Design And Performance Analysis Of And Gate Using Synaptic Inputs For Neural Network Application

The objective of the neural network is to transform the input to meaningful output. Neural networks are often used for statistical analysis and data modeling. Neural network has many uses in data processing, robotics, and medical diagnosis [2]. From the starting of the neural network there are various types found, but each and every types has some advantages and disadvantages. Deep learning and -neural network software are the categories of artificial neural network. The parallel process also allows ANNs to process the large amount of data very efficiently. The artificial neural network is built with a systematic

The following steps are used to design the back propagation neural network algorithm for the proposed research work. The first step is to set the input, output data sets. The second step is to set the number of hidden layer and output activation functions. The third step is to set the training functions and training parameters, finally run the network.

The training is divided into two phases: learning phase and testing phase. In the learning phase, an iterative which updated the synoptic weights is formed upon the error BP (Back Propagation) algorithm. In the testing phase the number of input and output parameters as well as the cases number influenced the neural network,whereas the trained results is then compared to the target to make a decision about the continuing of the iteration or the obtained results is concluded. The common ANN structure for the three architectures is (3X3), which means three neurons in the input layer and three neurons in the hidden layer. The training of each ANN architecture designs are shown in the following: fig.3, fig.4 and fig.5,

Within the human anatomy, an intricate and complex network of specialised nerve fibres and neurons works in collaboration with the central nervous system and peripheral system, designed to carry out the various actions humans perform every day. The nervous system is also known as the master control unit of the human body, as it operates other major functions such as the circulatory and respiratory systems (Jakab, 2006). It is composed of the central nervous system (CNS) and the peripheral nervous system (PNS). The neurons established within the various sections of the nervous system, is structured with three main parts: a dendrite which is a cluster of branches that operates by receiving information from the

There are a multitude of neurons in our bodies that are continuously communicating with each other to help us perform everyday tasks.  These communications are a way for the neurons to transmit information between one another.  This information is generally related to the physical actions and feelings which the body performs.  Neurons allow us to feel pain and other sensations which would

The neural network is a powerful mathematical method that is capable of representing complex non-linear functions cite{RLStateOfArt_ch10} which has been used widely in machine learning applications. Figure

First, we have encountered one major problem that is how to interpret a neural network given its black box characteristics. We really wanted to try ourselves, giving interpretation of our results so that we dug into the existing literature and found out a very interesting research paper written by Garson in 1991. In « Illuminating the black box: a randomization approach for understanding variable contributions in artificial neural networks », Olden and al. describes Garson’s algorithm very concisely so that we could create a user-defined function on Python that replicates the method. The interpretation of the method is provided below. The outputs of the different algorithms in the context of our study:

First, the ELM was proposed for the single hidden layer feedforward neural network (SLFN), which was then changed to single hidden layer feedforward network, since the hidden nodes

Abstract: This paper presents hardware efficient Delta Sigma linear processing circuits for the next generation low power VLSI device in the Internet-of-things (IoT). We first propose the P-N pair method to manipulate both the analog value and length of a first-order Delta Sigma bit sequence. We then present a binary counter method. Based on these methods, we develop Delta Sigma domain on-the-fly digital-signal-processing circuits: the Delta Sigma sum adder, average adder, and coefficient multiplier. The counter-based average adder can work with both first-order and higher-order Delta Sigma modulators and can also be used as a coefficient multiplier. The functionalities of the proposed circuits are verified by Matlab simulation and FPGA implementation. We also compare the area and power between the proposed Delta Sigma adders and a conventional multi-bit adder by synthesizing both circuits in the IBM 0.18 µm technology. Synthesis results show that the proposed Delta Sigma processing circuits can extensively reduce circuit area and power. With 100 inputs, a Delta Sigma average adder saves 94% of the silicon area and 96% of the power compared to a multi-bit binary adder. The proposed circuits have the potential to be widely used in future miniaturized low power VLSI circuits.

Neural technology is a field of engineering that specializes in taking information that is present in the brain and translating it to a medium that can be understood by a wide range of people. One of the ways this is done is with systems that take information directly from the brain and enable control over a computerized system. These are referred to as brain computer interfaces, also known as BCIs. Brain-computer interface (BCI) technology decodes neural signals in real time to control external devices (Rouse). With many varying potential applications, it is possible to see BCIs applied to many aspects of everyday life. This could include- but is not limited to- limb replacement, advanced computer systems, and brain monitoring.

Artificial neural network was combined with the genetic algorithm to get the more optimized prediction . An improved technique that uses artificial neural network with photovoltaic system was proposed by Isa et al.that utilizes perceptron model with Levenberg Marquardt algorithm. Apart from neural network Fuzzy logic has also been being used in weather prediction models. The rainfall was classified into three fuzzy sets which can be predicted by making use of simple fuzzy rules . Also a fuzzy self-regression model was proposed by Lu Feng and Xu xiao Guang which makes use of the form of self-related sequence number according to observed number. The self-related coefficients were computed by making use of Fuzzy Logic . A combined approach of neural network with Fuzzy Logic is being proposed for the weather prediction system. The work has applied principle component analysis technique to the fuzzy data by making use of Autoassociative neural networks.

FSW) and Artificial neural networks (ANN) are two well known approaches in their respective field. FSW is a well known method in material sciences and ANN in computer science. The aim is to combine these two approaches to get some important results.

It has been seen that algorithm can improve the memory bandwidth. Here the accelerator can be used in hardware design to improve the memory efficiency. In recent year, the hardware architecture for deep learning employed the GPU to increase the speed. Next it moved to FPGA and then latest one is ASIC with extra unit. the Application-specific integrated circuit (AISC) is integrated circuit which is used to developing hardware to solve a problem by building gates to emulate the logic. The purpose of the chips to provide maximum performance at given power and cost budget. ASIC provide some sort of software engine to run deep learning algorithm to optimize performance power and memory. The different of component of hardware

Abstract—This Paper includes the development of domino CMOS technology for the design of XOR gate. Low power dissipation is one of the main design considerations for high level performance circuits. The leakage power dissipation is controlled by the factor gate oxide leakage and threshold leakage and thus the overall leakage of domino XOR circuits. To show the efficiency of the proposed model, a simple example like implementing of XOR gate with P type domino XOR, N type domino XOR gate and PN mixed domino XOR gate, an average power dissipation reduced up to 66.15% and propagation delay is 46.66%

Extreme learning machine proposed by\cite{elm,elms} is a feed forward neural network classifier with single hidden layer in which the weights between input and hidden layer are initialized randomly. ELM uses analytical approach to compute weights between hidden and output layer\cite{elm} ,which