Introduction to Machine Learning

Slide 1

Slide 1 text

Machine Learning Ricardo Coelho @ramcoelho

Slide 2

Slide 2 text

Artiﬁcial Intelligence

Slide 3

Slide 3 text

Algorithm

Slide 4

Slide 4 text

Learning

Slide 5

Slide 5 text

People learn from EXPERIENCE

Slide 6

Slide 6 text

Machines learn from DATA

Slide 7

Slide 7 text

How much data? • A LOT!! • Big Data • Text, Image, Audio, Video, Database, Spreadsheets • AI, Narrow AI, Deep Learning • Neural Network

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

How much data? • A LOT!! • Big Data • Text, Image, Audio, Video, Database, Spreadsheets • AI, Narrow AI, Deep Learning • Neural Network • Statistics

Slide 11

Slide 11 text

Freakonomics

Slide 12

Slide 12 text

Statistics Data Relations Probability Future Data Values Reality Past and Present

Slide 13

Slide 13 text

Inferential Algorithms • Regression • Anomaly Detection • Clustering • Classiﬁcation

Slide 14

Slide 14 text

Regression Find about the future based on the relationship between variables PREDICT

Slide 15

Slide 15 text

Anomaly Detection Identify rare behavior UNUSUAL

Slide 16

Slide 16 text

Clustering Separate intuitive groups STRUCTURE

Slide 17

Slide 17 text

Algorithms (Clustering)

Slide 18

Slide 18 text

Classiﬁcation Find a category for information. Decision Tree, Data Mining TAG

Slide 19

Slide 19 text

Algorithms

Slide 20

Slide 20 text

Supervised learning

Slide 21

Slide 21 text

Genetic/Evolutive Algorithms https://bit.do/evolutionsim

Slide 22

Slide 22 text

Unsupervised learning

Slide 23

Slide 23 text

Want to tag yourself? Yes . No

Slide 24

Slide 24 text

Reinforcement learning

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

Udacity - Intro to Machine Learning (2-3 mo) https://br.udacity.com/course/intro-to-machine-learning--ud120/

Slide 27

Slide 27 text

scikit-learn (sklearn) >>> import numpy as np >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]]) >>> Y = np.array([1, 1, 1, 2, 2, 2]) >>> from sklearn.naive_bayes import GaussianNB >>> clf = GaussianNB() >>> clf.fit(X, Y) GaussianNB(priors=None) >>> print(clf.predict([[-0.8, -1]])) [1]

Slide 28

Slide 28 text

PHP-ML https://github.com/php-ai/php-ml

Slide 29

Slide 29 text

TensorFlow

Slide 30

Slide 30 text

TensorFlow https://youtu.be/oZikw5k_2FM

Slide 31

Slide 31 text

Restrict vs General AI

Slide 32

Slide 32 text

No content

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

No content

Slide 38

Slide 38 text

Thank you!

Slide 39

Slide 39 text

Questions?