written 3.6 years ago by |
(i) ANFIS:
For simplicity, we assume the fuzzy inference system under consideration has two inputs x and y and one output z.
Suppose that the rule base contains two fuzzy it..then rules of Takegi and Sugeno's type:
Rule 1: If x is $A_1$and y is$B_1$ , then
$f_1=p_1x+q_1y+r_1$
Rule 2: If x $A_2$is and y is $B_2$ , then
$f_2=p_2x+q_2y+r_2$
Depending on the two rule ANFIS architecture is as follows:
Layer 1:
Every node i in this layer is a square node with a node function
$O_i^1=\mu_{Ai}(x)$
where x is the input to node i, and Ai is the linguistic label (small,large etc) associated with this node function
Layer 2:
Every node in this layer is a circle node labeled π which multiplies the incoming signals and send the product out. For instance,
$w_i=\mu_{Ai}(x) \times i \mu_{Bi}(y); i=1,2,3..$
Each node output represents the firing strength of a rule.
Layer 3:
Every node in this layer is a circle node labeled N. The i th node calculates the ration of the i th rules firing strength to the sum of all rules firing strengths:
$\bar w_i=\frac{w_i}{w_2+w_2 };i=1,2,..$
For convenience, outputs of this layer will be called "Normalized firing strengths".
Layer 4:
Every node i in this layer is a square node with a node function
$O_i^4=\bar w_if_i=\bar w_i(p_ix+q_iy+r_i)$
where w¯iw¯i is the output of layer 3 and {pi,qi,ripi,qi,ri} is tha parameter set. Parameters in this layer will be referred to as consequent parameters.
Layer 5:
The single node in this layer is a circle node labeled ∑∑ that computes the overall output as the summation of all incoming signals i.e.
$O_i^5=$ overall output = $\sum_{i} w_if_i=\frac{\sum_{i}w_if_i}{\sum_{i}w_i}$
Thus we have constructed an adaptive network which is functionally equivalent to a Type-3 fuzzy inference system.
(ii) Brain state in box mode:
The "brain-state-in-box" sounds like we have a brain in a box without body. But the model is defined as follows:
Let W be a symmetric weight matrix whose largest eigenvalues have positive real components. In addition, W is required to be positive semi-definite, i.e., xTWx >= 0 for all x. Let x(0) denotes the initial state vector. The BSB algorithm is defined by the pair of equations:
$y(n) = x(n) + h Wx(n)\\ x(n+1) = f(y(n)).$
Or more concisely, the updating rule of the "brain state" x (a vector) is
$ x = f(x + h W x)$
where h is a small positive constant called the feedback factor. The f is a piecewise-linear function of the form
( f(x) = +1 \hspace{1cm} if\hspace{1cm} x > 1;\
f(x) = x \hspace{1cm} if \hspace{1cm}-1 < x < 1;\
f(x) = -1 \hspace{1cm} if \hspace{1cm}x < -1.)
When the W is choosing with the required property (positivity of largest eigenvalues), the effect of the algorithm is to drive the system for components of x to binary values +1 or 1 for each of the neuron. We can view it as a mapping from continuous inputs x(0) to discrete binary outputs. The final states are of the form (-1,+1,-1,-1,+1,+1, ..., +1). This represents a corner of cube in an N-dimensional space of linear size 2, centered at origin. This is the box of the brain-state-in "a box". The dynamics is such that the state moves to the wall of the box and then drives to the corner of the box.
Application of BSB model
What is a good use of BSB model? A natural application for the BSB model is clustering. Such as the classification of radar signals from the source of emitters. The matrix W has to be (unsupervised) learned using some of the methods discussed in early chapters.