Thermodynamic cost of edge detection in artificial neural network (ANN)-based processors

References

• Ercan İ, Anderson NG. Heat dissipation in nanocomputing: lower bounds from physical information theory. IEEE Trans Nanotechnol. 2013;12:1047–1060. doi: 10.1109/TNANO.2013.2276938
   Web of Science ®Google Scholar
• Ercan İ, Suyabatmaz E. Fundamental energy limits of SET-based Brownian NAND and half-adder circuits. Eur Phys J B. 2018;91:13. doi: 10.1140/epjb/e2018-80619-6
   Web of Science ®Google Scholar
• Ercan İ. Fundamental energy dissipation limits in logic circuits. ICT Energy Lett. 2016;12:3–4.
   Google Scholar
• Yakar O, Nie Y, Wada K, et al. Energy efficiency analyses of microring-resonator based BDD logic circuits. Proceedings of the IEEE International Conference on Rebooting Computing; 2019. p. 1–8.
   Google Scholar
• Ganesh N, Anderson NG. Irreversibility and dissipation in finite-state automata. Phys Lett A. 2013;377(45–48):3266–3271. doi: 10.1016/j.physleta.2013.10.010
   Web of Science ®Google Scholar
• Ganesh N, Anderson NG. Dissipation in neuromorphic computing: Fundamental bounds for feedforward networks. IEEE 17th International Conference on Nanotechnology (IEEE-NANO); 2017. p. 594–599.
   Google Scholar
• Anderson NG, Ercan İ, Ganesh N. Toward nanoprocessor thermodynamics. IEEE Trans Nanotechnol. 2013;12:902–909. doi: 10.1109/TNANO.2013.2260352
   Web of Science ®Google Scholar
• Ricci JP, Anderson NG. Architecture and dissipation: thermodynamic costs of general purposeness in von Neumann processors. Proceedings of the IEEE International Conference on Rebooting Computing (ICRC); 2017. p. 1–4.
   Google Scholar
• Conte T, DeBenedictis E, Ganesh N, et al. Thermodynamic computing: a report based on a CCC workshop. arXiv: 1911.01968v2 [Preprint]. 2019 [cited 2019 Mar 9]: [36 p.]. Available from: https://arxiv.org/abs/1911.01968 https://arxiv.org/abs/1911.01968.
   Google Scholar
• Haykin S. Neural networks and learning machines. 3rd ed. New Jersey: Pearson Education; 2008.
   Google Scholar
• Hertz J, Krogh A, Palmer RG. Introduction to the theory of neural computation. 1st ed. London: CRC Press; 1991.
   Google Scholar
• Anderson JA. An introduction to neural networks. 3r ed. Cambridge: MIT Press; 1995.
   Google Scholar
• Becerikli Y, Demiray HE. Alternative neural network based edge detection. Neural Inf Process Lett Rev. 2006;10:193–199.
   Google Scholar
• Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323:533–536. doi: 10.1038/323533a0
   Web of Science ®Google Scholar
• Gheorghiu T. ANN visualizer [Internet]. 2018 Jul 2 [cited 2019 Mar 9]. Available from: https://pypi.org/project/ann_visualizer/ https://pypi.org/project/ann_visualizer/.
   Google Scholar
• Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics [dataset]. 2001 [cited 2019 Mar 9]. Available from: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/BSDS300/html/dataset/images.html.
   Google Scholar
• Wang R. Edge detection using convolutional neural network. International Symposium on Neural Networks; 2016. p. 12–20.
   Google Scholar
• He K, Zhang X, Ren S, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision; 2015. p. 1026–1034.
   Google Scholar
• Kingma DP, Adam BaJ. A method for stochastic optimization. arXiv: 1412.6980v9 [Preprint]. 2017 [cited 2019 Mar 9]: [15 p.]. Available from: https://arxiv.org/abs/1412.6980https://arxiv.org/abs/1412.6980.
   Google Scholar
• Prechelt L. Early stopping-but when? In: Montavon G, Orr GB., Müller KR, editors. Neural networks: tricks of the trade. Berlin: Springer; 1998. p. 55–69.
   Google Scholar
• Anderson NG. Information erasure in quantum systems. Phys Lett A. 2008;372:5552–5555. doi: 10.1016/j.physleta.2008.06.081
   Web of Science ®Google Scholar
• Anderson NG. On the physical implementation of logical transformations: generalized l-machines. Theor Comput Sci. 2010;411:4179–4199. doi: 10.1016/j.tcs.2010.06.015
   Web of Science ®Google Scholar
• Anderson NG. Overwriting information: correlations, physical costs, and environment models. Phys Lett A. 2012;376:1426–1433. doi: 10.1016/j.physleta.2012.03.012
   Web of Science ®Google Scholar