Scalable GP Adapter for Time Series Classification

Requirements

Python 2.7
Numpy
Scipy
Theano
Lasagne
Cython: run the command python setup.py build_ext --inplace to compile Cython modules.

Train GP adapter with a convolutional net for 100 epochs on the sparsified uWave data:

python gpnet_fast.py -f data/UWaveGestureLibraryAll-1.pkl -e 100 -n cnn

Run python gpnet_fast.py -h to learn the command line options.

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
data		data
LICENSE		LICENSE
README.md		README.md
blcgrq.py		blcgrq.py
cmp_fast_gp.py		cmp_fast_gp.py
cmp_lanczos.py		cmp_lanczos.py
cmp_np_post_gp.py		cmp_np_post_gp.py
cmp_theano_post_gp.py		cmp_theano_post_gp.py
cov_vec_bprop.py		cov_vec_bprop.py
exact_posterior_gp.py		exact_posterior_gp.py
fast_gp.py		fast_gp.py
fast_gp_block.py		fast_gp_block.py
gp_kernel.py		gp_kernel.py
gpnet_exact.py		gpnet_exact.py
gpnet_fast.py		gpnet_fast.py
lanczos_sqrtm.py		lanczos_sqrtm.py
logdet.py		logdet.py
logger.py		logger.py
meg_kernel_exact.py		meg_kernel_exact.py
meg_kernel_gpa.py		meg_kernel_gpa.py
native_interp_to_u.pyx		native_interp_to_u.pyx
np_posterior_gp.py		np_posterior_gp.py
pickle_io.py		pickle_io.py
posterior_gp.py		posterior_gp.py
sample_gp.py		sample_gp.py
setup.py		setup.py
theano_sqrtm.py		theano_sqrtm.py
train_gp_marlik.py		train_gp_marlik.py