Performance Evaluation of Various ANN Architectures Using Proposed Cost Function

Traditional learning methods focus on the training of neural networks. However robustness or fault tolerance or sensitivity of its input to output which plays an important role while designing a neural network are not considered appropriately. Purpose of this paper is the optimization of various feed forward artificial neural network (FFANN) architectures with hyper-parmeter selection and using proposed cost function AvgNew.This paper, has proposed a cost function which when applied to TDFFANN(tailored deep feed forward artificial neural network) and other FFANN architectures makes it more fault-tolerant, sensitive or robust. Result obtained using variants of MLP(Multi Layer Perceptron) and FFANN(feed forward artificial neural network) proves AvgNew to be efficient.

[1]  Isil Dillig,et al.  Optimization and abstraction: a synergistic approach for analyzing neural network robustness , 2019, PLDI.

[2]  Hamid Reza Karimi,et al.  Performance evaluation of feedforward neural networks for modeling a vehicle to pole central collision , 2011 .

[3]  Pravin Chandra,et al.  Empirical Study of FFANN Tolerance to Weight Stuck at Max/Min Fault , 2010 .

[4]  Walter Schön,et al.  Fault Tolerant Deep Neural Networks for Detection of Unrecognizable Situations , 2018 .

[5]  Yee Whye Teh,et al.  A Statistical Approach to Assessing Neural Network Robustness , 2018, ICLR.

[6]  Moumen T. El-Melegy,et al.  Robust Training of Artificial Feedforward Neural Networks , 2009, Foundations of Computational Intelligence.

[7]  John Sum,et al.  Fault Tolerant Learning for Neural Networks: Survey, Framework and Future Work , 2009 .

[8]  Amit Prakash Singh,et al.  Empirical Study of Least Sensitive FFANN for Weight-Stuck-at Zero Fault , 2010 .

[9]  Udayan Ghose,et al.  Tailored feedforward artificial neural network based link prediction , 2019, International Journal of Information Technology.

[10]  Austin P. Arechiga,et al.  Sensitivity of Feedforward Neural Networks to Harsh Computing Environments , 2018 .

[11]  Jay H. Lee,et al.  Fault detection and classification using artificial neural networks , 2018 .

[12]  Amit Prakash Singh,et al.  New Metrics for Sensitivity Analysis of FFANN , 2010 .

[13]  Yogesh Singh,et al.  Feedforward sigmoidal networks - equicontinuity and fault-tolerance properties , 2004, IEEE Transactions on Neural Networks.

[14]  Hongtu Zhu,et al.  Sensitivity Analysis of Deep Neural Networks , 2019, AAAI.

[15]  Andrew Chi-Sing Leung,et al.  Prediction error of a fault tolerant neural network , 2006, Neurocomputing.

[16]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[17]  Corina S. Pasareanu,et al.  DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks , 2018, ATVA.

[18]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[19]  Jing Wang,et al.  Fault Localization Analysis Based on Deep Neural Network , 2016 .

[20]  Liang Zhao,et al.  Interpreting and Evaluating Neural Network Robustness , 2019, IJCAI.

[21]  Robert B. Fisher,et al.  Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches , 2016, BMVC.

[22]  Bernard Ghanem,et al.  Towards Analyzing Semantic Robustness of Deep Neural Networks , 2019, ECCV Workshops.

[23]  Mark S. Squillante,et al.  PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach , 2018, ICML.

[24]  Min Wu,et al.  Robustness Guarantees for Deep Neural Networks on Videos , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Jascha Sohl-Dickstein,et al.  Sensitivity and Generalization in Neural Networks: an Empirical Study , 2018, ICLR.

[26]  Cho-Jui Hsieh,et al.  Efficient Neural Network Robustness Certification with General Activation Functions , 2018, NeurIPS.

[27]  Maosen Cao,et al.  Advanced Methods in Neural Networks-Based Sensitivity Analysis with their Applications in Civil Engineering , 2016 .

[28]  Vincenzo Piuri,et al.  Analysis of Fault Tolerance in Artificial Neural Networks , 2001, J. Parallel Distributed Comput..

[29]  Thi-Lan Le,et al.  Robustness Analysis of 3D Convolutional Neural Network for Human Hand Gesture Recognition , 2019, International Journal of Machine Learning and Computing.

[30]  Yang Song,et al.  Improving the Robustness of Deep Neural Networks via Stability Training , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).