Doan Dong Nguyen doandongnguyen

doandongnguyen / stock_price_autoencoding.ipynb

Created April 25, 2019 14:49 — forked from GerardBCN/stock_price_autoencoding.ipynb

Stock market Bitcoin data compression with autoencoders

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

doandongnguyen / timeseries_cnn.py

Created March 19, 2019 00:56 — forked from jkleint/timeseries_cnn.py

Example of using Keras to implement a 1D convolutional neural network (CNN) for timeseries prediction.

	#!/usr/bin/env python
	"""
	Example of using Keras to implement a 1D convolutional neural network (CNN) for timeseries prediction.
	"""

	from __future__ import print_function, division

	import numpy as np
	from keras.layers import Convolution1D, Dense, MaxPooling1D, Flatten
	from keras.models import Sequential

doandongnguyen / universal_sentence_encoder_featurizer.py

Created March 5, 2019 11:14 — forked from georgwiese/universal_sentence_encoder_featurizer.py

Universal Sentence Encoder Featurizer

	from rasa_nlu.featurizers import Featurizer

	import tensorflow_hub as hub
	import tensorflow as tf


	class UniversalSentenceEncoderFeaturizer(Featurizer):
	"""Appends a universal sentence encoding to the message's text_features."""

	# URL of the TensorFlow Hub Module

doandongnguyen / dropout_bayesian_approximation_tensorflow.py

Created December 3, 2018 19:16 — forked from VikingPenguinYT/dropout_bayesian_approximation_tensorflow.py

Implementing Dropout as a Bayesian Approximation in TensorFlow

	import numpy as np
	import tensorflow as tf
	import matplotlib.pyplot as plt
	from tensorflow.contrib.distributions import Bernoulli


	class VariationalDense:
	"""Variational Dense Layer Class"""
	def __init__(self, n_in, n_out, model_prob, model_lam):
	self.model_prob = model_prob