Challenging the Evolutionary Strategy for Synthesis of Analogue Computational Circuits

Abstract

There are very few reports in the past on applications of Evolutionary Strategy (ES) towards the synthesis of analogue circuits. Moreover, even fewer reports are on the synthesis of computational circuits. Last fact is mainly due to the difficulty in designing of the complex nonlinear functions that these circuits perform. In this paper, the evolving power of the ES is challenged to design four computational circuits: cube root, cubing, square root and squaring functions. The synthesis succeeded due to the usage of oscillating length genotype strategy and the substructure reuse. The approach is characterized by its simplicity and represents one of the first attempts of application of ES towards the synthesis of “QR” circuits. The obtained experimental results significantly exceed the results published before in terms of the circuit quality, economy in components and computing resources utilized, revealing the great potential of the technique proposed to design large scale analog circuits

Synthesis of Time-to-Amplitude Converter by Mean CoeVolution with Adaptive Parameters

“…In earlier works, we already had reported about some aspects of DM and adaptation [1,3]. In later works, we found that the system performs better at SRs 10 times lower than before (from 10% to 1%) [3].…”

“…In earlier works, we already had reported about some aspects of DM and adaptation [1,3]. In later works, we found that the system performs better at SRs 10 times lower than before (from 10% to 1%) [3]. Despite proving our recent technique to be a powerful tool in comparison with others [7], we have failed with it when evolving TIMC.…”

“…In the following section, we give details of the methodology we propose, the basics of which is stated previously in [3].…”

“…The linear (direct) circuit representation is proposed for use, similar to that one exploited in [3,24], where each component in a circuit is coded in a gene. Whether it is a transistor or a resistor or a capacitor, the component's features (nodes, parameter, and name) are coded into four loci.…”

“…In recent years, evolutionary strategy (ES) has been found to be one of the most powerful evolutionary algorithms (EA) when applied toward the synthesis of electronic circuits [1][2][3][4]. Despite ES proving itself effective in solving the scalability problem and reaching great experimental results, the existing ES-based circuit synthesizers by their technique are far behind the state-of-theart EA theoretical developments.…”