machine learning 참고 자료 2 learning definition learning is the improvement of performance in...
TRANSCRIPT
Machine Learning 참고 자료
2
Learning Definition
Learning is the improvement of performance in some environment through the acquisition of knowledge resulting from experience in that environment.
3
Machine Learning: Tasks Supervised Learning
Learn fw from training set D={(x,y)} s.t.
Classification: y is discrete Regression: y is continuous
Unsupervised Learning Learn fw from D={(x)} s.t. Density Estimation Compression, Clustering
)()( xxw fyf
xxw )(f
4
Machine Learning: Methods Symbolic Learning
Version Space Learning Neural Learning
Multilayer Perceptrons (MLPs) Evolutionary Learning
Genetic Algorithms Probabilistic Learning
Bayesian Networks (BNs) Other Machine Learning Methods
Decision Trees (DTs)
5
Applications of Machine Learning Driving an autonomous vehicle
무인 자동차 운전 , 센서기반 제어 등에도 응용 Classifying new astronomical structures
천체 물체 분류 , Decision tree learning 기법 사용 Playing world-class Backgammon
실제 게임을 통해서 전략을 학습 , 탐색공간 문제에 응용
6
A Definition of Learning: Well-posed Learning Problems
Definition A computer program is said to learn from experience E
with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
A class of tasks T Experience E Performance measure P
7
Checkers Problem (1/2)
말은 대각선으로만 움직일 수 있다 . 맞은편 끝까지 가기 전에는 앞으로만 진행할 수 있다 . 대각선에 상대편 말이 있을 경우 그 말을 없앨수 있다 . 게임은 한편 말이 모두 없어지면 끝난다 .
8
Checkers Problem (2/2) homepage
http://www.geocities.com/Heartland/7134/Green/grprechecker.htm http://www.acfcheckers.com
9
A Checkers Learning Problem Three Features: 학습문제의 정의
The class of tasks The measure of performance to be improved The source of experience
Example Task T: playing checkers Performance measure P: percent of games won against
opponent Training experience E: playing practice games against
itself
10
Designing a Learning System Choosing the Training Experience Choosing the Target Function Choosing a Representation for the Target
Function Choosing a Function Approximation
Algorithm
11
Choosing the Training Experience (1/2) Key Attributes
Direct/indirect feedback Direct feedback: checkers state and correct move Indirect feedback: move sequence and final
outcomes Degree of controlling the sequence of training
example Learner 가 학습 정보를 얻을 때 teacher 의 도움을
받는 정도
12
Choosing the Training Experience (2/2)
Distribution of examples 시스템의 성능을 평가하는 테스트의 예제 분포를 잘
반영해야 함
13
Choosing the Target Function (1/2) A function that chooses the best move M fo
r any B ChooseMove : B M Difficult to learn
It is useful to reduce the problem of improving performance P at task T to the problem of learning some particular target function.
14
Choosing the Target Function (2/2) An evaluation function that assigns a
numerical score to any B V : B R
15
Target Function for the Checkers Problem Algorithm
If b is a final state that is won, then V(b) = 100 ……. that is lost, then V(b)=-100 ……. that is drawn, then V(b)=0 If b is not a final state, then V(b)=V(b’), where
b’ is the best final board state
16
Choosing a Representation for the Target Function Describing the function
Tables Rules Polynomial functions Neural nets
Trade-off in choice Expressive power Size of training data
^
V
17
Linear Combination as Representation
(b) = w0 + w1x1 + w2x2 + w3x3 +w4x4 + w5x5 + w6x6
x1: # of black pieces on the board
x2: # of red pieces on the board
x3: # of black kings on the board
x4: # of red kings on the board
x5: # of black pieces threatened by red
x6: # of red pieces threatened by black
w1 - w6: weights
^
V
18
Partial Design of a Checkers Learning Program Task T: playing checkers Performance measure P: Percent of games won in
the world tournament Training experience E: games played against itself Target function V: Board R Target function representation (b) = w0 + w1x1 + w2x2 + w3x3 + w4x4 + w5x5 + w6x6
^
V
19
Choosing a Function Approximation Algorithm A training example is represented as an ordered pa
ir <b, Vtrain(b)> b: board state Vtrain(b): training value for b
Instance: “black has won the game (x2 = 0)
<<x1=3, x2=0, x3=1, x4=0, x5=0, x6=0>, +100>
20
Choosing a Function Approximation Algorithm Estimating training values for intermediate
board states Vtrain(b) (Successor(b)) : current approximation to V Successor(b): the next board state
^
V^
V
21
Adjusting the Weights (1/2) Choosing wi to best fit the training example
s Minimize the squared error
ampletrainingexbVb
train
train
bVbVE)(,
2))(')((
22
Adjusting the Weights (2/2) LMS Weight Update Rule
For each training example <b, Vtrain(b)>
1. Use the current weights to calculate V’(b)
2. For each weight wi, update it as
itrainii xbVbVww ))()((^
23
Sequence of Design ChoicesDetermine Type of Training Experience
Determine Target Function
Determine RepresentationOf Learned Function
Determine Learning Algorithm
Table of correct moves
Games against experts Games against
self
Board move
Board value
PolynomialLinear functionof six features
Arfiticial NN
Gradientdescent
Complete Design
LinearProgramming
24
Perspectives in ML “Learning as search in a space of possible h
ypotheses” Representations for hypotheses
Linear functions Logical descriptions Decision trees Neural networks
25
Perspectives in ML Learning methods are characterized by their
search strategies and by the underlying structure of the search spaces.
26
Summary 기계학습은 다양한 응용분야에서 실용적
가치가 크다 . 많은 데이터로부터 규칙성을 발견하는 문제 (data
mining) 문제의 성격 규명이 어려워 효과적인 알고리즘을
개발할 지식이 없는 문제 영역 (human face recognition)
변화하는 환경에 동적으로 적응하여야 하는 문제 영역 (manufacturing process control)
27
Summary 기계학습은 다양한 다른 학문 분야와 밀접히
관련된다 . 인공지능 , 확률통계 , 정보이론 , 계산이론 ,
심리학 , 신경과학 , 제어이론 , 철학 잘 정의된 학습 문제는 다음을 요구한다 .
문제 (task) 의 명확한 기술 , 성능평가 기준 , 훈련경험을 위한 사례
28
Summary 기계학습 시스템의 설계 시에는 다음 사항을 고려
하여야 한다 . 훈련경험의 유형 선택 학습할 목표함수 목표함수에 대한 표현 훈련 예로부터 목표함수를 학습하기 위한 알고리즘
29
Summary 학습은 가능한 가설 공간에서 주어진 훈련 예와
다른 배경지식을 가장 잘 반영하는 하나의 가설을 탐색하는 탐색이다 . 다양한 학습 방법은 서로 다른 가설공간의 형태와 이
공간 내에서 탐색을 수행하는 전략에 의해 규정 지어진다 .
Neural Networks
31
Biological motivation
Neuron receives signals from other neurons through its dendrites
Transmits signals generated by its cell body along the axon
Network of Neuron
32
Neural Network Representations
The primitive unit(e.g. perceptron) N input signals weighted sum threshold function generate
an output
A learning process in the ANN Learning process involves choosing values for the weights w0, …,
wn
Learning rules How network weights are updated?
33
Gradient descent and the delta rule
The delta rule Linear unit for which the output o is given by
Measure for the training error of a hypothesis
d : the set of traing examples td : the target output for training example d
od : the output of the linear unit for training example d We can characterize E as a function of
xwxo )(
w
34
Gradient descent and the delta rule
35
Gradient descent and the delta rule Derivation of the gradient descent rule
Direction of steepest descent along the error space
Derivative E with respect to each component of
The negative of this vector therefore gives the direction of steepest decrease )(wE
w
36
Gradient descent and the delta rule Training rule for gradient descent
wi ← wi + wi where,
Efficient way of calculating the gradient
So,idd
Dddi xotw )(
37
Gradient descent and the delta rule
If is too large, the gradient descent search runs the risk of overstepping the minimum
gradually reduce the value of
38
Multilayer Networks Why multilayer network?
Single perceptrons can only express linear decision surfaces
So, add an extra(hidden) layer between the inputs and outputs
E.g.) the speech recognition task
39
Multilayer Networks Sigmoid function
40
E defined as a sum of the squared errors over all the output units k for all the training examples d.
Dd outputsk
kdkd otwE 2)(2
1)(
Error Function for BP
41
BP Algorithm
42
After a fixed number of iterations (epochs)
Once the error falls below some threshold Once the validation error meets some
criterion
Learning Until…
Self Organizing Map
44
Introduction Unsupervised Learning SOM (Self Organizing Map)
Visualization Abstraction
45
SOM structures
Neighborhood
Input Layer
Output Layer
46
Data to be clustered
47
After 100 iterations
48
After 500 iterations
49
After 2000 iterations
50
After 10000 iterations