paulhendricks

"""Genetic Algorithmn Implementation
see:
http://www.obitko.com/tutorials/genetic-algorithms/ga-basic-description.php
"""
import random

class GeneticAlgorithm(object):
    def __init__(self, genetics):
        self.genetics = genetics
        pass

paulhendricks

-- MarI/O by SethBling
-- Feel free to use this code, but please do not redistribute it.
-- Intended for use with the BizHawk emulator and Super Mario World or Super Mario Bros. ROM.
-- For SMW, make sure you have a save state named "DP1.state" at the beginning of a level,
-- and put a copy in both the Lua folder and the root directory of BizHawk.

if gameinfo.getromname() == "Super Mario World (USA)" then
	Filename = "DP1.state"
	ButtonNames = {
		"A",

paulhendricks

--
-- A simple genetic algorithm for function optimization, in lua
-- Copyright (c) 2009 Jason Brownlee
--
-- It uses a binary string representation, tournament selection, 
-- one-point crossover, and point mutations. The test problem is 
-- called one max (a string of all ones)
--

-- configuration

paulhendricks

## ------------------------------------------------------------------------
# Set the repo for use throughout
cran <- "https://cran.rstudio.org"

# Install
if(!require(miniCRAN)){ 
  install.packages("miniCRAN", repos = cran)
}

## ------------------------------------------------------------------------

paulhendricks

install.packages('caret')
install.packages('ccd')
install.packages('d3Network')
install.packages('data.table')
install.packages('dplyr')
install.packages('DMwR')
install.packages('e1071')
install.packages('ergm')
install.packages('ff')
install.packages('foreach')

paulhendricks

require(Mcomp)
nseries <- length(M3)

theta <- as.matrix(M3Forecast$THETA)
fpro <- as.matrix(M3Forecast$ForecastPro)
fcx <- as.matrix(M3Forecast$ForcX)
bjauto <- as.matrix(M3Forecast$`B-J auto`)
ab1 <- as.matrix(M3Forecast$AutoBox1)
ab2 <- as.matrix(M3Forecast$AutoBox2)
ab3 <- as.matrix(M3Forecast$AutoBox3)

paulhendricks

from random import randint

def create_population(create, pop_size=1000):
    """Create population list"""
    return [create() for i in xrange(pop_size)]

def crossover(combine, population, pop_size):
    """Increase population size by combining"""
    original_size = len(population)
    while len(population) < pop_size:

paulhendricks

paulhendricks

1. Feature Learning

• Learning Feature Representations with K-means by Adam Coates and Andrew Y. Ng
• The devil is in the details: an evaluation of recent feature encoding methods by Chatfield et. al.
• Emergence of Object-Selective Features in Unsupervised Feature Learning by Coates, Ng
• Scaling Learning Algorithms towards AI Benjio & LeCun
• A Theory of Feature Learning by Brendan van Rooyen, Robert C. Williamson

2. Deep Learning

• Dropout: A Simple Way to Prevent Neural Networks from Overfitting by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov
• [Understanding

paulhendricks

innovationScore,innovationScore2,names,type,description
4.7,470,3L Labs Footlogger,medical,"The 3L Labs Footlogger is a wearable fitness tracking device that aims at spotting health problems early, as well as logging daily activity. Placed in the user's shoe, 8 sensors coupled to 1 accelerometer help identify and record exercise habits. The data is then disclosed to the user via text or smartphone app. This computing device's technology can be used for athletes training, regular everyday workouts and rehabilitation."
5.44,544,4D Force,,"The 4D Force is a wearable technology that detects brain waves and converts them into electric signals. 4D Force developed a platform that can capture and compute high quality EEG/ EOG/EMG signals. With the device, users can control games by using the power of their thoughts. 4D Force can also be used for medical purposes as it has the ability to interpret electrical signals generated by the body, and create recommendations for changes in lifestyle."
4,400,4iiii Viiiiva,Fitnes