Protocol Verification Using Finite State Machine Model:- The finite state machine is a mainly used in several protocol models with this technique, every protocol machine is always in a particular state at every time instant. Variables, including the program counter. From every state, there are zero or more possible transition to other states. When some event happens, transition take place. In case of a protocol machine, a transition might take place if a frame is transmitted, if a frame arrives, if a timer expires, if an interrupt takes place, etc. One particular state is designated as the initial state. This state corresponds to the description of the system when it starts running, or at some convenient starting place shortly thereafter. From the initial state, some, perhaps all, of the other states may be approached by a sequence of transition. this technique is called reachability analysis. This analysis can be helpful in determining whether a protocol is correct. All processes are

 Model and Hyper Parameters  Both Parameters ( model and hyper parameters) are very important. Model Parameter:- It is a configuration variable that is internal to the model and whose value can be estimated from the given data. * They are required by the model when making predictions. * Their values define the skill of the model on your problem. * They are estimated or learned from data. * They are often not set manually by the practitioner. * They are often saved as part of the learned model. Examples:- * The weights in an artificial neural network. * The support vectors in a support vector machine. * The coefficients in a linear regression or logistic regression. Hyper Parameter:- The parameters of the convolution layer which need to be set by the user. Period to the filler learning are called hyper parameters. Hyper Parameters are very important concepts in machine learning especially in the context of neural network since these types of models employ a variety of them. The most imp

 Some of the key design issues are listed below- 1. Every layer needs a mechanism for identifying transmitters and receivers. Because a network generally contain several computers, some form of addressing is needed in order to specify a specific computer. 2. Decision should be made about the rules for data transfer. Among the following three modes of data communication one may be selected. a) Simplex Communication:- Data only travels in one direction. For example, home television set. b) Half-duplex Communication:- Data can travel in either direction, but not simultaneously. For example, wireless. c) Full-duplex Communication:- Data travels in both directions at once. For example, telephonic conversation. The protocol must also determine about the number of logical channels per connection and about their priorities. 3. The layer should have some means for error detection and error correction. 4. The layer should have some mechanism for orderly Transfer of data, this involves the capabi

Layered Network Architecture Layering is a widely accepted structuring technique  in designing a communication system. A set of layers and protocols is called a network architecture. To reduce their design complexity, networks are organized as a series of layers, each one built on the layer below it. The number of layers, their contents and their functions varies from network to network. However, in all networks, the purpose of each layer is to offer certain services to the higher layers, protecting those layers from the implementation details of services. The communication between the two machines or parties is done by protocols. A protocols is defined as a set of rules governing the exchange of data between two separate entities or application programs. These conventions when standardized are called protocols. Violating the protocol will make communication more difficult, if not impossible. Advantages Layering reduces the design complexity of the network. In a layered architecture, e

 Back Propagation Back Propagation is the essence of neural net training. It is the practice of finetuning the weights of a neural net based on the error rate. obtained in the previous epoch. proper tuning of the weights ensures lower error rates, making the model model reliable by increasing its generalization. Advantages The computing time is minimized if the weights chosen are small at the beginning. The mathematical formula of back propagation can be applied to any network. Disadvantages It has more number of learning steps, and also the learning phase has intensive calculations. The training may sometimes cause temporal instability to  the system The network may get trapped in a local minima. Applications Data compression Image compression Face recognition Optical character recognition Control problems Non-linear simulation Fault detection problem Load forecasting problem https://rgpvnotesforcsestudents.blogspot.com/2021/03/neural-network-architecture.html https://rgpvnotesforcses

  Neural Network Architectures An artificial neural network is a data processing system consists of a large number of highly interconnected processing elements (artificial neural) in an architecture inspired by the human brain. An artificial neural network (ANN) is represented using digraph. On the basis of learning machanism, there are several classes of neural network. In general, we may identify Three fundamentaly different classes of network architectures. 1. Single Layer Feedforward Network:- There are two layers input layer and output layer, in Single Layer Feedforward Network. The input layer neurons receive the input signals and the output layer neurons receive the output signals. 2. Multilayer Feedforward Network:- the Multilayer Feedforward Network comprises of multiple layers. Thus, this type of Architecture besides processing an input and output layer also contain one or more intermediary layer known as hidden layers. 3. Recurrent Network:- A recurrent network distinguishes

 Activation Function:- An activation function is a very important feature of an artificial neural network, basically decide whether the neural should be activated or not.  In Artificial Neural Network, the activation function defines the output of that node given an input or set of inputs. Types of activation function:- Linear Function  Non-linear Function Binary Step Function The role of activation function in artificial neural  network:- The role of the activation function can be understood by an example, Suppose a person is carrying out same work. Some force or activation may be given to make the work more efficient and to get exact output. This activation aids in obtaining the exact output. In a similar manner the activation function is applied over the net input to determine the ANN output. Linear and Non-linear Function are:- Identity Function Binary Step Function Sigmoidal Function            a) Binary Sigmoidal Function            b) Bipolar Sigmoidal Function                 4