Abstract. We report an inter-comparison of some popular algorithms within the artificial neural network domain ( viz., Local search algorithms, global search algorithms, higher order algorithms and the hybrid algorithms) by applying them to the standard benchmarking problems like the IRIS data, XOR/N-Bit parity and Two Spiral. Apart from giving a brief description of these algorithms, the results obtained for the above benchmark problems are presented in the paper. The results suggest that while Levenberg-Marquardt algorithm yields the lowest RMS error for the N-bit Parity and the Two Spiral problems, Higher Order Neurons algorithm gives the best results for the IRIS data problem. The best results for the XOR problem are obtained with the Neuro Fuzzy algorithm. The above algorithms were also applied for solving several regression problems such as cos(x) and a few special functions like the Gamma function, the complimentary Error function and the upper tail cumulative χ 2 -distribution function. The results of these regression problems indicate that, among all the ANN algorithms used in the present study, Levenberg-Marquardt algorithm yields the best results. Keeping in view the highly nonlinear behaviour and the wide dynamic range of these functions, it is suggested that these functions can be also considered as standard benchmark problems for function approximation using artificial neural networks.

No abstract

: An Artificial Neural Network-based error compensation method is proposed for improving the accuracy of resolver-based 16-bit encoders by compensating for their respective systematic error profiles. The error compensation procedure, for a particular encoder, involves obtaining its error profile by calibrating it on a precision rotary table, training the neural network by using a part of this data and then determining the corrected encoder angle by subtracting the ANNpredicted error from the measured value of the encoder angle. Since it is not guaranteed that all the resolvers will have exactly similar error profiles because of the inherent differences in their construction on a micro scale, the ANN has been trained on one error profile at a time and the corresponding weight file is then used only for compensating the systematic error of this particular encoder. The systematic nature of the error profile for each of the encoders has also been validated by repeated calibration of the encoders over a period of time and it was found that the error profiles of a particular encoder recorded at different epochs show near reproducible behaviour. The ANN-based error compensation procedure has been implemented for 4 encoders by training the ANN with their respective error profiles and the results indicate that the accuracy of encoders can be improved by nearly an order of magnitude from quoted values of ∼± 6 arc-min to ∼±0.65 arc-min when their corresponding ANN-generated weight files are used for determining the corrected encoder angle.

We present results from multi-wavelength study of intense flaring activity from a high frequency peaked BL Lac object Mrk 421. The source was observed in its flaring state on

Abstract. In this paper we report on the Markarian 501 results obtained during our TeV γ-ray observations from March 11 to May 12, 2005 and February 28 to May 7, 2006 for 112.5 hours with the TACTIC γ-ray telescope. During 2005 observations for 45.7 hours, the source was found to be in a low state and we have placed an upper limit of 4.62 × 10 −12 photons cm −2 s −1 at 3σ level on the integrated TeV γ-ray flux above 1 TeV from the source direction. However, during the 2006 observations for 66.8h, detailed data analysis revealed the presence of a TeV γ-ray signal from the source with a statistical significance of 7.5σ above E γ ≥ 1 TeV. The time averaged differential energy spectrum of the source in the energy range 1-11 TeV is found to match well with the power law function of the form (dΦ/dE = f 0 E −Γ ) with f 0 = (1.66 ± 0.52) × 10 −11 cm −2 s −1 T eV −1 and Γ = 2.80 ± 0.27.