redwrasse

package main

import (
	"fmt"
	"strings"
	"crypto/sha1"
	"encoding/base64"
)

type Document struct {

redwrasse

abstract class NeuralNetwork {


  val numImmediateInputs: Int
  var children: Map[Int, NeuralNetwork] 


  /**
   * The integration function contains implicitly the weights
   * for this compute unit

redwrasse

package main



import (
	"math"
	"fmt"
)

redwrasse

class McCullochPitts(
  val numExcitatoryInputs: Int,
  val numInhibitoryInputs: Int,
  val threshold: Int,
  val inhibitoryInputIndices: Option[Seq[Int]] = None)
    extends NeuralNetwork {

  val numImmediateInputs: Int = (numExcitatoryInputs
    + numInhibitoryInputs)
  var children: Map[Int, NeuralNetwork] = Map.empty

redwrasse

/**
  * Maximum value algorithm: at each iteration each
  * node sends to its neighbors the largest value it 
  * has ever seen.
  */

package graphalgorithms


import org.apache.spark.graphx._

redwrasse

# svdtext.py
"""
   Singular value decomposition and 
   plotting on text 
"""
import numpy as np
import matplotlib.pyplot as plt

def svdtext(filename):
    neighbors = {}

redwrasse

from multiprocessing.dummy import Pool 
from urllib import urlretrieve, urlopen
from bs4 import BeautifulSoup
import os
from datetime import datetime

startDate = datetime.strptime('01.01.1996', '%d.%m.%Y')
endDate = datetime.strptime('01.01.2018', '%d.%m.%Y')

redwrasse

def kernel_perceptron():

    import numpy as np
    import tensorflow as tf

    c1 = np.random.randn(50, 75) + 1
    c2 = np.random.randn(50, 75) - 1
    X = np.vstack([c1, c2])
    Y = np.concatenate([np.ones((50, 1)), 1 - np.zeros((50, 1))])
    alpha = tf.Variable(tf.random_normal((100, 1)),

redwrasse

def dual_perceptron():

    import numpy as np
    import tensorflow as tf

    c1 = np.random.randn(50, 75) + 1
    c2 = np.random.randn(50, 75) - 1
    X = np.vstack([c1, c2])
    Y = np.concatenate([np.ones((50, 1)), 1 - np.zeros((50, 1))])

redwrasse

def margin_perceptron():

    import numpy as np
    import tensorflow as tf

    c1 = np.random.randn(50, 100) + 1
    c2 = np.random.randn(50, 100) - 1
    X = np.vstack([c1, c2])