Академический Документы
Профессиональный Документы
Культура Документы
Hopfield Neural Network Gaussian Machine Quadratic Assignment Problems How to Solve Problem Computation Results Conclusion
An mathematic model Inspired by the biological nervous systems Acquires knowledge through learning
Use continuous activation function Fully connected recurrent network Notion of energy
Each state has an energy Computes recursively until a stable state reached Converges to stable states
Output:
ui (t ) 1 xi (t ) = f (ui (t )) = 1 + tanh 2 a 0
Activation Function
ui ( t ) 1 xi (t ) = f (ui (t )) = 1 + tanh 2 a 0
xi =f(ui)
1
a0 parameter determines behavior of the gain function Higher ~ gentle Lower ~ steep
ui
Energy
Lyapunov Condition:
N dE dxi = - 0 dt i =1 dt
Added Gaussian noises that its power vary in time Vary the activation function gain in time
Dynamic Equation:
N dui (t ) = -ui (t ) + Ti , j x j (t ) + I i + i (t ) dt j =1
Output:
1 xi (t ) = f (ui (t )) = 1 + tanh 2
( )
Temperature
1.5
hi (t ) = N (0, s i (t ))
0.5
hi (t )
-0.5
-1
-1.5
0.5
1.5
2.5
xi =f(ui)
1
ui
Minimum sum of product of flow between facilities and distance between locations
N! Possible Solutions
Problem Representation:
and d kk = 0 , d kl = dlk F = [ fij ] ~ the traffic flow between facility i and j and fii = 0 , fij = f ji
1 if i is assigned to k xik = 0 otherwise
The constraints
N
x
i =1 N
ik
= 1 for i = 1,..., N
x
k =1
ik
QAP Example
Representation of QAP
P = [ xik ] =
Representation of QAP
Dynamic
Output:
Energy function:
ik
(t )
Energy function:
Its minima must correspond to the valid solutions Shorter paths and flow must have lower energy So, break it down into
E ( x) = Epenalty + Ecost
Constraint Satisfaction:
Epenalty A A C N N = xik - 1 + xik - 1 + xik (1 - xik ) 2 i =1 k =1 2 k =1 i =1 2 k =1 i =1
Only one 1 in each row Only one 1 in each column Output level close to 1
N N 2 N N 2
Cost:
Ecost B N N = fij d kl xik x jl 2 i , j =1 k ,l =1
Quadratic term
Linear term
Linear term
Linear term
1 , i = j d ik = 0 , i j
Agenda
Hopfield Neural Network Gaussian Machine Quadratic Assignment Problems How to Solve Problem Computation Results Conclusion
Computation Results
Conclusion