Johnny Chan Atlas7

## entropy-cost.md

      
              1 file
            
          
              0 forks
            
          
              2 comments
            
          
              5 stars
            
          
                Atlas7
                / entropy-cost.md
            
            
              Last active
              October 5, 2022 05:31
            
              
                Deep Neural Network - cross entropy cost - np.sum vs np.dot styles
              
          
    Cross Entropy Cost and Numpy Implementation

Given the Cross Entroy Cost Formula:

where:

J is the averaged cross entropy cost
m is the number of samples
super script [L] corresponds to output layer


## pred-accuracy.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Atlas7
                / pred-accuracy.md
            
            
              Last active
              September 11, 2017 08:36
            
              
                Prediction accuracy computation
              
          
    Q: how the following two differ, in the computation of prediction accuracy? (note: Y = true label, Y_preduction = predicted label).
(from deeplearning.ai, programming assignment. Course 1 - deep learning and neural network.)
Option 1 - Logistric Regression (Week 2):
print("Test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction - Y)) * 100))

  
## nbody.md

      
              1 file
            
          
              0 forks
            
          
              1 comment
            
          
              3 stars
            
          
                Atlas7
                / nbody.md
            
            
              Last active
              August 2, 2021 13:56
            
              
                High Performance Computing (HPC) with Intel Xeon Phi: N-body Simulation Example
              
          
    Abstract

Imagine we have n particles in our "universe". These particles have a random initial x, y, and z coordinates to begin with. Defined by Newton's law of universal gravitation, each particle attracts every other particles in this universe using a force that is directly proportional to the product of their masses and inversely proportional to the square of the distance between their centers. As as result, these particles gain (and lose) velocities and change positions over time. The modelling of this physical mechanics is called a N-body simulation.
There currently exists many N-body simulation algorithms. Some are less advanced and highly computational costly (execution time in the order of O(N^2)) - but simple and easy to understand. Some others are more advanced and significantly more efficient (execution in the order of O(n*log(n)) - but not as simple and easy to understand. This articles focuses on the implementation aspect of the less advanced toy algorithm - for the benefit of ease o

  
## tmux-cheatsheet.markdown

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Atlas7
                / tmux-cheatsheet.markdown
            
            
              Created
              August 13, 2017 10:53
                — forked from MohamedAlaa/tmux-cheatsheet.markdown
            
              
                tmux shortcuts & cheatsheet
              
          
    tmux shortcuts & cheatsheet

start new:
tmux

start new with session name:
tmux new -s myname


## environment.yml
name: helloworld
dependencies:
  - python=2.7
  - anaconda

## alexa_dev_notes.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Atlas7
                / alexa_dev_notes.md
            
            
              Last active
              June 16, 2017 16:02
            
              
                Alex Development - Notes
              
          
    Started learning about voice assistant development with Alexa recently. Using this page to jot down some notes for ease of future references.
Core Sites


Amazon Developer Portal - where you get to develop Alexa Skills.
AWS Developer Portal - where you setup and run the Alexa skills.

Tutorial


Build a Trival Alexa Skill in 60 minutes


## readme.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Atlas7
                / readme.md
            
            
              Created
              June 12, 2017 18:06
                — forked from endolith/readme.md
            
              
                How to stream a webcam to a web browser in Ubuntu
              
          
    Grr this took hours to figure out.  I was trying to install MJPG-streamer and running VLC command lines and all this crap but nothing worked.
First install motion:
~> sudo apt-get install motion

Then create a config file:
~> mkdir ~/.motion

~> nano ~/.motion/motion.conf

  
## SGBP.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Atlas7
                / SGBP.md
            
            
              Last active
              June 12, 2017 13:50
            
              
                Intel Joule, Ubuntu, and Intel RealSense - Setup Instructions
              
          
    Use this page to jot down notes regarding small garden birdwatch project.
Intel Joule


Step 1 - Flash latest Firmware to Intel Joule
Step 2 - Install Intel Joule Ubuntu Desktop on Intel Joule - Get Started - use the Alternative install for Ubuntu Desktop (not core)

How to create a bootable USB on Windows with Rufus - do this for both Ubuntu Desktop Image only.
On Intel Joule, boot Ubuntu from USB (at bootup, press shift). Once installed, power down.
Unplug power. Unplug boot USB. Plug Power to boot up.


step 3 - Update Ubuntu, and install librealsense to enable RealSense camera - See GitHub instructions.


## numpy_fancy_2.py
import numpy as np

# sow a fix seed to make trial and error more predictable
np.random.seed(0)

# create a 10 x 3 NumPy array
a = np.random.rand(10,3)

# do the fancy indexing: for each row, extract the element that is closest to 0.5
a2 = a[np.arange(a.shape[0]), np.argsort(np.abs(a - 0.5))[:,0]]

## fourier.html
<html>
<head>
<script src="//cdnjs.cloudflare.com/ajax/libs/underscore.js/1.4.2/underscore-min.js"></script>
<script src="//ajax.googleapis.com/ajax/libs/jquery/1.8.2/jquery.min.js"></script>
<script src="//cdnjs.cloudflare.com/ajax/libs/modernizr/2.6.2/modernizr.min.js"></script>
<script src="//ajax.cdnjs.com/ajax/libs/json2/20110223/json2.js"></script>

<!--
TODO:
	import numpy as np

	# sow a fix seed to make trial and error more predictable
	np.random.seed(0)

	# create a 10 x 3 NumPy array
	a = np.random.rand(10,3)

	# do the fancy indexing: for each row, extract the element that is closest to 0.5
	a2 = a[np.arange(a.shape[0]), np.argsort(np.abs(a - 0.5))[:,0]]
	<html>
	<head>
	<script src="//cdnjs.cloudflare.com/ajax/libs/underscore.js/1.4.2/underscore-min.js"></script>
	<script src="//ajax.googleapis.com/ajax/libs/jquery/1.8.2/jquery.min.js"></script>
	<script src="//cdnjs.cloudflare.com/ajax/libs/modernizr/2.6.2/modernizr.min.js"></script>
	<script src="//ajax.cdnjs.com/ajax/libs/json2/20110223/json2.js"></script>

	<!--
	TODO: