redwrasse’s gists

redwrasse / mock_refmon.go

Last active February 19, 2022 06:01

A mock reference monitor for accessing a top secret recipe

	// A mock reference monitor design for a mock security system, enforcing the following access control policy:
	// Only the user 'Alice' who identifies herself on requested inputs
	// with her name and her birthday of '01.01.1980' is granted access to
	// the top secret recipe file, stored on disk.
	// This reference monitor design provides (some) security towards the given access policy
	// by a) storing a hash rather than the values of the user inputs of (name, birthday) to compare against,
	// and b) using a salt of the valid inputs as a symmetric key for AES encrypting the top secret recipe file beforehand and
	// for decrypting before returning to Alice.
	//
	// Of course these comments would not be kept in the source code.

redwrasse / mc1.py

Created July 2, 2020 01:34

monte carlo integration of functions on subset of the real line

	"""
	Monte Carlo integration of functions on subsets of the real line,
	using uniform probability distributions
	"""
	import math
	import random


	def montecarlo(f, g, a, b):
	"""

redwrasse / objectrackerstep1.html

Created July 17, 2020 01:41

object tracker step 1

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<title>Object Tracking Service</title>
	<h1>Object Tracker</h1>
	</head>
	<body>
	<video controls width="1250">

redwrasse / conv_ar.py

Last active August 11, 2020 19:08

demonstrating auto-regressive model (motivating full generative model) as trained convolutional layer

redwrasse / genaudiostep2.py

Last active July 30, 2020 02:15

	"""
	Currently trains with decreasing loss

	*** epoch: 0 epoch loss: 276.47448682785034
	*** epoch: 1 epoch loss: 216.9058997631073
	*** epoch: 2 epoch loss: 190.01888144016266
	*** epoch: 3 epoch loss: 171.68642991781235
	*** epoch: 4 epoch loss: 157.7317717075348
	*** epoch: 5 epoch loss: 145.89844578504562
	...

redwrasse / backprop_ex.py

Last active February 11, 2021 05:51

example backprop

	"""
	backprop algorithm on F[a] = xa^2 + a

	For each node function f_i
	- method to calculate value on input, f_i(x_i)
	- method to calculate derivative value on input, K_ij
	- method to calculate parameter derivative on input, xi_i

	Suppose a single input x in R. Suppose the functional to be
	optimized is F[a] = xa^2 + a

redwrasse / gist:221f0d2bb566c616697d3e509e31d784

Created November 12, 2020 21:51

learning query completion as all next-character models

	"""
	attempting to learn query completion as product of all next character models
	P(x_c\|x_q) = prod_i P(x_i \| x_1:i-1)

	Does not scale well for any reasonable sized text document(s). Need smaller length distributions, approximations.
	"""

	import numpy as np
	import random
	import tensorflow.keras as keras

redwrasse / array_reinforcement_learning.py

Created November 13, 2020 17:46

Toy reinforcement learning on an array

	# array_reinforcement_learning.py
	"""
	array_reinforcement_learning
	~~~~~~~~~~~~~~~~~~~~~~~~~~~~
	Reinforcement learning is performed on a 1-dimensional
	finite state space ("array") of k elements:

	S = {1,...,k}

	There are two possible actions: move right (a = 1), or move left (a = -1),

redwrasse / gd_gaussian.py

Last active November 20, 2020 23:03

gradient descent solving mu, sigma for generative gaussian

	# -- coding: utf-8 --
	"""
	generative gaussian model, minimizing <-log p>_data wrt. mu, sigma
	with gradient descent

	-log p = log sigma + log sqrt(2pi) + (x - mu)^2 / (2 sigma^2)
	So

	grad_mu (-log p) = - (x - mu) / sigma^2
	grad_sigma (-log p) = 1 / sigma - (x - mu)^2 / sigma^3

redwrasse / gmm_gd.py

Created November 21, 2020 00:04

Attempted direct gradient descent on 2-state gaussian mixture model

	# gmm_gd.py
	"""
	Direct gradient descent on 2-state gaussian mixture model.
	Not the best way to do this, typically use the EM algorithm instead.

	Training is highly unstable.

	model:
	p(x) = pi * phi_1 + (1-pi) * phi_2
	phi_1, phi_2 ~ normal