MLCC part-2

Machine Learning Terminology, Linear regression hands-on , logistics regression hands-on , reducing loss and Tensorflow

Transcript

1. MLCC Study Jam-part 2 Ahmedabad
2. • ML Terminology (Revise) • Linear Regression and loss (Practical approach) • Reducing loss (Practical approach) • Tensorflow • Logistic Regression (Practical approach) • Build basic ANN from Scratch • Learning material • Conclusion Agenda
3. Machine learning Terminology • Dataset • Input Features • Label/ target • Model weights • loss • Regression • Clustering • Feature extraction • Training • Prediction
5. Continue.. Machine Learning Glossary by Google https://developers.google.com/machine-learning/glossary/
6. Linear Regression
7. Learning (determining) good values for all the weights and the bias from labeled examples (With minimum loss) that model can able to predict new unseen data value. Given an X (input Features) and Y (target/label) GOAL
8. Linear regression - Theory
9. Loss • loss is a number indicating how bad the model's prediction was on a single example. If the model's prediction is perfect, the loss is zero; otherwise, the loss is greater.
11. Linear Regression with One Variable Problem : Here we will implement linear regression with one variable to predict profits for a food truck. Suppose you are the CEO of a restaurant franchise and are considering different cities for opening a new outlet. The chain already has trucks in various cities and you have data for profits and populations from the cities. http://bit.ly/linearReg (colab) File-> Save a copy in drive http://bit.ly/datasetex1(Dataset)
12. No, I don’t like loss let’s reduce it. But how ??
13. Here is Solution
15. Gradient descent
17. Return to colab http://bit.ly/linearReg Another approach
18. Multiple Linear Regression(Multiple Features)
19. TensorFlow
21. Tensorflow Datacamp free tensorflow tutorial : http://bit.ly/tftftf
22. Logistic Regression
23. Theory Instead of predicting exactly 0 or 1, logistic regression generates a probability—a value between 0 and 1, exclusive Many problems require a probability estimate as output. Logistic regression is an extremely efficient mechanism for calculating probabilities. Log Loss is the loss function for logistic regression.
24. Sigmoid function
25. Logistic Regression using Python (scikit-learn) http://bit.ly/log987
27. Artificial Neural Networks
29. ANN example in local machine
30. Learning Material https://goo.gl/3L9cGu Or
31. Krupa Galiya Let’s Connect • Twitter : https://twitter.com/Krupagaliya • LinkedIn : https://www.linkedin.com/in/krupagaliya/ • Github : https://github.com/krupagaliya • Email : krupagaliya@gmail.com