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.

Introduction to machine learning

319 views

Published on

Introduction to machine learning

Coding Example:
https://github.com/almamuncsit/Machine-Learning/blob/master/AI%20Project/diabetes%20Prediction.ipynb

Published in: Technology
  • Login to see the comments

Introduction to machine learning

  1. 1. Welcome
  2. 2. Al-Mamun Sarkar Software Engineer weDevs
  3. 3. MACHINE LEARNING
  4. 4. Agenda ❏ Machine Learning ❏ Machine Learning Application ❏ Type of Machine Learning ❏ Machine Learning Algorithms ❏ Machine Learning Workflow ❏ User of Machine Learning
  5. 5. Machine Learning
  6. 6. Artificial Intelligence ❏ Enable the machine to think ❏ Is the brain of a computer
  7. 7. Machine Learning ❏ Gives computers the ability to learn without being explicitly programmed ❏ Statistical tools to explore and analyze data
  8. 8. ML Application ❏ Spam filtering ❏ Recommendation Engine ❏ Search Engine ❏ Fraud Detection ❏ Sentiment Analysis ❏ News Classification
  9. 9. Type of Machine Learning ❏ Supervised learning ❏ Unsupervised learning ❏ Semi-supervised Learning ❏ Reinforcement learning
  10. 10. Supervised Learning ❏ Learn from labeled training data ❏ Input and desired output data are provided
  11. 11. Supervised Learning ❏ Classification ❏ Regression
  12. 12. Classification A classification problem is when the output variable is a category, such as: » “red” or “blue” or “green” » “man” and “women”. » “0” or “1”
  13. 13. Regression A regression problem is when the output variable is a real value, such as: » “dollars” » “Weight” » “Temperature”
  14. 14. Supervised Learning Algorithms ❏ Naive Bayes ❏ Linear regression. ❏ Logistic regression. ❏ Artificial neural networks (ANN) ❏ Decision trees. ❏ Support vector machines (SVM). ❏ Random forests.
  15. 15. Unsupervised Learning ❏ Find hidden structure in unlabeled data ❏ Input and desired output data are not provided
  16. 16. Unsupervised Learning ❏ Clustering ❏ Association
  17. 17. Clustering A clustering problem is where you want to discover the inherent groupings in the data, such as grouping customers by purchasing behavior.
  18. 18. Clustering
  19. 19. Association An association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y.
  20. 20. Unsupervised Learning Algorithms ❏ Hierarchical clustering ❏ K-means clustering ❏ K-NN (k nearest neighbors) ❏ Principal Component Analysis ❏ Singular Value Decomposition ❏ Independent Component Analysis ❏ Association Rules
  21. 21. Semi-Supervised Learning ❏ A mix of supervised and unsupervised learning ❏ Mix of labeled and unlabeled data
  22. 22. Reinforcement learning ❏ Allows the machine or software agent to learn its behavior based on feedback from the environment ❏ Learn by doing ❏ Learn from mistake
  23. 23. Deep Learning
  24. 24. Deep Learning ❏ Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. ❏ Artificial Neural Networks
  25. 25. DL Application ❏ Computer Vision ❏ Face Recognition ❏ Speech Recognition ❏ Natural Language Processing ❏ Audio Recognition ❏ Image Processing
  26. 26. ML Workflow ❏ Find Out The Problem ❏ Creating Dataset ❏ Dataset Cleaning and Visualization ❏ Algorithm Selection ❏ Model Training ❏ Model Testing ❏ Deployment
  27. 27. USE OF MACHINE LEARNING ❏ FACEBOOK ❏ GOOGLE, YAHOO, MSN ❏ GMAIL, YAHOO, HOTMAIL ❏ AMAZON, EBAY, ALIBABA ❏ ROBOTICS
  28. 28. Python for Machine Learning ❏ Numpy ❏ Pandas ❏ Matplotlib, Seaborn ❏ Scikit-learn ❏ Tensorflow, PyTorch ❏ OpenCV ❏ And Many more ……….
  29. 29. Coding Example
  30. 30. Question ?
  31. 31. Thank YOU

×