Search

Search Results

• DESIGNING MLP AND CNN NEURAL NETWORK MODULES ON FPGA FOR IMAGE CLASSIFICATION TASKS

  E. V. Melnik , D.Е. Blokh , А.I. Bezmeltsev , V.S. Panishchev , S.N. Poltoratsky

  214-229

  2025-11-10

  Abstract ▼

  Relevance. The development of machine learning methods and neural network architectures, as well as their spread into various industrial sectors, determine the relevance of solving problems related to their hardware implementation. The use of programmable logic integrated circuits in this area will increase data processing speed and the adaptability of the implemented algorithms. However, designing neural network architectures on programmable logic integrated circuits is associated with a number of methodological and technical difficulties, including the optimization of parallel computing, hardware resource management, and ensuring operation under conditions of limited computing resources. The purpose of this work is to analyze and compare two neural network architectures, the multilayer perceptron (MLP) and the convolutional neural network (CNN), in the context of their hardware implementation on programmable logic integrated circuits (PLICs). Particular attention is paid to the trade-off between classification accuracy and the efficient use of limited FPGA hardware resources. Research methods.
  To achieve the goal, two modules were developed and simulated on a Virtex 7 FPGA, a perceptron and a convolutional module. The MNIST dataset, reduced to 20×20 pixels, was used. The implementation included quantizing parameters to a fixed 16:16 format, optimizing hyperparameters, using tabular computations for nonlinear functions, and evaluating FPGA resource usage. Results and discussions.
  MLP achieved 93% accuracy using 11% of logic elements, while CNN achieved 98% accuracy but required significantly more resources. The use of internal buffers to store intermediate data in CNN resulted in exceeding the allowable resources. The forced transition to external memory increased delays and the number of I/O ports. Conclusions. The study showed that the choice of architecture depends on priorities: CNN provides better accuracy but is less resource-efficient. For embedded systems with memory and power consumption constraints, a simplified MLP implementation is preferable. The main problems remain the lack of internal memory and the high resource intensity of operations, which requires further research in the field of hardware optimization and adaptive computation control

• RANDOM ERROR OF PULSE DURATION MEASUREMENT WITH OSCILLATIONS AT THE TOP BY MULTI-THRESHOLD DURATION METERS

  D.V. Belyaev, D.E. Gubarev, К. Е. Rumyantsev

  2021-12-24

  Abstract ▼

  In systems for automatic measurement of the duration of video pulses, various devices for amplifying
  and shaping pulses of a normalized level are used, the duration of which is equal to the duration
  of the input signals. A rough measurement of the duration of video pulses can be made with onethreshold
  meters. More accurate are multi-threshold and floating-threshold meters. Pulse duration
  meters have found wide application in electronic warfare equipment, in measuring technology. The
  variation in the shape of electrical signals does not allow the use of a single measurement method,
  which is the best for all shapes, therefore, the search for technical solutions that satisfy the conflicting
  requirements continues: a wide range of durations and duty cycles. The aim of this work is to
  carry out a mathematical analysis of the random error in measuring the pulse duration with oscillations
  at the top by multi-threshold duration meters. In the course of the work, the results of a numerical
  experiment were obtained to measure the duration of a pulse with oscillations at the top using
  multi-threshold duration meters. And also a comparison was made of four multi-threshold duration
  meters for the investigated pulse shape. The calculation results are presented for a signal dynamic
  range of 60 dB and an amplitude quantization step of 3dB and 12 dB.