The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Neural networks (NNs) have been widely used in microwave device modeling. One of the greatest challenges is how to speed up the model training process and reduce the development cost. To address the issue, this paper exploits FPGAs to accelerate NN training. Experimental results demonstrate that the model training time can be reduced by up to 99.1%, compared to the traditional software implementation.
This paper proposes a knowledge-based neural network (KBNN) modeling approach for field-programmable gate array (FPGA) logical architecture design. The KBNN embeds the existing FPGA analytical models (AMs) into an NN. The NN can complement the AMs according to their needs to provide further increased model accuracy, while maintaining the meaningful trends successfully captured in the AMs. The obtained...
Artificial neural network (ANN) modeling approach to analyze noise figure (NF) of the entire circuit is proposed for the first time. In the proposed technique, the effects of input and output matching networks on the circuit's NF are analyzed respectively. The neural network model is exploited to represent the relationship between matching networks and circuit's NF. Developed ANN model allows the...
We propose a neural network based approach for estimating the total wirelength of a digital circuit, mapped onto an FPGA, before circuit placement and routing. A 3-layer MLP neural network is trained to learn the behavior of a placement tool and then quickly predicts the wirelength of a circuit design with the accuracy similar to one obtained after placement. A priori knowledge about the wirelength...
In this paper, an advanced Neuro-Space Mapping (SM) modeling technique for nonlinear device modeling is proposed. By neural network mapping of the voltage and current signals from the coarse to the fine models, Neuro-SM can modify the behavior of the coarse model to match that of the fine model. The novelty of our work is to introduce a Neuro-SM model combining separate mappings for voltage and current...
A gallium nitride Doherty power amplifier (GaN Doherty PA) was designed for 2.5 GHz WiMAX band, and a radial-basis function neural network (RBFNN) model is proposed for predicting this amplifier' nonlinear characteristics. Comparison of AM/AM, AM/PM, PAE and Pout curves between the RBFNN model and circuit simulation are given. After 125 epochs, the convergence of this RBFNN model becomes slower and...
This paper presents an overview of emerging artificial neural network (ANN) techniques and applications for electromagnetic (EM) simulation and design. Accurate time domain EM modeling using recurrent neural networks (RNNs) is reviewed. Advanced robust training algorithm combining particle swarm optimization (PSO) and quasi-Newton method is described through frequency domain EM modeling, showing its...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.