Visual Learning and Recognition: Difference between revisions
No edit summary |
|||
Line 6: | Line 6: | ||
==Introduction to Data== | ==Introduction to Data== | ||
September 8 | |||
The extremes of data. | |||
If we have very few images, we are working on an extrapolation problem. | |||
As we approach an infinite number of training samples, learning becomes an interpolation problem. | |||
Traditional datasets are in the order of \(10^2-10^4\) training samples. | |||
Current datasets are in the order of \(10^5-10^7\) training samples. | |||
==Data-driven Methods in Vision== | ==Data-driven Methods in Vision== |
Revision as of 16:48, 8 September 2020
Notes for CMSC828I Visual Learning and Recognition (Fall 2020) taught by Abhinav Shrivastava
This class covers:
- How a sub-topic evolved
- State of the art
Introduction to Data
September 8
The extremes of data.
If we have very few images, we are working on an extrapolation problem.
As we approach an infinite number of training samples, learning becomes an interpolation problem.
Traditional datasets are in the order of \(10^2-10^4\) training samples.
Current datasets are in the order of \(10^5-10^7\) training samples.
Data-driven Methods in Vision
Will be on the exam
- Back-prop and SGD,
- Softmax, sigmoid, cross entropy