FPGA-based artificial neural network using CORDIC modules
3
Citation
0
Reference
10
Related Paper
Citation Trend
Abstract:
Artificial neural networks have been used in applications that require complex procedural algorithms and in systems which lack an analytical mathematic model. By designing a large network of computing nodes based on the artificial neuron model, new solutions can be developed for computational problems in fields such as image processing and speech recognition. Neural networks are inherently parallel since each neuron, or node, acts as an autonomous computational element. Artificial neural networks use a mathematical model for each node that processes information from other nodes in the same region. The information processing entails computing a weighted average computation followed by a nonlinear mathematical transformation. Some typical artificial neural network applications use the exponential function or trigonometric functions for the nonlinear transformation. Various simple artificial neural networks have been implemented using a processor to compute the output for each node sequentially. This approach uses sequential processing and does not take advantage of the parallelism of a complex artificial neural network. In this work a hardware-based approach is investigated for artificial neural network applications. A Field Programmable Gate Arrays (FPGAs) is used to implement an artificial neuron using hardware multipliers, adders and CORDIC functional units. In order to create a large scale artificial neural network, area efficient hardware units such as CORDIC units are needed. High performance and low cost bit serial CORDIC implementations are presented. Finally, the FPGA resources and the performance of a hardware-based artificial neuron are presented.Keywords:
CORDIC
Physical neural network
In order to measure the phase difference at high speed,using the analyzing solution in frequency domain,with the field programmable gate array(FPGA),the FFT transformation was finished.The coordinate rotation digital computer(CORDIC) algorithm was used to improve the performance of the FPGA.A new real-time phase difference measurement method was proposed.The simulation results show that accurate measurement result can be obtained at high speed.
CORDIC
Phase difference
Gate array
Cite
Citations (0)
This paper presents a neural-tuned neural network, which is trained by genetic algorithm (GA). The neural-tuned neural network consists of a neural network and a modified neural network. In the modified neural network, a neuron model with two activation functions is introduced. Some parameters of these activation functions is tuned by neural network. The proposed network structure can increase the search space of the network and gives better performance than traditional feedforward neural networks. Some application examples are given to illustrate the merits of the proposed network.
Feedforward neural network
Physical neural network
Cite
Citations (5)
Artificial neural network is the core of deep learning algorithms and the forefront of artificial intelligence. Its inspiration comes from neurons within the human brain. Artificial neural network mimics the way biological neurons transmit signals to each other. It can thus achieve the goal of learning experiences. This chapter introduces artificial neuron, perceptron and basic model of artificial neural network. Moreover, the chapter also introduces backpropagation neural network, Hopfield neural network, competitive neural network. Finally, deep neural network is introduced in the chapter. Five examples are given to show the working principle of artificial neural network. The programs for implementing the examples are also provided for better understanding the model of artificial neural network.
Physical neural network
Perceptron
Artificial neuron
Backpropagation
Cite
Citations (22)
The FPGA implementation of digital down convert based on the CORDIC algorithm is introduced.The method can also complete the NCO function and mixer function.The shortcoming such as occupying FPGA multiplier and a lot of resources of ROM,outputting spectrum spurious larger,can be overcoming.The article describes the principles of the CORDIC algorithm,and discusses the digital down-conversion architecture principle based on the CORDIC algorithm and the specific methods of the FPGA implementation.The method simulates filter and system for function and timing in the Quartus II and Modelsim platform.The test shows that the program correctly,and effectively save the FPGA hardware resources.
CORDIC
ModelSim
Spurious relationship
Cite
Citations (0)
In many pattern classification applications of artificial neural networks, the objects to be classified are represented by fixed sized 2-dimensional (or 1-dimensional) arrays of which the elements are the values of cells in a fixed sized 2-dimensional (or 1-dimensional) grid and the values of these elements are of the same type. For such problems, besides a general neural network structure, called an undistricted neural network, a districted neural network can be used to reduce the training complexity. A districted neural network consists of two levels of sub-neural networks, where each of the lower level sub-neural networks takes the elements in a region of the array as its inputs and outputs a temperate class label, while the higher level sub-neural network, uses the outputs of lower level sub-neural networks as inputs and derives the consensus label decision. We show, by using a simple model, that a districted neural network is more stable than an undistricted neural network. The conclusion is verified by experiments of using neural networks for face recognition.
Physical neural network
Cite
Citations (21)
Image recognition is one of the basic tasks of computer vision, and it is also one of the important research directions in the field of machine learning. The artificial neural network algorithm has achieved very remarkable results in image recognition, convolutional neural network is one of the most popular artificial neural network, it's also the main solution to image recognition currently. The spiking neural network is called the third-generation neural network, which is different from the previous generation of neural networks. Inspiring by neuroscience, spiking neural network try to build neural networks in a way closer to the human brain mechanism. Referring the application of artificial neural network in image recognition, we decide to use the convolutional neural network in image recognition, moreover, we combine the spiking neural network to construct a new neural network and try to apply it in the field of image classification.
Neocognitron
Physical neural network
Cellular neural network
Random neural network
Neural gas
Cite
Citations (1)
In this paper, a hidden node pruning algorithm based on the neural complexity is proposed, the entropy of neural network can be calculated by the standard covariance matrix of the neural network's connection matrix in the training stage, and the neural complexity can be acquired. In ensuring the information processing capacity of neural network is not reduced, select and delete the least important hidden node, and the simpler neural network architecture is achieved. It is not necessary to train the cost function of the neural network to a local minimal, and the pre-processing neural network weights is avoided before neural network architecture adjustment. The simulation results of the non-linear function approximation shows that the performance of the approximation is ensured and at the same time a simple architecture of neural networks can be achieved.
Feedforward neural network
Physical neural network
Pruning
Function Approximation
Cite
Citations (27)
본 논문에서는 움직이는 영상에 대해 물리적인 회전이 발생하였을 때, 빠른 보정을 처리하기 위해 회전된 영상의 회전 각도를 고속으로 처리하기 위한 ECP (Extreme Contour Point) 알고리즘의 FPGA (Field Programmable Gate Array) 하드웨어 설계를 최적화하였고, XC7Z020 xc7z020-3clg400 FPGA 보드와 xilinx 14.2 툴을 사용하여 검증하였다. 잘 알려진 각도 산출 알고리즘인 CORDIC (Coordinate Rotation Digital Integrated Computation)과 비교하여 4ns의 유사한 동작 속도 안에서 CORDIC 대비 Registers는 108%, Look Up Tables (LUTs)는 91% 감소하는 등 하드웨어 비용이 우수함을 확인하였다. In this Paper, we propose an optimized method of hardware design based on Field Programmable Gate Array (FPGA) to detect rotated angle of high definition image about Extreme Contour Point (ECP) algorithm with moving video image could be not happened to translation motion, but also physical rotation motion. It was evaluated by XC7Z020 xc7z020-3clg400 FPGA board by using xilinx 14.2 tool. The much well-known method, the Coordinate Rotation Digital Integrated Computation (CORDIC) is an algorithm to estimate rotated angle between point and point. Through the result both ECP and CORDIC, our proposed design are confirmed to have similar operating speed of about 4ns with CORDIC. However, it is verified to have high performance result in terms of the hardware cost, is much better than CORDIC with cost reduction of registers and Look Up Tables (LUTs) of 108% and 91%, respectively.
CORDIC
Gate array
Cite
Citations (0)
Many artificial neural network models (ANNs) have been proposed to mimic the human brain in solving problems involving human-like intelligence. An application of an artificial neural network approach for optical character recognition (OCR) is discussed in this paper. We examine a simple pattern-recognition system using an artificial neural network to simulate character recognition. A simple feedforward neural network model has been trained with different sets of noisy data. The backpropagation method is used for learning in the neural network.
Backpropagation
Feedforward neural network
Neocognitron
Physical neural network
Optical character recognition
Cite
Citations (46)
We find experimentally that when artificial neural networks are connected in parallel and trained together, they display the following properties. (i) When the parallel-connected neural network (PNN) is optimized, each sub-network in the connection is not optimized. (ii) The contribution of an inferior sub-network to the whole PNN can be on par with that of the superior sub-network. (iii) The PNN can output the correct result even when all sub-networks give incorrect results. These properties are unlikely for natural biological sense organs. Therefore, they could serve as a simple yet effective criterion for measuring the bionic level of neural networks. With this criterion, we further show that when serving as the activation function, the ReLU function can make an artificial neural network more bionic than the sigmoid and Tanh functions do.
Sigmoid function
Physical neural network
Activation function
Cite
Citations (0)