.m: This code gets a matrix of classes and returns a tree structure.

predictedFunction.dat: This is the list of our predictions for Ecoli’s ORFs with unknown function.

predictedWithDescription.pdf: These are some of the predicted classes with descriptions.