INTRODUCTION TO Machine Learning

Views:
 
Category: Education
     
 

Presentation Description

No description available.

Comments

Presentation Transcript

INTRODUCTION TO Machine Learning : 

INTRODUCTION TO Machine Learning Lecture Slides for

Slide 2: 

Local Models

Introduction : 

3 Introduction Divide the input space into local regions and learn simple (constant/linear) models in each patch Unsupervised: Competitive, online clustering Supervised: Radial-basis func, mixture of experts

Competitive Learning : 

4 Competitive Learning

Slide 5: 

5 Winner-take-all network

Adaptive Resonance Theory : 

6 Adaptive Resonance Theory Incremental; add a new cluster if not covered; defined by vigilance, ? (Carpenter and Grossberg, 1988)

Self-Organizing Maps : 

7 Self-Organizing Maps Units have a neighborhood defined; mi is “between” mi-1 and mi+1, and are all updated together One-dim map: (Kohonen, 1990)

Radial-Basis Functions : 

8 Radial-Basis Functions Locally-tuned units:

Local vs Distributed Representation : 

9 Local vs Distributed Representation

Training RBF : 

10 Training RBF Hybrid learning: First layer centers and spreads: Unsupervised k-means Second layer weights: Supervised gradient-descent Fully supervised (Broomhead and Lowe, 1988; Moody and Darken, 1989)

Regression : 

11 Regression

Classification : 

12 Classification

Rules and Exceptions : 

13 Rules and Exceptions Default rule Exceptions

Rule-Based Knowledge : 

14 Rule-Based Knowledge Incorporation of prior knowledge (before training) Rule extraction (after training) (Tresp et al., 1997) Fuzzy membership functions and fuzzy rules

Normalized Basis Functions : 

15 Normalized Basis Functions

Competitive Basis Functions : 

16 Competitive Basis Functions Mixture model:

Regression : 

17 Regression

Classification : 

18 Classification

EM for RBF (Supervised EM) : 

19 EM for RBF (Supervised EM) E-step: M-step:

Learning Vector Quantization : 

20 Learning Vector Quantization H units per class prelabeled (Kohonen, 1990) Given x, mi is the closest: x mi mj

Mixture of Experts : 

21 Mixture of Experts In RBF, each local fit is a constant, wih, second layer weight In MoE, each local fit is a linear function of x, a local expert: (Jacobs et al., 1991)

MoE as Models Combined : 

22 MoE as Models Combined Radial gating: Softmax gating:

Cooperative MoE : 

23 Cooperative MoE Regression

Competitive MoE: Regression : 

24 Competitive MoE: Regression

Competitive MoE: Classification : 

25 Competitive MoE: Classification

Hierarchical Mixture of Experts : 

26 Hierarchical Mixture of Experts Tree of MoE where each MoE is an expert in a higher-level MoE Soft decision tree: Takes a weighted (gating) average of all leaves (experts), as opposed to using a single path and a single leaf Can be trained using EM (Jordan and Jacobs, 1994)