Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical...

17
Adaptive Hopfield Network Dr. Gürsel Serpen Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo Toledo, Ohio, USA

Transcript of Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical...

Page 1: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Adaptive Hopfield Network

Dr. Gürsel SerpenGürsel SerpenAssociate Professor

Electrical Engineering and Computer Science DepartmentUniversity of ToledoToledo, Ohio, USA

Page 2: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Presentation Topics

Motivation for research Classical Hopfield network (HN) Adaptation – Gradient Descent Adaptive Hopfield Network (AHN) Static Optimization with AHN Results and Conclusions

Serpen et al., Upcoming Journal Article (Insallah!)

http://www.eecs.utoledo.edu/~serpen

FOR MORE INFO...

Page 3: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Motivation Classical Hopfield neural network (HN) has been shown to

have the potential to address a very large spectrum of static optimization problems.

Classical HN is NOT trainable: implies that it can NOT learn from prior search attempts.

A hardware realization of the Hopfield network is very attractive for real-time, embedded computing environments.

Is there a way (e.g., training or adaptation) to incorporate

the experience (gained as a result of prior search attempts) into the network dynamics (weights) to help the network focus on promising regions of the overall search space?

Page 4: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Research Goals Propose gradient-descent based procedures to “adapt”

weights and constraint weighting coefficients of HN. Develop an indirect procedure to define Develop an indirect procedure to define “pseudo” values “pseudo” values

for desired neuron outputsfor desired neuron outputs (much like the way desired (much like the way desired output values for hidden layer neurons in an MLP).output values for hidden layer neurons in an MLP).

Develop space-efficient schemes to store the symmetric weight matrix (upper/lower triangular) for large-scale problem instances.

Apply (through simulation) the adaptive HN algorithm to (large-scale) static optimization problems.

Page 5: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Classical Hopfield Net Dynamics

K

jijiji

i btzwtudt

tdu

1

)( ii ufz

Neuron Dynamics Sigmoid functionNumber of Neurons

,,....,2,1 Ki

jiij ww wk1

wk2

wkJ

1z

2z

Kz

kz k-th node

Page 6: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Weights (interconnection) - Redefined

S K

iii

S K

i

K

jjiijij zgzzdgE

1 11 1 12

1)(z

S

ijijij dgw1

=

S

ii gb1

=

K

i

K

jjiij zzwE

1 12

1

K

i

z K

iii

i

zbdzzf1 0 1

1 )(1

Liapunov Function

Generic

Decomposed

Weights Defined

Page 7: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Adaptive Hopfield NetBlock Diagram

(Classical)

Hopfield Network

Adapt Constraint Weighting Coefficients

Adapt Weights

,ktz

1ktW

ktg

0tg

0tz

Initial weight values

Initial weight coefficient values

Initial neuron outputs

0tW

Adjoint Hopfield Network

,*ktz

Page 8: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Adaptive Hopfield NetPseudoCode

Initialization• Initialize network constraint weighting coefficients.• Initialize weights.• Initialize Hopfield net neuron outputs (randomly).

Adaptive SearchRelaxation• Relax Hopfield dynamics until convergence to a fixed

point.Adaptation• Relax Adjoint network until convergence to a fixed point.• Update weights.• Update constraint weighting coefficients.

Termination Criteria • if not satisfied, continue with Adaptive Search.

Page 9: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Hopfield Network Relaxation

wk1

wk2

wkK

Hopfield Network

1z

2z

Kz

kz

k-th node

Page 10: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Adaptation of WeightsAdjoint Hopfield Network

1z

2z

Kz

*kz

k-th node

kwuf 22

kwuf 11

KkK wuf

ek

K

jijjiji

i etzwuftzdt

tdz

1

***

iii ze

Adjoint Network

,,....,2,1 Ki

Page 11: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Adaptation of WeightsRecurrent BackProp

jiiij

ij zzufw

Ew *

jiij ww

Kji ,...,2,1,

Weight Update – Recurrent BackProp

Page 12: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

AdaptationConstraint Weighting Coefficients

),(),(),(),( 21 kSkkk tEtEtEtE zzzz

k

kkk tg

tEtgtg

,

1zGradient Descent

Adaptation Rule

Error Function – Problem Specific and Redefined

),()(),()( ''11 kCkCkk tEtgtEtg zz

),(),(),(),( 21 kSkkk tEtEtEtE zzzz

Page 13: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

AdaptationConstraint Weighting Coefficients

kk

k tEtg

tE,

)(

, ' zz

kkk tEtgtg ,'1 z

Partial Derivative – Readily Computable

Final Form of Coefficient Update Rule

Page 14: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Mapping A Static Optimization Problem

N

i

N

j

N

nnjrowrow zgE

1 1

2

1

1

NN

iieE

1

2

2

1

NN

i kl

ii

kl w

ze

w

E

1

N

q

N

r kl

qrqr

kl w

ze

w

E

1 1

.12

1 1 1

N

q

N

r kl

qrN

nqnrow

kl

row

w

zzg

w

E

N

nnrrowqr zge

1

12

Generic Partial Problem-Specific Partial

Page 15: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Simulation Study

Traveling Salesman ProblemA preliminary work at this timeUp to 100 cities performedComputing Resources – Ohio Supercomputing CenterPreliminary findings suggest that the theoretical framework is sound and projections are validComputational cost (weight matrix size) poses significant challenge for simulation purposes – on going research effortCurrently in progress

Page 16: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Conclusions

An adaptation mechanism, which modifies constraint weighting coefficient parameter values and weights of the classical Hopfield network, was proposed.

A mathematical characterization of the adaptive Hopfield network was presented.

Preliminary simulation results suggest the proposed adaptation mechanism to be effective in guiding the Hopfield network towards high-quality feasible solutions of large-scale static optimization problems.

We are also exploring incorporating a computationally viable stochastic search mechanism to further improve quality of solutions computed by the adaptive Hopfield network while preserving parallel computation capability.

Page 17: Adaptive Hopfield Network Gürsel Serpen Dr. Gürsel Serpen Associate Professor Electrical Engineering and Computer Science Department University of Toledo.

Thank You !

Questions ?We gratefully acknowledge the computing resources grant provided by the State of Ohio Supercomputing Center (in USA) in facilitating the simulation study.

We appreciate the support provided by the Kohler Internationalization Awards Program at the University of Toledo to facilitate this conference presentation.