kastnerkyle

# Alec Radford, Indico, Kyle Kastner
# License: MIT
"""
Convolutional VAE in a single file.
Bringing in code from IndicoDataSolutions and Alec Radford (NewMu)
Additionally converted to use default conv2d interface instead of explicit cuDNN
"""
import theano
import theano.tensor as T
from theano.compat.python2x import OrderedDict

kastnerkyle

# Authors: Kyle Kastner
# License: BSD 3-clause
import theano.tensor as T
import numpy as np
import theano


class rmsprop(object):
    """
    RMSProp with nesterov momentum and gradient rescaling

macks22

"""
Implementations of:

    Probabilistic Matrix Factorization (PMF) [1],
    Bayesian PMF (BPMF) [2],
    Modified BPFM (mBPMF)

using `pymc3`. mBPMF is, to my knowledge, my own creation. It is an attempt
to circumvent the limitations of `pymc3` w/regards to the Wishart distribution:

Andy-P

# This code is part of a presentation on streaming analytics in Julia
# It was inspired by a number of individuals and makes use of some of their ideas
#     1. FastML.com got me thinking about inline processing after 
#        reading his great Vowpal Wabbit posts
#     2. John Lanford and his fantastic Vowpal Wabbit library. 
#        Check out his NYU video course to learn more (see below)
#     3. John Myles White's presentation on online SDG and his StreamStats.jl library 
# Thank you all!

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

smly

"""
An example to check the AUC score on a validation set for each 10 epochs.
I hope it will be helpful for optimizing number of epochs.
"""
# -*- coding: utf-8 -*-
import logging

from sklearn.metrics import roc_auc_score
from keras.callbacks import Callback

vene

""" Poisson-loss Factorization Machines with Numba

Follows the vanilla FM model from:
Steffen Rendle (2012): Factorization Machines with libFM.
In: ACM Trans. Intell. Syst. Technol., 3(3), May.
http://doi.acm.org/10.1145/2168752.2168771

See also: https://github.com/coreylynch/pyFM
"""

shamatar

from keras.layers import Recurrent
import keras.backend as K
from keras import activations
from keras import initializers
from keras import regularizers
from keras import constraints
from keras.engine import Layer
from keras.engine import InputSpec

eamartin

neubig

"""
DyNet implementation of a sequence labeler (POS taggger).
This is a translation of this tagger in PyTorch: https://gist.github.com/hal3/8c170c4400576eb8d0a8bd94ab231232

Basic architecture:
 - take words
 - run though bidirectional GRU
 - predict labels one word at a time (left to right), using a recurrent neural network "decoder"
The decoder updates hidden state based on:
 - most recent word