chapter(13.( neurodynamicschapter(13.(neurodynamics neural’networks’and’learning’machines’...
TRANSCRIPT
![Page 1: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/1.jpg)
Chapter 13. Neurodynamics
Neural Networks and Learning Machines (Haykin)
2019 Lecture Notes on Self-‐learning Neural Algorithms
Byoung-‐Tak ZhangSchool of Computer Science and Engineering
Seoul National University
Version 20171109/20191028/20191104
![Page 2: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/2.jpg)
Contents
13.1 Introduction ……………………………………………………..…………………………….... 313.2 Dynamic Systems ……………………………………………….…….………………..…. 513.3 Stability of Equilibrium States …………………………....………………….…….... 813.4 Attractors ……….………..………………….……………………………………..………..... 1313.5 Neurodynamic Models ……………………………..…………………………...…...…. 1413.6 Attractors and Recurrent Networks ….……..……..…….…….……………….. 1813.7 Hopfield Model ….……………………………………..……..…….……….………….. 1913.8 Cohen-‐Grossberg Theorem ……………….…………..………….………….....……. 3113.9 Brain-‐State-‐In-‐A-‐Box Model ……………………….……..…......................…. 33Summary and Discussion …………….…………….………………………….……………... 37
(c) 2017 Biointelligence Lab, SNU 2
![Page 3: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/3.jpg)
(c) 2017 Biointelligence Lab, SNU 3
13.1 Introduction (1/2)
• Time plays a critical role in learning. Two ways in which time manifests itself in the learning process:1. A static neural network (NN) is made into a dynamic mapper by stimulating
it via a memory structure, short term or long term.2. Time is built into the operation of a neural network through the use of
feedback.• Two ways of applying feedback in NNs:
1. Local feedback, which is applied to a single neuron inside the network;2. Global feedback, which encompasses one or more layers of hidden
neurons—or better still, the whole network.• Feedback is like a double-‐edged sword in that when it is applied
improperly, it can produce harmful effects. In particular, the application of feedback can cause a system that is originally stable to become unstable. Our primary interest in this chapter is in the stability of recurrent networks.
• The subject of neural networks viewed as nonlinear dynamic systems, with particular emphasis on the stability problem, is referred to as neurodynamics.
![Page 4: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/4.jpg)
(c) 2017 Biointelligence Lab, SNU 4
13.1 Introduction (2/2)
• An important feature of the stability (or instability) of a nonlinear dynamic system is that it is a property of the whole system. – The presence of stability always implies some form of
coordination between the individual parts of the system.• The study of neurodynamics may follow one of two routes,
depending on the application of interest:– Deterministic neurodynamics, in which the neural network
model has a deterministic behavior. Described by a set of nonlinear differential equations è This chapter.
– Statistical neurodynamics, in which the neural network model is perturbed by the presence of noise. Described by stochastic nonlinear differential equations, thereby expressing the solution in probabilistic terms.
![Page 5: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/5.jpg)
(c) 2017 Biointelligence Lab, SNU 5
13.2 Dynamic Systems (1/3)
A dynamic system is a system whose state varies with time.
( ) ( )( ) , = 1, 2, ..., j j jd x t F x t j Ndt
=
( ) ( ) ( ) ( )1 2[ , , ... , ]TNt x t x t x t=x
( ) ( )( )d t tdt
=x F x
Figure 13.1 A two-‐dimensional trajectory (orbit) of a dynamic system.
velocity vector fieldor vector field
![Page 6: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/6.jpg)
(c) 2017 Biointelligence Lab, SNU 6
13.2 Dynamic Systems (2/3)
Figure 13.2 A two-‐dimensional state (phase) portrait of a dynamic system.
Figure 13.3 A two-‐dimensional vector field of a dynamic system.
![Page 7: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/7.jpg)
(c) 2017 Biointelligence Lab, SNU 7
13.2 Dynamic Systems (3/3)
( ) ( ) K− ≤ −F x F u x u
M
x x.
x u
Lipschitz condition
Let denote the norm, or Euclidean length, of the vector
Let and be a pair of vectors in an open set in a noraml vector (state) space.Then, acco K Mx urding to the Lipschitz condition, there exists a constant for all and in .
( ( ) ) S ( ( ))⋅ = ∇ ⋅∫ ∫S V
d dVF x n F x
If the divergence ( ) (which is a scalar) is zero,the system is conservative and if it is negative the system is dissipative
∇ ⋅ , , .
F x
Divergence Theorem
Volume integral of the divergence of F(x)
Surface integral of the outwardly directed normal component of F(x)Net flux flowing out of the region surrounded by the closed surface S
![Page 8: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/8.jpg)
(c) 2017 Biointelligence Lab, SNU 8
13.3 Stability of Equilibrium States (1/6)
Table 13.1 ( ) =F x 0
( ) = + ( )t tΔx x x
( ) + ( )t≈ ΔF x x A x
= ( ) | =∂∂
x xA F xx
( ) ( )d t tdt
Δ ≈ Δx A x
Jacobian
Taylor series expansion
Equilibrium state
![Page 9: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/9.jpg)
(c) 2017 Biointelligence Lab, SNU 9
13.3 Stability of Equilibrium States (2/6)Figure 13.4 (a) Stable node. (b) Stable focus. (c) Unstable node. (d) Unstable focus. (e) Saddle point. (f) Center.
![Page 10: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/10.jpg)
(c) 2017 Biointelligence Lab, SNU 10
13.3 Stability of Equilibrium States (3/6)
Lyapunov’s Theorems
The equilibrium state is stable if, in a small neighborhood ofthere exists a positive - definite function such that its derivative with respect to time is negative semidefinite in t
VTheorem1. x x,
(x) hat region.
The equilibrium state is asymptotically stable if, in a small neighborhood of , there exists a positive - definite function such that its derivative with respect to time is negative de
VTheorem2. x
x (x)finite in that region.
![Page 11: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/11.jpg)
(c) 2017 Biointelligence Lab, SNU 11
13.3 Stability of Equilibrium States (5/6)
( ) 0 for x≤ ∈ −d V udt
x x
According to Theorem 1,
( ) < 0 for x∈ −d V udt
x x
According to Theorem 2,
( ) ( )
. ( ) = 0
VV
V
xx
xx
Requirement :The Lyapunov function to be a positive -‐ definite function1. The function has continous partial derivatives with respect to the elements of the state2. .
( ) > 0 - .∈V u ux x x x3. if where is a small neighborhood around
![Page 12: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/12.jpg)
(c) 2017 Biointelligence Lab, SNU 12
13.3 Stability of Equilibrium States (6/6)
1 2 3c < <
xc c cFigure 13.6 Lyapunov surfaces for decreasing value of constant , with . The equilibribum state
is denoted by the point .
![Page 13: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/13.jpg)
(c) 2017 Biointelligence Lab, SNU 13
13.4 Attractors• A k-‐dimensional surface embedded in the N-‐dimensional state space,
which is defined by the set of equations
• These manifolds are called attractors in that they are bounded subsets to which regions of initial conditions of a nonzero state-‐space volume converge as time t increases.
( )1 2
1, 2, ... , , , ... , 0,
=⎧
= ⎨ <⎩j N
j kM x x x
k N
Figure 13.7 Illustration of the notion of a basin of attraction and the idea of a separatrix.
-‐ Point attractors-‐ Limit cycle-‐ Basin (domain) of attraction-‐ Separatrix-‐ Hyperbolic attractor
![Page 14: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/14.jpg)
(c) 2017 Biointelligence Lab, SNU 14
13.5 Neurodynamic Models (1/4)
• General properties of the neurodynamic systems1. A large number of degrees of freedom
The human cortex is a highly parallel, distributed system that is estimated to possess about 10 billion neurons, with each neuron modeled by one or more state variables. The system is characterized by a very large number of coupling constants represented by the strengths (efficacies) of the individual synaptic junctions.
2. NonlinearityA neurodynamic system is inherently nonlinear. In fact, nonlinearity is essential for creating a universal computing machine.
3. DissipationA neurodynamic system is dissipative. It is therefore characterized by the convergence of the state-‐space volume onto a manifold of lower dimensionality as time goes on.
4. NoiseFinally, noise is an intrinsic characteristic of neurodynamic systems. In real-‐life neurons, membrane noise is generated at synaptic junctions
![Page 15: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/15.jpg)
(c) 2017 Biointelligence Lab, SNU 15
13.5 Neurodynamic Models (2/4)
Figure 13.8 Additive model of a neuron, labeled j.
![Page 16: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/16.jpg)
(c) 2017 Biointelligence Lab, SNU 16
13.5 Neurodynamic Models (3/4)
( ) ( ) ( )1
Nj
j ji i jij
jdv v tC w x t I
dtt R =
+ = +∑
( ) ( )( )j jx t v tϕ=
( ) ( ) ( ) ,1
= 1, 2, ..., N
j jj ji i j
ij
dv t v tC w x t I j N
dt R =
= − + +∑
( ) ( )1φ , = 1, 2, ...,
1 + expjj
v j Nv
=−
Additive model
Flowing away Flowing toward
Cj: leakage capacitanceRj: leakage resistance
wji: conductancexi: potential
I = V/R (Kirchoff’s law)
![Page 17: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/17.jpg)
(c) 2017 Biointelligence Lab, SNU 17
13.5 Neurodynamic Models (4/4)
( ) ( ) ( )( ) = φ , = 1, 2, ..., jj ji i j
i
dv tv t w v t I j N
dt− + +∑
( ) ( ) ( )jdx t = x t φ x t , = 1, 2, ...,
dt j ji i jiw K j N⎛ ⎞− + +⎜ ⎟⎝ ⎠
∑
Related model
( ) ( ) = k kj jj
v t w x t∑ = k kj j
jI w K∑
Normalizing wji and Ijwrt Rj ( ) ( )( )j jx t v tϕ=cf:
[Pineda, 1987]
tauj = RjCj
![Page 18: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/18.jpg)
(c) 2017 Biointelligence Lab, SNU18
13.6 Manipulation of Attractors as Recurrent Network Paradigm
• A neurodynamic model can have complicated attractor structures and may therefore exhibit useful computational capabilities.
• The identification of attractors with computational objects is one of the foundations of neural network paradigms.
• One way in which the collective properties of a neural network may be used to implement a computational task is by way of the concept of energy minimization.
• The Hopfield network and brain-‐state-‐in-‐a-‐box model are examples of an associative memory with no hidden neurons; an associative memory is an important resource for intelligent behavior. Another neurodynamic model is that of an input–output mapper, the operation of which relies on the availability of hidden neurons.
![Page 19: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/19.jpg)
(c) 2017 Biointelligence Lab, SNU 19
13.7 Hopfield Model (1/12)
• The Hopfield network (model) consists of a set of neurons and a corresponding set of unit-‐time delays, forming a multiple-‐loop feedback system.
Figure 13.9 Architectural graph of a Hopfield network consisting of N = 4 neurons.
1 1
12
N N
ji i ji ji j
E w x x= =≠
= − ∑∑
1
N
j ji i ji
v w x b=
= +∑
( ) 1 exp( ) φ = tanh2 1 exp( )i i
ii
a v a vx va v
− −⎛ ⎞= =⎜ ⎟ + −⎝ ⎠
![Page 20: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/20.jpg)
(c) 2017 Biointelligence Lab, SNU 20
13.7 Hopfield Model (2/12)
• Dynamics of the Hopfield network
• To study the stability of this system of differential equations, we make three assumptions:– The matrix of synaptic weights is symmetric
– Each neuron has a nonlinear activation of its own– The inverse of the nonlinear activation function exists
for all and ji ijw w i j=( )1φiv x−=
( ) 1 exp( ) φ = tanh2 1 exp( )i i
ii
a v a vx va v
− −⎛ ⎞= =⎜ ⎟ + −⎝ ⎠
( ) ( ) ( )( )1
= φ , = 1, ... , N
jj j ji i i j
ij
v tdC v t w v t I j Ndt R =
− + +∑
![Page 21: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/21.jpg)
21
13.7 Hopfield Model (3/12)
φ2i i
v oa d
dv ==
( )1 1 1φ log1i
i
xv xa x
− −⎛ ⎞= = − ⎜ ⎟+⎝ ⎠
( )1 1φ log1ixxx
− −⎛ ⎞= − ⎜ ⎟+⎝ ⎠
( ) ( )1 11φ φii
x xa
− −=
( )1
01 1 1 1
1 1 φ2
jN N N Nx
ji i j j j ji j j jj
E w x x x dx I xR
−
= = = =
= − + −∑∑ ∑ ∑∫
1 1
N Nj j
ji i jj i j
v dxdE w x Idt R dt= =
⎛ ⎞= − − +⎜ ⎟⎜ ⎟⎝ ⎠∑ ∑
Figure 13.10 Plots of (a) the standard sigmoidal nonlinearity, and (b) its inverse.
è
Energy function of the Hopfield network
Differentiating E wrt t
![Page 22: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/22.jpg)
22
13.7 Hopfield Model (4/12)
1
Nj j
jj
dv dxdE Cdt dt dt=
⎛ ⎞= − ⎜ ⎟
⎝ ⎠∑
( ) ( )2
1 1
1 1φ φ
N Nj j
j j j j j jj j j
dx dxdE d dC x C xdt dt dt dt dx
− −
= =
⎡ ⎤⎛ ⎞⎡ ⎤= − = − ⎢ ⎥⎜ ⎟⎢ ⎥⎣ ⎦ ⎢ ⎥⎝ ⎠ ⎣ ⎦∑ ∑
( )1φ 0 for all j j jj
d x xdx
− ≥2
0 for all jj
dxx
dt⎛ ⎞
≥⎜ ⎟⎝ ⎠
( ) ( ) ( )( )1
= φ , = 1, ... , N
jj j ji i i j
ij
v tdC v t w v t I j Ndt R =
− + +∑1 1
N Nj j
ji i jj i j
v dxdE w x Idt R dt= =
⎛ ⎞= − − +⎜ ⎟⎜ ⎟⎝ ⎠∑ ∑
Note:
( )1 1 1φ log1i
i
xv xa x
− −⎛ ⎞= = − ⎜ ⎟+⎝ ⎠
dph/dt= dph/dx dx/dt
𝑑𝐸𝑑𝑡
≤ 0 for all 𝑡
è
è
1. The energy function E is a Lyapunov function of the continuous Hopfield model.
2. The model is stable in accordance with Lyapunov’s theorem 1.
![Page 23: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/23.jpg)
(c) 2017 Biointelligence Lab, SNU 23
13.7 Hopfield Model (5/12)
< 0 except at a fixed pointdEdt
• The (Lyapunov) energy function E of a Hopfield network is a monotonically decreasing function of time.
• Accordingly, the Hopfield network is asymptotically stable in the Lyapunov sense; the attractor fixed points are the minima of the energy function, and vice versa.
Figure 13.12 An energy contour map for a two-‐neuron, two-‐stable-‐state system. The ordinate and abscissa are the outputs of the two neurons. Stable states are located near the lower left and upper right corners, and unstable extrema are located at the other two corners. The arrows show the motion of the state. This motion is not generally perpendicular to the energy contours.
![Page 24: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/24.jpg)
(c) 2017 BiointelligenceLab, SNU 24
13.7 Hopfield Model (6/12)
( )φ 0 0j =
( )1
01 1 1
1 1 φ 2
jN N N x
ji i j ji j j ji j
E w x x x dxR
−
= = =≠
= − +∑∑ ∑ ∫
( )1
01 1 1
1 1 φ2
jN N N x
ji i ji j j j ji j
E w x x x dxa R
−
= = =≠
= − +∑∑ ∑ ∫
1. The output of neuron j has the asymptotic values
2. The midpoint of the activation function of the neuron lies at the origin
1 for
1 for j
jj
vx
v+ = ∞⎧⎪= ⎨− = −∞⎪⎩
1 1
12
N N
ji i ji ji j
E w x x= =≠
= − ∑∑
Figure 13.11 Plot of the integral
( ) ( )1 11φ φii
x xa
− −=
If gain 𝑎𝑗 → ∞, the second term goes to 0, and the continuous Hopfield model becomes the discrete Hopfield model
for discrete Hopfield model
![Page 25: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/25.jpg)
(c) 2017 Biointelligence Lab, SNU 25
13.7 Hopfield Model (7/12)
The Discrete Hopfield Model as a Content-‐Addressable Memory
1
N
j ji i ji
v w x b=
= +∑• The induced local field vj of neuron j is defined by
where bj is a fixed bias applied externally to neuron j. Hence, neuron j modifies its state xj according to the deterministic rule
1 if for 0
1 if for 0j
jj
vx
v+ >⎧⎪= ⎨− <⎪⎩
• This relation may be rewritten in the compact form sgn(v )j jx =
• Energy function1 1
12
N N
ji i ji ji j
E w x x= =≠
= − ∑∑
![Page 26: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/26.jpg)
(c) 2017 Biointelligence Lab, SNU 26
13.7 Hopfield Model (8/12)
The Discrete Hopfield Model as a Content-‐Addressable MemoryStorage of samples (= learning)
– According to the outer-‐product rule of storage—that is, the generalization of Hebb’s postulate of learning—the synaptic weight from neuron i to neuron j is defined by
, ,1
1 M
ji j iwN µ µ
µ=
= ξ ξ∑
0 for all iiw i=
Figure 13.13 Illustration of the encoding–decoding performed by a recurrent network.
![Page 27: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/27.jpg)
13.7 Hopfield Model (9/12)
(c) 2017 Biointelligence Lab, SNU 27
The Discrete Hopfield Model as a Content-‐Addressable Memory1. Storage Phase
– The output of each neuron in the network is fed back to all other neurons.– There is no self-‐feedback in the network (i.e.,wii = 0).– The weight matrix of the network is symmetric, as shown by the following
relation
2. Retrieval Phase
1
1 M
MN µ µ
µξ ξ Τ
=
= −∑W Ι
Τ =W W
, j = 1, 2, …, N1
sgnN
j ji i ji
y w y b=
⎛ ⎞= +⎜ ⎟⎝ ⎠∑
sgn( )= +y Wy b
![Page 28: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/28.jpg)
13.7 Hopfield Model (10/12)
28
![Page 29: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/29.jpg)
13.7 Hopfield Model (11/12)
(c) 2017 Biointelligence Lab, SNU 29
Figure 13.14 (a) Architectural graph of Hopfield network for N = 3 neurons. (b) Diagram depicting the two stable states and flow of the network.
, j = 1, 2, …, N( )( ) ( )j j jd x t F x tdt
=
![Page 30: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/30.jpg)
13.7 Hopfield Model (12/12)
(c) 2017 Biointelligence Lab, SNU 30
Spurious States• An eigenanalysis of the weight matrix W leads us to take the following
viewpoint of the discrete Hopfield network used as a content-‐addressable memory1. The discrete Hopfield network acts as a vector projector in the sense that it
projects a probe onto a subspace spanned by the fundamental memory vectors.
2. The underlying dynamics of the network drive the resulting projected vector to one of the corners of a unit hypercube where the energy function is minimized.
• Tradeoff between two conflicting requirements:1. The need to preserve the fundamental memory vectors as fixed points in the
state space.2. The desire to have few spurious states.
![Page 31: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/31.jpg)
13.8 The Cohen-‐Grossberg Theorem (1/2)
(c) 2017 Biointelligence Lab, SNU 31
, j = 1, 2, …, N1
( ) ( ) ( )N
j j j j j ji i ii
d u a u b u c udt
ϕ=
⎡ ⎤= −⎢ ⎥⎣ ⎦∑
01 1 1
1 ( ) ( ) ( ) ( )2
jN N N u
ji i i j j j ji j j
E c u u b dϕ ϕ λ ϕ λ λ= = =
′= −∑∑ ∑∫
ij jic c=
( ) 0j ja u ≥
(u ) ( ) 0j j j jj
d udu
ϕ ϕ′ = ≥
Symmetricity
Nonnegativity
Monotonicity
A general principle for assessing the stability of a certain class of neural networks:
which admits a Lyapunov function:
if the following three conditions hold:
![Page 32: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/32.jpg)
(c) 2017 Biointelligence Lab, SNU 32
13.8 The Cohen-‐Grossberg Theorem (2/2)
01 1 1
1 ( ) ( ) ( )2
jN N N v j
ji i i j j j ji j j j
vE w v v I v dv
Rϕ ϕ ϕ
= = =
⎛ ⎞′= − + −⎜ ⎟⎜ ⎟⎝ ⎠
∑∑ ∑∫𝑑𝐸𝑑𝑡
≤ 0
Cohen–Grossberg Theorem
, j = 1, 2, …, N1
( ) ( ) ( )N
j j j j j ji i ii
d u a u b u c udt
ϕ=
⎡ ⎤= −⎢ ⎥⎣ ⎦∑
( ) ( ) ( ) ,1
= 1, 2, ..., N
j jj ji i j
ij
dv t v tC w x t I j N
dt R =
= − + +∑
Note:
![Page 33: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/33.jpg)
(c) 2017 Biointelligence Lab, SNU 33
Figure 13.15 (a) Block diagram of the brain-‐state-‐in-‐a-‐box (BSB) model. (b) Signal-‐flow graph of the linear associator represented by the weight matrix W.
13.9 Brain-‐State-‐in-‐a-‐Box Model (1/4)
( ) ( ) ( )n n nβ= +y x Wx
( 1) ( ( ))n nϕ+ =x y
1 if ( ) 1( 1) ( ( )) ( ) if 1 ( ) 1
1 if ( ) 1
j
j j i i
i
y nx n y n y n y n
y nϕ
+ > +⎧⎪+ = = − ≤ ≤ +⎨⎪ − < −⎩
![Page 34: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/34.jpg)
(c) 2017 Biointelligence Lab, SNU 34
BSB ModelFigure 13.16 Piecewise-‐linear activation function used in the BSB model.
13.9 Brain-‐State-‐in-‐a-‐Box Model (2/4)
1( 1) ( ) , 1, 2, ,
N
j ji ii
x n c x n j Nϕ=
⎛ ⎞+ = =⎜ ⎟⎝ ⎠∑ K
ji ji jic wδ β= +
1( ) ( ) ( ) , 1, 2, ,
N
j j ji ii
d x t x t c x t j Ndt
ϕ=
⎛ ⎞= − + =⎜ ⎟⎝ ⎠∑ K
1( ) ( )
N
j ji ii
x t c v t=
=∑1
( ) ( )N
j ji ii
v t c x t=
=∑
1( ) ( ) ( ( )), 1, 2, ,
N
j j ji ii
d v t v t c v t j Ndt
ϕ=
= − + =∑ K
Continuous form
Equivalent form
To transform this into the additive model, we introduce
![Page 35: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/35.jpg)
35
Lyapunov (Energy) Function of BSB
13.9 Brain-‐State-‐in-‐a-‐Box Model (3/4)
1 12 2
N N
ji j ii j
E w x xβ β Τ
= =
= − = −∑∑ x Wx
01 1 1
1 ( ) ( ) ( )2
jN N N v
ji i ji j j
E c v v v v dvϕ ϕ ϕ= = =
′= − +∑∑ ∑∫
Dynamics of the BSB Model• It can be demonstrated that the BSB model is a gradient descent algorithm that
minimizes the energy function E.• The equilibrium states of the BSB model are defined by certain corners of the unit
huypercube and its orgin.• For every corner to serve as a possible equilibrium sate of BSB, the weight matrix W
should be diagonal dominant, which means that• For an equilibrium state to be stable, i.e. for a certain corner of the unit hypercube to be
a fixed point attractor, the weight matrix W should be strongly diagonal dominant:
w for 1,2, ,jj iji j
w j N≠
≥ =∑ K
w + for 1,2, ,jj iji j
w j Nα≠
≥ =∑ K
![Page 36: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/36.jpg)
(c) 2017 Biointelligence Lab, SNU 36
Clustering
13.9 Brain-‐State-‐in-‐a-‐Box Model (4/4)
Figure 13.17 Illustrative example of a two-‐neuron BSB model, operating under four different initial conditions:• the four shaded areas of the figure represent the model’s basins of attraction;• the corresponding trajectories of the model are plotted in blue;• the four corners, where the trajectories terminate, are printed as black dots.
![Page 37: Chapter(13.( NeurodynamicsChapter(13.(Neurodynamics Neural’Networks’and’Learning’Machines’ (Haykin) 2019Lecture(Notes(on(SelfAlearning(NeuralAlgorithms ByoungATak(Zhang Contents](https://reader034.vdocuments.us/reader034/viewer/2022042806/5f746322e2e9e43294254aed/html5/thumbnails/37.jpg)
Summary and Discussion
(c) 2017 BiointelligenceLab, SNU 37
l Dynamic Systems• Stability, Liapunov functions• Attractors
l Neurodynamic Models• Additive model• Related model
l Hopfield Model (Discrete)• Recurrent network (associative memory)• Liapunov (energy) function• Content-addressable memory
l BSB Model• Liapunov function• Clustering