llSourcell

"""
Once a model is learned, use this to play it.
"""

from flat_game import carmunk
import numpy as np
from nn import neural_net

NUM_SENSORS = 3

llSourcell

Close up lines (they are in parentheses in the script) insert them where necessary
get yur self driving truks rite her
SLAM
Planning ain’t easy but somebody gotta do itt
 The truth will set you free
but they’re WRONG 

Intro skit:
me: forced human interaction sucks, im glad i can book a self driving Uber

llSourcell

#Siraj:
Hi everyone, welcome to the Stack Share Tech Stack Podcast. I’m your host Siraj and I have with me the Stack Share CEO Yonas. In this episode we sat down with Jatinder Singh directory of engineering at HotelTonight. One of the world’s largest hotel apps with over fourteen million downloads. We talked about how engineers contribute new ideas, their iOS and Android teams, the first version of HotelTonight hint, it wasn’t native.




How they introduced global caching via Fastly and reduced the number of servers by 4x, how they run tests in containers, building a schemaless append only store on top of MySQL based on FriendFeed and Uber’s implementation plus much more. How are you doing today how’s life?

llSourcell

$(document).ready(function(){
     $('body,html').animate({scrollTop: 156}, 800); 
});

llSourcell

import numpy as np

def nonlin(x,deriv=False):
	if(deriv==True):
	    return x*(1-x)

	return 1/(1+np.exp(-x))
    
X = np.array([[0,0,1],
            [0,1,1],

llSourcell

import numpy as np  


# The following is a function definition of the sigmoid function, 
which is the type of non-linearity chosen for this neural net.
It is not the only type of non-linearity that can be chosen, 
but is has nice analytical features and is easy to teach with. 
In practice, large-scale deep learning systems use piecewise-linear functions 
because they are much less expensive to evaluate. 
# The implementation of this function does double duty. 

llSourcell

sh-3.2# python pipeline.py 
Traceback (most recent call last):
 File "pipeline.py", line 10, in <module>
   features = np.delete(tpot_data.view(np.float64).reshape(tpot_data.size, -1), tpot_data.dtype.names.index('class'), axis=1)
 File "/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/numpy/core/records.py", line 498, in view
   return self.__array__().view(dtype)
ValueError: new type not compatible with array.

llSourcell

# -*- coding: utf-8 -*-
#we're gonna take a 10 x 10 grid of squares
#obstacles are black squares
#objects defined by shape, size, color
#each square gets an x, y coordinate

#return list of occupied grids using computer vision
#find minimimum path between starting object and matching object using a star search

llSourcell

# -*- coding: utf-8 -*-
#we're gonna take a 10 x 10 grid of squares
#obstacles are black squares
#objects defined by shape, size, color
#each square gets an x, y coordinate

#return list of occupied grids using computer vision
#find minimimum path between starting object and matching object using a star search

llSourcell

//Intro

//Neuroevolution
//way of learning.  
//While most neural learning methods focus on modifying 
//only the strengths of neural connections (i.e. their connection weights) like 
//backprop 
//neuroevolution can additionally optimize other parameters, 
//such as the structure of the network (e.g. adding neurons or connections), 
//the type of computation performed by individual neurons, and even learning