Machine Learning Intro Session
Download as PPTX, PDF0 likes593 views
The document discusses various use cases for data analysis in photography and computational efficiency, particularly highlighting the Nikon D700's exposure settings determined through a database comparison of images. It further explores machine learning concepts like precision and recall, PCA for feature reduction, and different recommendation engine strategies. Additionally, it touches on anomaly detection in server monitoring, emphasizing the importance of understanding feature relationships and error analysis.
Machine Learning Intro Session
- 23. Identifying use cases – without Google • Anything repetitive (classifying digits/gestures/road conditions/e-mail contents) • Capturing best practices
- 25. The Nikon D700 has a 1,005-pixel RGB (red, green, blue) sensor that measures the intensity of the light and the color of a scene. The camera then compares the information to information from 30,000 images stored in its database. The D700 determines the exposure settings based on the findings from the comparison. Simplified, it works like this: You're photographing a portrait outdoors, and the sensor detects that the light in the center of the frame is much dimmer than the edges. The camera takes this information along with the focus distance and compares it to the ones in the database. The images in the database with similar light and color patterns and subject distance tell the camera that this must be a close-up portrait with flesh tones in the center and sky in the background. From this information, the camera decides to expose primarily for the center of the frame although the background may be over or underexposed. Source: http://my.safaribooksonline.com/book/photography/9780470413203/nikon- d700-essentials/metering_modes • Note the effort on Data collection. • Need for synthetic data.
- 26. • Confusion Matrix Precision is the fraction of retrieved instances that are relevant Recall is the fraction of relevant instances that are retrieved Confusion Matrix
- 28. Sample code • Demo 1 – Simple fit() & predict() • Demo 2 – With Cross Validation • Demo 3 – Use a pickled Classifier
- 31. PCA – Hum Dus, Humara Ek! • Why? Computationally efficient. A pre-processing step when features are large. • Up-to 10X reduction in number of features, without losing information. • Demo 4 – Original # of features 1850. Features used 150
- 32. Clustering
- 33. Recommendation Engines • Where the money is – 75% sales • Don’t make money on hardware – Amazon • User based - based on User Similarity – Collaborative Filtering • Item based – “Users who bought X also bought Y” • Demo 5
- 34. Anomaly Detection So anomaly detection doesn't know what they look like, but knows what they don't look like! Very small number of positive examples
- 35. Error Analysis: Example - data center monitoring. Features x1 = memory use x2 = number of disk access/sec x3 = CPU load x4 = network traffic We suspect CPU load and network traffic grow linearly with one another If server is serving many users, CPU is high and network is high Fail case is infinite loop, so CPU load grows but network traffic is low New feature - CPU load/network traffic Multivariate Gaussian algorithm is aware of “covariance”.