Allison Parrish aparrish

Interactive Machine Learning

Taught by Brad Knox at the MIT Media Lab in 2014. Course website. Lecture and visiting speaker notes.

Power to the People: The Role of Humans in Interactive Machine Learning by Knox, Cakmak, Kulesza, Amershi, and Lau
A Few Useful Things to Know about Machine Learning by Domingos
Machine Learning that Matters by Wagstaff
Beyond Concise and Colorful: Learning Intelligible Rules by Pazzani et al.
[Designing Games with a Purpose] (https://www.cs.cmu.edu/~biglou/GWAP_CACM.pdf) by von Ahn and Dabbish
[Human Model Evaluation in Interactive Supervised

Description

Use these commands to run a jupyter server on a remote server and access it locally in a browser. You must have SSH access to the browser. Use any port you want.

Do not forget to change username@server to the correct value!

TLDR

where	using	command

	from fabric.api import env, run, sudo, local, put

	def production():
	"""Defines production environment"""
	env.user = "deploy"
	env.hosts = ['example.com',]
	env.base_dir = "/var/www"
	env.app_name = "app"
	env.domain_name = "app.example.com"
	env.domain_path = "%(base_dir)s/%(domain_name)s" % { 'base_dir':env.base_dir, 'domain_name':env.domain_name }

	cons = (h, t) -> (m) -> m(h, t)
	car = (x) -> x((h, t) -> h)
	cdr = (x) -> if x then x((h, t) -> t) else null

	map = (ls, f) ->
	cons (f car ls), if cdr ls then map cdr(ls), f else null

	foldl = (ls, f, n) ->
	f (car ls), if cdr ls then foldl (cdr ls), f, n else n

	// Adapted from Zachary Johnson's Commander Clone 0.2 screen scaling example http://www.zachstronaut.com/projects/commander-clone/0.2/game.html
	// Modified to strictly choose 1X or 2X or 4X scaling as appopriate, so we don't end up with screwed up scaling artifacts.
	// NOTE: uses jQuery for the DOM load event
	$(function () {

	fullScreenify();

	window.addEventListener('resize', fullScreenify, false);

	function fullScreenify() {

	import math

	class Vector(object):
	def __init__(self, *args):
	""" Create a vector, example: v = Vector(1,2) """
	if len(args)==0: self.values = (0,0)
	else: self.values = args

	def norm(self):
	""" Returns the norm (length, magnitude) of the vector """

	# -- coding: utf-8 --
	import sys
	import enchant

	"""
	trying to make sense of unicode_ebooks
	you need pyenchant:
	brew install enchant
	pip install pyenchant
	"""

	#!/usr/bin/env python3
	# encoding: utf-8
	"""Use instead of `python3 -m http.server` when you need CORS"""

	from http.server import HTTPServer, SimpleHTTPRequestHandler


	class CORSRequestHandler(SimpleHTTPRequestHandler):
	def end_headers(self):
	self.send_header('Access-Control-Allow-Origin', '*')

	'''This scripts implements Kim's paper "Convolutional Neural Networks for Sentence Classification"
	with a very small embedding size (20) than the commonly used values (100 - 300) as it gives better
	result with much less parameters.

	Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_cnn.py

	Get to 0.853 test accuracy after 5 epochs. 13s/epoch on Nvidia GTX980 GPU.
	'''

	from __future__ import print_function