Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Learning	Machine	Learning
A	little	intro	to	a	(not	that	complex)	world
@joel__lord
#phptek
About	Me
@joel__lord
#phptek
Our	Agenda	for	today…
• AI	vs	ML
• Deep	Learning	&	
Neural	Networks
• Supervised	vs	
unsupervised
• Na...
@joel__lord
#phptek
@joel__lord
#phptek
Artificial	Intelligence
Artificial	intelligence (AI)	
is intelligence exhibited	by machines.	
In compu...
@joel__lord
#phptek
Artificial	Intelligence
“takes	actions	that	maximize	
its	chance	of	success	at	some	
goal”
@joel__lord
#phptek
Examples	in	real	life
@joel__lord
#phptek
Machine	Learning
Machine	learning	(ML) is	the	subfield	
of computer	science that	gives	"computers	the	...
@joel__lord
#phptek
@joel__lord
#phptek
@joel__lord
#phptek
@joel__lord
#phptek
@joel__lord
#phptek
@joel__lord
#phptek
“Don’t	be	afraid	of	artificial	intelligence,	be	
afraid	of	humanity.”
@joel__lord
#phptek
Deep	Learning	&	
Big	Data
• Explosion	of	digital	data
• Can’t	be	processed	with	
traditional	methods	
...
@joel__lord
#phptek
Neural	
Networks
• Breaking	big	problems	
in	small	layers
@joel__lord
#phptek
Supervised
Learning
• Requires feedback
• Starts with nothing
and increases its
understanding
• Useles...
@joel__lord
#phptek
Unsupervised	
Learning
• There	is	no	feedback
• Good	in	the	case	of	no	right	or	
wrong	answer
• Helps	...
@joel__lord
#phptek
The	Naïve	Bayes	Classifier
@joel__lord
#phptek
Bayes	Theorem
• 𝑃 𝐴 𝐵 =
% &
% & '% (
@joel__lord
#phptek
Bayes	Theorem
• 𝑃 𝐴 𝐵 =
% 𝐵 𝐴 % &
% 𝐵 𝐴 % & ' )*% 𝐵 𝐴 )*% &
@joel__lord
#phptek
Bayes	Theorem
• 𝑃 𝐴 𝐵 =
∏ % 𝐴 𝑊-
.
/01
∏ % 𝐴 𝑊-
.
/01 ' ∏ )*% 𝐴 𝑊-
.
/01
@joel__lord
#phptek
Bayes	Theorem
• 𝑃 𝐴 𝐵 = 𝑊2∱
@joel__lord
#phptek
Naive	Bayes	
Classifier
• Let’s	look	at	a	concrete	
example.
• You	never	know	what	
you’re	gonna get
@joel__lord
#phptek
Probability	that	a	chocolate	has	nuts
Nuts No	Nuts
Round 25% 75%
Square 75% 25%
Dark 10% 90%
Light 90%...
@joel__lord
#phptek
Do	round,	light	chocolates	have	nuts?
Nuts No	Nuts
Round 25% 75% 0.25 0.75
Square 75% 25% - -
Dark 10%...
@joel__lord
#phptek
Do	round,	light	chocolates	have	nuts?
Nuts No	Nuts
Round 25% 75% 0.25 0.75
Square 75% 25% - -
Dark 10%...
@joel__lord
#phptek
Do	round,	light	chocolates	have	nuts?
Nuts No	Nuts
Round 25% 75% 0.25 0.75
Square 75% 25% - -
Dark 10%...
@joel__lord
#phptek
Naïve	Bayes	Classifier	in	code
var Classifier = function() {
this.dictionaries = {};
};
Classifier.pro...
@joel__lord
#phptek
@joel__lord
#phptek
Sentiment	
Analysis
• Not	Machine	Learning
• Uses	classifiers	and	
AFINN-165	(and	
emojis)
@joel__lord
#phptek
Sentiment	
Analysis
• Javascript:
• npm install	sentiment
• PHP:	
• composer	require	
risan/sentiment-...
@joel__lord
#phptek
Genetic	
Algorithm
• Awesome	shit!
@joel__lord
#phptek
Genetic	
Algorithm
• Create	a	population	of	
random	individuals
• Keep	the	closest	individuals
• Keep	...
@joel__lord
#phptek
Genetic	
Algorithm
• Create	a	population	of	
random individuals
• Keep	the	closest	individuals
• Keep	...
@joel__lord
#phptek
Genetic	Algorithm
Credit:	AutoDesk
https://autodeskresearch.com/projects/Dreamcatcher
@joel__lord
#phptek
https://www.youtube.com/watch?v=yci5FuI1ovk
@joel__lord
#phptek
Genetic	Algorithm	in	code
//Declare Consts
function randomInt(min, max) {…}
function random(min, max) ...
Impact	of	parameters on	Genetic Algorithms
@joel__lord
#phptek
What	did	we	learn?
• Machine	Learning	and	Artificial	Intelligence
• Big	Data	and	Deep	Learning
• Super...
Presented	By
JOEL	LORD
PHP	[tek],	May	26th 2017
@joel__lord
joellord
Thank	you
https://joind.in/talk/47902
Presented	By
JOEL	LORD
PHP	[tek],	May	26th 2017
@joel__lord
joellord
Questions?
https://joind.in/talk/47902
Learning About Machine Learning
Upcoming SlideShare
Loading in …5
×

Learning About Machine Learning

178 views

Published on

Slides for my talk at PHP[tek] 2017 in Atlanta, GA
From chatbots to your home thermostat, it seems like machine learning algorithms are everywhere nowadays. How about understanding how this works now? In this talk, you will learn the basics of machine learning through various basic examples, without the need for a Ph.D. At the end of this talk, you will know what the Naive Bayes classifiers, sentiment analysis, and basic genetic algorithms are and how they work. You will also see how to create your own implementations in PHP.

Published in: Technology
  • Be the first to comment

Learning About Machine Learning

  1. 1. Learning Machine Learning A little intro to a (not that complex) world
  2. 2. @joel__lord #phptek About Me
  3. 3. @joel__lord #phptek Our Agenda for today… • AI vs ML • Deep Learning & Neural Networks • Supervised vs unsupervised • Naïve Bayes Classifier • Genetic Algorithms • Q&A
  4. 4. @joel__lord #phptek
  5. 5. @joel__lord #phptek Artificial Intelligence Artificial intelligence (AI) is intelligence exhibited by machines. In computer science, the field of AI research defines itself as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of success at some goal.
  6. 6. @joel__lord #phptek Artificial Intelligence “takes actions that maximize its chance of success at some goal”
  7. 7. @joel__lord #phptek Examples in real life
  8. 8. @joel__lord #phptek Machine Learning Machine learning (ML) is the subfield of computer science that gives "computers the ability to learn without being explicitly programmed."
  9. 9. @joel__lord #phptek
  10. 10. @joel__lord #phptek
  11. 11. @joel__lord #phptek
  12. 12. @joel__lord #phptek
  13. 13. @joel__lord #phptek
  14. 14. @joel__lord #phptek “Don’t be afraid of artificial intelligence, be afraid of humanity.”
  15. 15. @joel__lord #phptek Deep Learning & Big Data • Explosion of digital data • Can’t be processed with traditional methods anymore
  16. 16. @joel__lord #phptek Neural Networks • Breaking big problems in small layers
  17. 17. @joel__lord #phptek Supervised Learning • Requires feedback • Starts with nothing and increases its understanding • Useless if the data is of bad quality • Use cases: • Classification
  18. 18. @joel__lord #phptek Unsupervised Learning • There is no feedback • Good in the case of no right or wrong answer • Helps to identify patterns or data structures • Use case: • You might also be interested in… • Grouping customers by purchasing behaviors
  19. 19. @joel__lord #phptek The Naïve Bayes Classifier
  20. 20. @joel__lord #phptek Bayes Theorem • 𝑃 𝐴 𝐵 = % & % & '% (
  21. 21. @joel__lord #phptek Bayes Theorem • 𝑃 𝐴 𝐵 = % 𝐵 𝐴 % & % 𝐵 𝐴 % & ' )*% 𝐵 𝐴 )*% &
  22. 22. @joel__lord #phptek Bayes Theorem • 𝑃 𝐴 𝐵 = ∏ % 𝐴 𝑊- . /01 ∏ % 𝐴 𝑊- . /01 ' ∏ )*% 𝐴 𝑊- . /01
  23. 23. @joel__lord #phptek Bayes Theorem • 𝑃 𝐴 𝐵 = 𝑊2∱
  24. 24. @joel__lord #phptek Naive Bayes Classifier • Let’s look at a concrete example. • You never know what you’re gonna get
  25. 25. @joel__lord #phptek Probability that a chocolate has nuts Nuts No Nuts Round 25% 75% Square 75% 25% Dark 10% 90% Light 90% 10%
  26. 26. @joel__lord #phptek Do round, light chocolates have nuts? Nuts No Nuts Round 25% 75% 0.25 0.75 Square 75% 25% - - Dark 10% 90% - - Light 90% 10% 0.9 0.1
  27. 27. @joel__lord #phptek Do round, light chocolates have nuts? Nuts No Nuts Round 25% 75% 0.25 0.75 Square 75% 25% - - Dark 10% 90% - - Light 90% 10% 0.9 0.1 4 𝑷𝒊 𝒏 𝒊8𝟏 0.225 0.075
  28. 28. @joel__lord #phptek Do round, light chocolates have nuts? Nuts No Nuts Round 25% 75% 0.25 0.75 Square 75% 25% - - Dark 10% 90% - - Light 90% 10% 0.9 0.1 4 𝑷𝒊 𝒏 𝒊8𝟏 0.225 0.075 𝑃 🌰 = 0.225 0.225 + 0.075 = 0.75 = 75%
  29. 29. @joel__lord #phptek Naïve Bayes Classifier in code var Classifier = function() { this.dictionaries = {}; }; Classifier.prototype.classify = function(text, group) { }; Classifier.prototype.categorize = function(text) { };
  30. 30. @joel__lord #phptek
  31. 31. @joel__lord #phptek Sentiment Analysis • Not Machine Learning • Uses classifiers and AFINN-165 (and emojis)
  32. 32. @joel__lord #phptek Sentiment Analysis • Javascript: • npm install sentiment • PHP: • composer require risan/sentiment- analysis
  33. 33. @joel__lord #phptek Genetic Algorithm • Awesome shit!
  34. 34. @joel__lord #phptek Genetic Algorithm • Create a population of random individuals • Keep the closest individuals • Keep a few random individuals • Introduce random mutations • Randomly create ”children” • Magically end up with a valid solution
  35. 35. @joel__lord #phptek Genetic Algorithm • Create a population of random individuals • Keep the closest individuals • Keep a few random individuals • Introduce random mutations • Randomly create ”children” • Magically end up with a valid solution
  36. 36. @joel__lord #phptek Genetic Algorithm Credit: AutoDesk https://autodeskresearch.com/projects/Dreamcatcher
  37. 37. @joel__lord #phptek https://www.youtube.com/watch?v=yci5FuI1ovk
  38. 38. @joel__lord #phptek Genetic Algorithm in code //Declare Consts function randomInt(min, max) {…} function random(min, max) {…} function randomIndividual() {…} function randomPopulation(size) {…} function fitness(individual) {…} function sortByFitness(population) {…} function mutate(population) {…} function reproduce(father, mother) {…} function evolve(population) {…} function findSolution() { var population = randomPopulation(POP_SIZE); var generation = 0; while (fitness(population[0]) > CLOSE_ENOUGH) { generation++; population = evolve(population); } return {solution: population[0], generations: generation}; } var sol = findSolution();
  39. 39. Impact of parameters on Genetic Algorithms
  40. 40. @joel__lord #phptek What did we learn? • Machine Learning and Artificial Intelligence • Big Data and Deep Learning • Supervised vs unsupervised • Basic Algorithms • Naïve Bayes Classifier • Sentiment Analysis • Genetic Algorithm • Hopefully, you don’t feel intimidated by ML anymore
  41. 41. Presented By JOEL LORD PHP [tek], May 26th 2017 @joel__lord joellord Thank you https://joind.in/talk/47902
  42. 42. Presented By JOEL LORD PHP [tek], May 26th 2017 @joel__lord joellord Questions? https://joind.in/talk/47902

×