outline intro to representation and heuristic search machine learning (clustering) and my research

24
Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Upload: jeremy-wiggins

Post on 14-Jan-2016

214 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Outline

Intro to Representation and Heuristic Search

Machine Learning (Clustering) and My Research

Page 2: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction to Representation The representation function is to

capture the critical features of a problem and make that information accessible to a problem solving procedure

Expressiveness (the result of the feature abstracted) and efficiency (the computational complexity) are major dimensions for evaluating knowledge representation

Page 3: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction to Search

Consider “tic-tac-toe” Starting with an empty board, The first player can place a X on any

one of nine places Each move yields a different board

that will allow the opponent 8 possible responses

and so on…

Page 4: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction to Search We can represent this collection of

possible moves by regarding each board as a state in a graph

The link of the graph represent legal move

The resulting structure is a state space graph

Page 5: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

“tic-tac-toe” state space graph

Page 6: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction to Search

Human use intelligent search

Human do not do exhaustive search

The rules are known as heuristics, and they constitute one of the central topics of AI search

Page 7: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

State Space Representation

State space search characterizes problem solving as the process of finding a solution path form the start state to a goal

A goal may describe a state, such as winning board in tic-tac-toe

Page 8: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction Consider heuristic in the game of tic-tac-

toe A simple analysis put the total number of

states for 9! Symmetry reduction decrease the

search space Thus, there are not 9 but 3 initial moves:

to a corner to the center of a side to the center of the grid

Page 9: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction

Page 10: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction Use of symmetry on the second level

further reduces the number of path to 3* 12 * 7!

A simple heuristic, can almost eliminate search entirely: we may move to the state in which X has the most winning opportunity

In this case, X takes the center of the grid as the first step

Page 11: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction

Page 12: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Introduction

Page 13: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Outline

Intro to Representation and Heuristic Search

Machine Learning (Clustering) and My Research

Page 14: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Clustering

Clustering is trying to find similar groups based on given dimensions

It is know as unsupervised learning

Page 15: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

K-means Clustering

Page 16: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

K-means Clustering

Page 17: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

K-means Clustering

Page 18: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

K-means Clustering

Page 19: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

K-means Clustering

Page 20: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Experiment setup: HSSP matrix: 1b25

Page 21: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Representation of Segment Sliding window size: 9 Each window corresponds to a

sequence segment, which is represented by a 9 × 20 matrix plus additional nine corresponding secondary structure information obtained from DSSP.

More than 560,000 segments (413MB) are generated by this method.

DSSP: Obtain 2nd Structure information

Page 22: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

HSSP-BLOSUM62 Measure

Page 23: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Research Topics

Page 24: Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research

Part1Bioinformatics

Knowledge and Dataset Collection

Part2Discovering Protein

Sequence Motifs

Part3Motif Information

Extraction

Part4Mining the Relations between Motifs and

Motifs

Part5Protein Local Tertiary Structure Prediction

FutureWorks