1 Pertemuan 17 HOPFIELD NETWORK Matakuliah: H0434/Jaringan Syaraf Tiruan Tahun: 2005 Versi: 1
2 Learning Outcomes Pada akhir pertemuan ini, diharapkan mahasiswa akan mampu : Menjelaskan konsep dari Jaringan Hopfield
3 Outline Materi Hopfield Model. Lyapnov Function.
4 Hopfield Model
5 Equations of Operation n i - input voltage to the ith amplifier a i - output voltage of the ith amplifier C- amplifier input capacitance I i - fixed input current to the ith amplifier
6 Network Format Define: Vector Form:
7 Hopfield Network
8 Lyapunov Function V a a T Wa – f 1– u ud 0 a i i1= S b T a –+=
9 Individual Derivatives td d f 1– u ud 0 a i a i d d f 1– u ud 0 a i td da i f 1– a i td i n i td i === d dt f 1– u ud 0 a i i1= S n T d a dt = Third Term: Second Term: First Term:
10 Complete Lyapunov Derivative – a i d d f 1– a i td da i 2 i1= S = From the system equations we know: So the derivative can be written: Ifthen a i d d f 1– a i 0
11 Invariant Sets This will be zero only if the neuron outputs are not changing: Therefore, the system energy is not changing only at the equilibrium points of the circuit. Thus, all points in Z are potential attractors:
12 Example
13 Example Lyapunov Function V a a T Wa –f 1– u ud 0 a i i1= S b T a –+=
14 Example Network Equations
15 Lyapunov Function and Trajectory a 1 a 2 a 2 a 1 V(a)V(a)
16 Time Response tt a 1 a 2 V(a)V(a)
17 Convergence to a Saddle Point a 1 a 2
18 Hopfield Attractors V a 1 V a 2 V... a S V T 0 == The potential attractors of the Hopfield network satisfy: How are these points related to the minima of V(a)? The minima must satisfy: Where the Lyapunov function is given by: V a a T Wa – f 1– u ud 0 a i i1= S b T a –+=
19 Hopfield Attractors Using previous results, we can show that: The ith element of the gradient is therefore: a i V a – td dn i – td d f 1– a i () – a i d d f 1– a i td da i === Since the transfer function and its inverse are monotonic increasing: All points for whichwill also satisfy Therefore all attractors will be stationary points of V(a).
20 Effect of Gain n a
21 Lyapunov Function V a a T Wa – f 1– u ud 0 a i i1= S b T a –+= 1.4= 0.14= 14= a f 1– u ud 0 a i 2 --- a i cos log 4 a i coslog–== 4 a coslog–
22 High Gain Lyapunov Function where As the Lyapunov function reduces to: The high gain Lyapunov function is quadratic:
23 Example a 1 a 2 a 2 a 1 V(a)V(a)