mohammedgomaa’s gists

mohammedgomaa / catboost_playground.ipynb

Created November 13, 2018 20:51 — forked from talperetz/catboost_playground.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

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

mohammedgomaa / bayesian_neural_network.ipynb

Created November 8, 2018 11:37 — forked from anonymous/bayesian_neural_network.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

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

mohammedgomaa / nes.py

Created October 11, 2018 18:52 — forked from karpathy/nes.py

Natural Evolution Strategies (NES) toy example that optimizes a quadratic function

	"""
	A bare bones examples of optimizing a black-box function (f) using
	Natural Evolution Strategies (NES), where the parameter distribution is a
	gaussian of fixed standard deviation.
	"""

	import numpy as np
	np.random.seed(0)

	# the function we want to optimize

mohammedgomaa / keras_es.py

Created October 11, 2018 18:46 — forked from nicksam112/keras_es.py

Evolution Strategies with Keras


	#Evolution Strategies with Keras
	#Based off of: https://blog.openai.com/evolution-strategies/
	#Implementation by: Nicholas Samoray

	#README
	#Meant to be run on a single machine
	#APPLY_BIAS is currently not working, keep to False
	#Solves Cartpole as-is in about 50 episodes
	#Solves BipedalWalker-v2 in about 1000

mohammedgomaa / keras_es.py

Created October 11, 2018 18:46 — forked from MaxwellRebo/keras_es.py

Evolution Strategies with Keras


	#Evolution Strategies with Keras
	#Based off of: https://blog.openai.com/evolution-strategies/
	#Implementation by: Nicholas Samoray

	#README
	#Meant to be run on a single machine
	#APPLY_BIAS is currently not working, keep to False
	#Solves Cartpole as-is in about 50 episodes
	#Solves BipedalWalker-v2 in about 1000

mohammedgomaa / timeseries_cnn.py

Created February 20, 2018 04:30 — 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