A. Thompson. "On the Automatic design of Robust Electronics through Artificial Evolution", in M. Sipper, D. Mange, A. Prez-Uribe (eds.), Proc. of The 2 Int. Conf. on Evolvable Systems: From Biology to Hardware, LNCS, vol. 1478, Springer-Verlag, pp. 13- 24, 1998.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....of the circuits in an environment equally noisy to the one in which it was evolved (m t =m c ) The experiment was otherwise carried out as explained earlier. Thompson has demonstrated that it is possible to evolve robust circuits intrinsically by exposing them to various environments [8, 9]. In the second experiment, the same set of chromosomes were tested with the messiness of the test bench m t , being set to increasingly higher values. This simulates the circuits running in increasingly more noisy environments, and disregards whatever value m e used when the chromosomes were ....

A. Thompson. "On the Automatic design of Robust Electronics through Artificial Evolution", in M. Sipper, D. Mange, A. Prez-Uribe (eds.), Proceedings of The 2 Biology to Hardware (ICES96), Lecture Notes in Computer

....objective function. Existing methods for the expectation based search of robust solutions in evolutionary optimization can generally be divided into two categories. Averaging. To find a robust solution, the fitness of a solution (x) is calculated by averaging several points in its neighborhood [5 8]: f(a, x) i=1 w i f(a, x #x i ) w i , 1) where a and x denote a vector of environmental parameters and a vector of design variables, respectively, i = 1, 2, N is the number of points to be evaluated. Usually, N should be larger than 2 but not too large due to the increasing ....

A. Thompson. On the automatic design of robust electronics through artificial evolution. In Proceedings on 2nd International Conference on Evolvable Systems, pages 13--24. Springer, 1998.

....the circuits in an environment equally noisy to the one in which it was evolved (m =m c ) In all other respects the experiment was the same as that described previously. Thompson has demonstrated that it is possible to evolve robust circuits intrinsically by exposing them to various environments [9, 10]. In the second experiment, the same set of chromosomes were tested with the messiness of the test bench m t , being set to increasingly higher values. This simulates the circuits running in increasingly more noisy environments, and disregards whatever value m e used when the chromosomes were ....

A. Thompson. "On the Automatic design of Robust Electronics through Artificial Evolution ", in M. Sipper, D. Mange, A. Prez-Uribe (eds.), Proceedings of The 2 Conference on Evolvable Systems: From Biology to Hardware (ICES96), Lecture Notes in Computer Science, vol. 1478, Springer-Verlag, Heidelberg, pp. 13- 24, 1998

....signals which have not been encountered in training. This includes signals with noise added and with frequencies which are not in the training set. 1 Introduction Recently it has been demonstrated how a digital circuit may be evolved in circuit to carry out a frequency discrimination task [21][22]. The behaviour of the circuit was intimately related to the physical properties of the actual integrated circuit used (i.e. temperature, silicon batch) The circuit was not clocked and the evolutionary algorithm had to allow the circuit to construct internal timing circuits with periods varying ....

Thompson A., "On the Automatic Design of Robust Electronics Through Artificial Evolution", in in Sipper M., Mange D., and Perez-Uribe A. (eds.), Proceedings of 2nd International Conference on Evolvable Systems: From Biology to Hardware (ICES98), LNCS, Vol. 1478, Springer-Verlag, Heidelberg, pp. 13 -24, 1998.

.... Netlist Function Gates Logic Gates Asynchronous Logic Analog Components Function Level Units Configuration Level Units [23, 52] 36, 48, 67, 68, 74] 8, 27,30, 32, 35, 39, 46, 47, 51, 59, 60, 61, 55, 62, 88, 89, 90, 92,93,94] 80, 82] 2, 18, 41, 49, 50, 79, 99] 28, 11, 66, 99] [21, 43, 44, 46, 78, 80, 81, 82, 83, 84, 85, 86, 87, LESS [ Hardware Behavior I Fig. 3: Levels of abstraction needed to characterize behavior of evolved circuits. Torresen [89] partitioned levels of abstraction into the digital and analog paradigms that are commonly used in the evolvable hardware literature, and are included here. Anderson [1] ....

....different FPGA, but also a different area of the same FPGA. Similar results have been reported by Masner et al. 53] We can think of Thompson s solution as including the bounds of the operating requirements as a procedural ordering bias, although not one specified directly by the fitness function [83]. He took a 18 previously evolved FPGA circuit that discriminated between two tones. He then specified a number of parameters for an operational envelope which when varied affected the performance of this circuit: temperature, power supply, fabrication variations, packaging, electronic ....

[Article contains additional citation context not shown here]

Thompson A. (1998), On the Automatic Design of Robust Electronics Through Artificial Evolution, Proc. of the 2nd Int. Conf. on Evolvable Systems, Lausanne, Switzerland, pp. 13-25.

....would not reveal into the public domain information as to the relationship between the bit string and the internal configuration of the device; this strongly limited the way in which prior knowledge could be incorporated into the system. Thompson s work using FPGAs s as analogue circuits [11] in some ways can be seen as a sea of components widespread interconnection scheme, though it could be considered as an even lower level system that simply uses different areas of doped and insulated silicon rather than distinguishable components. Damaging configurations were avoided by the ....

A. Thompson, "On the automatic design of robust electronics through artificial evolution," Lecture Notes in Computer Science, vol. 1478, pp. 13--24, 1998.

....Table 1. Evaluations at the target task were then performed on all four chips simultaneously and independently. The evolutionary fitness of the candidate was taken to be the worst of the four measurements. This multiFPGA, multi condition apparatus, called The Evolvatron , was fully described in [12]. Only the configuration of a 10 Theta 10 region of the 64 Theta 64 array of cells on the FPGA was subject to evolution. For each chip of Table 1, the 10 Theta 10 region was translated in position by a different but constant amount, as shown. Only nearest neighbour interconnections between ....

A. Thompson. On the automatic design of robust electronics through artificial evolution. In M. Sipper, D. Mange, and A. P'erez-Uribe, Eds, Proc. 2nd Int. Conf. on Evolvable Systems (ICES'98), vol. 1478 of LNCS, pp. 13--24. Springer-Verlag, 1998.

No context found.

A. Thompson. "On the Automatic design of Robust Electronics through Artificial Evolution", in M. Sipper, D. Mange, A. Prez-Uribe (eds.), Proc. of The 2 Int. Conf. on Evolvable Systems: From Biology to Hardware, LNCS, vol. 1478, Springer-Verlag, pp. 13- 24, 1998.

No context found.

A. Thompson. On the automatic design of robust electronics through artificial evolution. In Proceedings on 2nd International Conference on Evolvable Systems, pages 13--24. Springer, 1998.

No context found.

Thompson A. (1998). On the Automatic Design of Robust Electronics Through Artificial Evolution in Proceedings of The 1 st Int. Conf. on Evolvable Systems: From Biology to Hardware (ICES98), Lecture Notes in Computer Science, Eds.: Sipper M., et al Vol. 1478, Publisher: Springer-Verlag, Heidelberg, pp. 1324.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC