+1-415-670-9189

info@expertsmind.com

# Cooperative Process Assignment Help

###
Neural Networks - Cooperative Process
**Cooperative Process**

The winning neuron places the center of a topological neighborhood of cooperating neurons. Practically, a neuron that is firing tends to excite the neurons in its immediate neighborhood more than those farther away from this, which is intuitively satisfying. Such observation leads to make the topological neighborhood around the winning neuron i, decay smoothly along with lateral distance. To be exact let h_{j,i} indicate the topological neighborhood centered on winning neuron i, and encompassing a set of j or excited neurons. Assume d_{i,j} indicate the lateral distance between winning neuron i and excited neuron j. Then an assumption can be made that the topological neighborhood h_{j,i} is a uni-modal function of the lateral distance d_{j,i}, such that it satisfies two distinct needs as:

- The topological neighborhood h
_{j,i} is symmetric to the maximum point defined by d_{j,i} = 0; in other words it gets its maximum value at the winning neuron i, for which the distance d_{j,i} is zero.
- The amplitude of the topological neighborhood h
_{j,i} reduces monotonically along with the increasing lateral distance d_{j,i,} decaying to zero for d_{j,i} → ∞; it is necessary condition for convergence.

A typical choice of h_{j,i} such satisfies these needs is Gaussian function:

** h**_{ij(x)} = exp{-(d^{2}_{j,i})/2s^{2}}..............................Eqn(15)

This is translational invariant

The parameter σ is the "effective width" of topological neighborhood; this measures the degree to which excited neurons in the vicinity of the winning neuron participate in the learning method or process. This also makes the SOM algorithm converge faster than a rectangular topological neighborhood would.

For cooperation in between neighboring neurons to hold, this is essential that topological neighborhood be dependent on lateral distance between excited neuron j and winning neurons i in the output space quite than on some distance measure in the original output space. It is precisely what we have in Eq. 15. In case of one dimensional lattice, d_{i,j} is an integer equivalent to | i - j |. On the other hand, in case of a two dimensional lattice is explained by:

** d**^{2}= || r_{j} - r_{i} ||...................................Eqn(16)

Where the distance r_{j} shows the position of excited neuron j and r_{i} shows the discrete position of winning neuron i, both of this are measured in the discrete output space.

Other unique feature of the SOM algorithm is the size of the topological neighborhood shrinks along with time. It requirement is satisfied by making the width σ of the topological neighborhood function h_{i,j} decrease along with time. A popular alternative of the dependence of σ upon discrete time n is the exponential decay.

** s(n) = s**_{0} exp(-(n/ t_{1}))..............................Eqn(17)

Whereas σ_{0} is the value of σ at the initiation of the SOM algorithm and

And τ_{1} is a time constant.

Expertsmind’s world class education services

We at www.expertsmind.com offer email based assignment help – homework help and projects assistance from k-12 academic level to college and university level and management and engineering studies. Our experts are helping students in their studies and they offer instant tutoring assistance giving their best practiced knowledge and spreading their world class education services through e-Learning program.

- Quality assignment help assistance 24x7 hrs

- Best qualified tutor’s network

- Time on delivery

- Quality assurance before delivery

- 100% originality and fresh work

**Cooperative Process**

_{j,i}indicate the topological neighborhood centered on winning neuron i, and encompassing a set of j or excited neurons. Assume d

_{i,j}indicate the lateral distance between winning neuron i and excited neuron j. Then an assumption can be made that the topological neighborhood h

_{j,i}is a uni-modal function of the lateral distance d

_{j,i}, such that it satisfies two distinct needs as:

_{j,i}is symmetric to the maximum point defined by d_{j,i}= 0; in other words it gets its maximum value at the winning neuron i, for which the distance d_{j,i}is zero._{j,i}reduces monotonically along with the increasing lateral distance d_{j,i,}decaying to zero for d_{j,i}→ ∞; it is necessary condition for convergence._{j,i}such satisfies these needs is Gaussian function:

**h**

_{ij(x)}= exp{-(d^{2}_{j,i})/2s^{2}}..............................Eqn(15)_{i,j}is an integer equivalent to | i - j |. On the other hand, in case of a two dimensional lattice is explained by:

**d**

^{2}= || r_{j}- r_{i}||...................................Eqn(16)_{j}shows the position of excited neuron j and r

_{i}shows the discrete position of winning neuron i, both of this are measured in the discrete output space.

_{i,j}decrease along with time. A popular alternative of the dependence of σ upon discrete time n is the exponential decay.

**s(n) = s**

_{0}exp(-(n/ t_{1}))..............................Eqn(17)_{0}is the value of σ at the initiation of the SOM algorithm and

_{1}is a time constant.