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.

Machine Learning vs. Deep Learning

213 views

Published on

Las aplicaciones de Inteligencia Artificial como Machine Learning y Deep Learning se han convertido en parte importante en nuestras vidas. Los productos que compramos, si somos o no aptos para un préstamo bancario, las películas o series que Netflix nos recomienda, coches autoconducidos, reconocimiento de objetos, etc; toda esa información es dirigida hacia nosotros por estos algoritmos.

En la actualidad, estos campos de estudio son los más apasionantes y retadores en computación debido a su alto nivel de complejidad y gran demanda en el mercado. En esta presentación vamos a conocer y aprender a diferenciar estos conceptos, ya que son herramientas inevitables para el mejoramiento de la vida humana.

A continuación, te presentamos algunos de los temas específicos que se expondrán:
- Contexto de ML y DL en Inteligencia Artificial.
- Machine Learning.
- Supervised Learning.
- Unsupervised Learning.
- Deep Learning.
- Artificial Neural Network.
- Convolutional Neural Networks.
- Aplicaciones en ML y DL.

Published in: Technology
  • Be the first to comment

Machine Learning vs. Deep Learning

  1. 1. Nuestras locaciones
  2. 2. Nuestros Panelistas Marvin Abisrror Data Scientist, CoE en Belatrix Jans Álvarez Marketing Analyst
  3. 3. Agenda • Context of ML and DL in Artificial Intelligence. • Machine Learning. • Deep Learning. • Artificial Neural Network. • Convolutional Neural Networks. • Applications in ML and DL. ¿QUESTIONS? #MachineLearningBSF
  4. 4. Context of ML and DL
  5. 5. ¿QUESTIONS? #MachineLearningBSF Artificial Intelligence
  6. 6. ¿QUESTIONS? #MachineLearningBSF Artificial Intelligence Machine Learning
  7. 7. ¿QUESTIONS? #MachineLearningBSF Artificial Intelligence Machine Learning Big Data
  8. 8. ¿QUESTIONS? #MachineLearningBSF Artificial Intelligence Machine Learning Big Data Deep Learning
  9. 9. Approaches of Machine Learning ¿QUESTIONS? #MachineLearningBSF MACHINE LEARNING SUPERVISED REINFORCEMENTUNSUPERVISED
  10. 10. Supervised Learning - Linear Regression ¿QUESTIONS? #MachineLearningBSF
  11. 11. Linear Regression ¿QUESTIONS? #MachineLearningBSF
  12. 12. Linear Regression ¿QUESTIONS? #MachineLearningBSF
  13. 13. Linear Regression ¿QUESTIONS? #MachineLearningBSF
  14. 14. Gradient Descent ¿QUESTIONS? #MachineLearningBSF
  15. 15. Gradient Descent ¿QUESTIONS? #MachineLearningBSF
  16. 16. Gradient Descent ¿QUESTIONS? #MachineLearningBSF
  17. 17. Supervised Learning - Classification ¿QUESTIONS? #MachineLearningBSF
  18. 18. Supervised Learning - Classification ¿QUESTIONS? #MachineLearningBSF
  19. 19. Unsupervised Learning: Clustering ¿QUESTIONS? #MachineLearningBSF
  20. 20. Unsupervised Learning - Recommended Systems ¿QUESTIONS? #MachineLearningBSF
  21. 21. Unsupervised Learning - Recommended Systems (Matrix Factorization) ¿QUESTIONS? #MachineLearningBSF
  22. 22. Reinforcement Learning ¿QUESTIONS? #MachineLearningBSF Agent Environment ActionState Reward
  23. 23. DeepMind - AlphaGO ¿QUESTIONS? #MachineLearningBSF
  24. 24. Deep Learning
  25. 25. Fully Connected Neural Network ¿QUESTIONS? #MachineLearningBSF
  26. 26. Perceptron - Single Layer Feedforward Neural Network ¿QUESTIONS? #MachineLearningBSF X1 X2 1 ∑ W1 b h f(h) yW2
  27. 27. Mathematically ¿QUESTIONS? #MachineLearningBSF
  28. 28. Neural Networks ¿QUESTIONS? #MachineLearningBSF
  29. 29. Convolutional Neural Network (CNN) ¿QUESTIONS? #MachineLearningBSF
  30. 30. Convolutional Neural Network (CNN) ¿QUESTIONS? #MachineLearningBSF
  31. 31. Convolutional Neural Network (CNN) ¿QUESTIONS? #MachineLearningBSF
  32. 32. Convolutional Neural Network (CNN) ¿QUESTIONS? #MachineLearningBSF
  33. 33. Would you cross this Bridge? ¿QUESTIONS? #MachineLearningBSF
  34. 34. DEMO
  35. 35. Examples of ML and DL https://github.com/Marvinsky/machine_learning_vs_deep_learning
  36. 36. Bibliography • Dmytro Mishkin and Nikolay Sergievskiy and Jiri Matas. Systematic evaluation of {CNN} advances on the ImageNet. (2016). https://arxiv.org/pdf/1606.02228.pdf • Andrej Karpathy and Justin Johnson and Fei{-}Fei Li. Visualizing and Understanding Recurrent Networks. (2015). https://arxiv.org/pdf/1506.02078.pdf • Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros. Generative Visual Manipulation on the Natural Image Manifold. (2016). https://arxiv.org/pdf/1609.03552.pdf • Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. (2017). https://arxiv.org/pdf/1703.10593.pdf • Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang, and Stephen Paul Smolley. Least Squares Generative Adversarial Networks. (2017). https://arxiv.org/pdf/1611.04076.pdf • Tianqi Chen, Carlos Guestrin. XGBoost: A Scalable Tree Boosting System. (2016). https://arxiv.org/pdf/1603.02754.pdf • Hado van Hasselt, Arthur Guez, David Silver. Deep Reinforcement Learning with Double Q-learning. (2015).https://arxiv.org/pdf/1509.06461.pdf ¿QUESTIONS? #MachineLearningBSF
  37. 37. Bibliography • Yoshua Bengio. Practical recommendations for gradient-based training of deep architectures. (2012). https://arxiv.org/pdf/1206.5533.pdf • Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. (2014). https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf • Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. Generative Adversarial Networks. (2014). https://arxiv.org/pdf/1406.2661.pdf • Xiaohan Jin, Ye Qi, Shangxuan Wu. CycleGAN Face-off. (2017). https://arxiv.org/pdf/1712.03451.pdf • Sergey Ioffe and Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. (2015). https://arxiv.org/pdf/1502.03167.pdf • Alec Radford, Luke Metz, Soumith Chintala. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. (2015). https://arxiv.org/pdf/1511.06434.pdf ¿QUESTIONS? #MachineLearningBSF
  38. 38. Preguntas
  39. 39. ¡Muchas Gracias! www.belatrixsf.com

×