Deep Learning - Theory and Practice Linear Regression, Least Squares - - PowerPoint PPT Presentation

deep learning theory and practice
SMART_READER_LITE
LIVE PREVIEW

Deep Learning - Theory and Practice Linear Regression, Least Squares - - PowerPoint PPT Presentation

Deep Learning - Theory and Practice Linear Regression, Least Squares 27-02-2020 Classification and Logistic Regression http://leap.ee.iisc.ac.in/sriram/teaching/DL20/ deeplearning.cce2020@gmail.com Logistic Regression 2- class logistic


slide-1
SLIDE 1

Deep Learning - Theory and Practice

27-02-2020

Linear Regression, Least Squares Classification and Logistic Regression

http://leap.ee.iisc.ac.in/sriram/teaching/DL20/ deeplearning.cce2020@gmail.com

slide-2
SLIDE 2
slide-3
SLIDE 3

Logistic Regression

Bishop - PRML book (Chap 3)

❖ 2- class logistic regression ❖ K-class logistic regression ❖ Maximum likelihood solution ❖ Maximum likelihood solution

slide-4
SLIDE 4
slide-5
SLIDE 5
slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9
slide-10
SLIDE 10
slide-11
SLIDE 11

Learning Using Gradient Descent

slide-12
SLIDE 12

Parameter Learning

  • Solving a non-convex
  • ptimization.
  • Iterative solution.
  • Depends on the initialization.
  • Convergence to a local
  • ptima.
  • Judicious choice of learning

rate

slide-13
SLIDE 13

Least Squares versus Logistic Regression

Bishop - PRML book (Chap 4)

slide-14
SLIDE 14

Least Squares versus Logistic Regression

Bishop - PRML book (Chap 4)

slide-15
SLIDE 15

Deep Networks

  • Are these networks trainable ?
  • Advances in computation and processing
  • Graphical processing units (GPUs) performing multiple

parallel multiply accumulate operations.

  • Large amounts of supervised data sets