O slideshow foi denunciado.
Seu SlideShare está sendo baixado. ×
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Anúncio
Próximos SlideShares
Road to machine learning
Road to machine learning
Carregando em…3
×

Confira estes a seguir

1 de 16 Anúncio
Anúncio

Mais Conteúdo rRelacionado

Diapositivos para si (20)

Quem viu também gostou (18)

Anúncio

Semelhante a Basic ML (20)

Mais recentes (20)

Anúncio

Basic ML

  1. 1. Basic Machine Learning for Developers @ignacio_elola
  2. 2. What is import
  3. 3. Who I am Ignacio Elola Background: ● Theoretical Physics ● Complex / Stochastic Systems Current Obsessions: ● Web Data ● Data Science for Business ● Growth
  4. 4. What is ML Arthur Samuel (1959). Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed. Tom Mitchell (1998) Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.
  5. 5. What is ML - Spam detection - Credit Card Fraud - Medical diagnosis - Sentiment analysis - Recommendation systems
  6. 6. What is ML Dataset: ● Train set ● Test set
  7. 7. What is ML Supervised Learning Unsupervised Learning Reinforcement Learning
  8. 8. ML Categorization by output: classification regression
  9. 9. ML Do I want to predict a category? or Do I want to predict a number?
  10. 10. ML - Regression Some algorithms: Least Squares Lasso Support Vector Regression
  11. 11. ML - Regression Least Squares
  12. 12. ML - Regression Support Vector Regression
  13. 13. ML - Classification Can be divided in two groups of algorithms, whether we have labeled data or not With labeled data: KNeighbours classifier SVC Without: KMeans MeanShfit
  14. 14. ML - Live Demo Link to the code used in the live demo: https://github.com/ignacioelola/ML-examples
  15. 15. Resources - O’Reilly books (Doing Data Science, Data Science for business) - For Python: sklearn - ML course on coursera - Kaggle competitions
  16. 16. Thank you!

×