A Dynamic Fitness Function Applied to Improve the Generalisation when Evolving a Signal Processing Hardware Architecture
نویسنده
چکیده
Evolvable Hardware (EHW) has been proposed as a new method for designing electronic circuits. In this paper it is applied for evolving a prosthetic hand controller. The novel controller architecture is based on digital logic gates. A set of new methods to incrementally evolve the system is described. This includes several different variants of the fitness function being used. By applying the proposed schemes, the generalisation of the system is improved.
منابع مشابه
FPGA Implementation of JPEG and JPEG2000-Based Dynamic Partial Reconfiguration on SOC for Remote Sensing Satellite On-Board Processing
This paper presents the design procedure and implementation results of a proposed hardware which performs different satellite Image compressions using FPGA Xilinx board. First, the method is described and then VHDL code is written and synthesized by ISE software of Xilinx Company. The results show that it is easy and useful to design, develop and implement the hardware image compressor using ne...
متن کاملDesign and Implementation of Digital Demodulator for Frequency Modulated CW Radar (RESEARCH NOTE)
Radar Signal Processing has been an interesting area of research for realization of programmable digital signal processor using VLSI design techniques. Digital Signal Processing (DSP) algorithms have been an integral design methodology for implementation of high speed application specific real-time systems especially for high resolution radar. CORDIC algorithm, in recent times, is turned out to...
متن کاملEvolving both Hardware Subsystems and the Selection of Variants of such into an Assembled System
Evolvable Hardware (EHW) has been proposed as a new method for designing electronic circuits. However, there are several problems to solve for making high performance systems. One is the limited scalability of the ordinary approach. To reduce this problem, a novel digital signal processing architecture has been developed that allows for incremental evolution. This is based on initially evolving...
متن کاملA Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...
متن کاملA Comparative Study of VHDL Implementation of FT-2D-cGA and FT-3D-cGA on Different Benchmarks (RESEARCH NOTE)
This paper presents the VHDL implementation of fault tolerant cellular genetic algorithm. The goal of paper is to harden the hardware implementation of the cGA against single error upset (SEU), when affecting the fitness registers in the target hardware. The proposed approach, consists of two phases; Error monitoring and error recovery. Using innovative connectivity between processing elements ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002