Getting started with Machine Learning

Types of machine learning, features, training data, labels.

Transcript

1. Getting started with Machine Learning Presented By : Krunal Kapadiya @krunal3kapadiya http://www.multidots.com/
2. Products using Machine Learning
3. • What is Regression ? • What is Classification of data ? • What is Cluster ? Before we started
4. What is Machine Learning ?
5. What is Machine Learning ? A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. - Tom M Mitchell
6. Types Of Categories
7. Types Of Categories • Supervised Learning • Unsupervised Learning • Reinforcement Learning
8. Supervised Learning
9. Supervised Learning The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.
12. Unsupervised Learning
13. Unsupervised Learning No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).
15. Reinforcement Learning
16. A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle), without a teacher explicitly telling it whether it has come close to its goal. Another example is learning to play a game by playing against an opponent. Reinforcement Learning
18. Neural Network
19. Neural Network Neural networks (also referred to as connectionist systems) are a computational approach which is based on a large collection of neural units loosely modeling the way a biological brain solves problems with large clusters of biological neurons connected by axons.
20. Neural Network
21. Artificial Neural Network
22. Where Machine Learning is used ?
27. How it works ?
28. Collect Data Train Classifier Make Prediction How it works ?
32. Weight Texture Label 150g Bumpy Orange 170g Bumpy Orange 140g Smooth Apple 130g Smooth Apple Feature Feature Training Data
33. Weight Texture Label 150g Bumpy Orange 170g Bumpy Orange 140g Smooth Apple 130g Smooth Apple Feature Feature Examples Training Data
34. Orange Apple Weight => 150g? Yes No Yes No Texture = bumpy ? ... Decision Tree
35. 1. Import Dataset 2. Train Classifier 3. Predict Label for new flower 4. Visualize the tree Goals
36. Demo Time
38. Researchers Developers Data-Scientists Who are using ML Algo ?
41. Google Home
43. No Questions ? Krunal Kapadiya @krunal3kapadiya http://www.multidots.com/