dean-shaff

import sympy as sym 

x1, x2 = sym.symbols("x1 x2")
coord = [x1, x2]
g = sym.Matrix([[1,0],[0,x1**2]])
ginv = g.inv()

def christoffel(coord, g, ginv, index1, index2, index3):
	"""
	coord is the list of coordinates, eg coord = [r, theta, phi] 

dean-shaff

def feed_forward(self,x):
	"""
	Calculate the value(s) of the neural net at the output level.
	"""
	y_guess = self.act(T.dot(x,self.W[0])+ self.b[0])
	for i in xrange(1,len(self.W)):
		W = self.W[i]
		b = self.b[i]
		if i == len(self.W)-1:
			y_guess = T.nnet.softmax(T.dot(y_guess,W)+b)

dean-shaff

void loop() {
  randNumber1 = random(0,100);
  randNumber2 = random(0,100);
  int bigger;
  if (randNumber1 > randNumber2){
    bigger = 1;
  }else{
    bigger = 0;
  }
  while (digitalRead(pin_in1) == HIGH){

dean-shaff

"""
Took the main functionality of this code from https://www.lebsanft.org/?p=48 
"""
import serial
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt 
import numpy as np 
import time
import sys

dean-shaff

/*
Random Squares, originally by Bill Kolomyjec
*/

int max_sqrs = 9 ; 
int large_sqr_dim = 7;
int sqr_dim ; //= width / 7 ; 
int init_sqr_dim ; // = sqr_dim / 5 ;
boolean zero_sqr = false;

dean-shaff

-- building the MLP 
net = nn.Sequential() 
net:add(nn.Linear(150,400))
net:add(nn.Linear(400,300))
net:add(nn.Linear(300,200))
net:add(nn.Tanh()) -- tanh squashing function 
net:add(nn.Linear(200,2))
net:add(nn.LogSoftMax())

-- Training the net 

dean-shaff

from PyQt4 import QtCore, QtGui
from mainui import MainUI
import time 
from hardware_controller import Hardware_Controller

class Worker(QtCore.QThread):

    update_text_signal = QtCore.pyqtSignal(str) #have to pass the type str
    
    def __init__(self, hdwr_ctrl, update_rate):

dean-shaff

function Array2D(...)
	
	local args = {...}
	if #args == 0 then 
		args = {{{}}}
	end
	local array2d = {
		__index = self,
		vals = args[1],
		shape = {#args[1], #args[1][1]},

dean-shaff

import theano 
import theano.tensor as T 
import numpy as np 
import h5py 
import os 
import time


def rungekuttastep(h,y,fprime,*args):
    k1 = h*fprime(y,*args)

dean-shaff

import time
import pdb

import numpy as np 
import theano 
import theano.tensor as T 
import h5py

class LSTMLayer(object):