Estimation method for inverse problems with linear forward operator and its application to magnetization estimation from magnetic force microscopy images using deep learning

References

• Leyva-Cruz JA, Ferreira ES, Miltão MSR, et al. Reconstruction of magnetic source images using the Wiener filter and a multichannel magnetic imaging system. Rev Sci Instrum. 2014;85:074701.
   Google Scholar
• Mallinson J. On the properties of two-dimensional dipoles and magnetized bodies. IEEE Trans Magn. 1981;17:2453–2460.
   Google Scholar
• Vellekoop B, Abelmann L, Porthun S, et al. On the determination of the internal magnetic structure by magnetic force microscopy. J Magn Magn Mater. 1998;190:148–151.
   Google Scholar
• Saito H, Chen J, Ishio S. Description of magnetic force microscopy by three-dimensional tip green's function for sample magnetic charges. J Magn Magn Mater. 1999;191:153–161.
   Google Scholar
• Cao Y, Kumar P, Zhao Y, et al. Active magnetic force microscopy of Sr-ferrite magnet by stimulating magnetization under an AC magnetic field: direct observation of reversible and irreversible magnetization processes. Appl Phys Lett. 2018;112:223103.
   Google Scholar
• Cao Y, Zhao Y, Kumar P, et al. Magnetic domain imaging of a very rough fractured surface of Sr ferrite magnet without topographic crosstalk by alternating magnetic force microscopy with a sensitive FeCo–GdOx superparamagnetic tip. J Appl Phys. 2018;123:224503.
   Google Scholar
• Saito H, Ikeya H, Egawa G, et al. Magnetic force microscopy of alternating magnetic field gradient by frequency modulation of tip oscillation. J Appl Phys. 2009;105:07D524.
   Google Scholar
• Chang T, Lagerquist M, Zhu JG, et al. Deconvolution of magnetic force images by Fourier analysis. IEEE Trans Magn. 1992;28:3138–3140.
   Google Scholar
• Hsu CC, Miller CT, Indeck RS, et al. Magnetization estimation from MFM images. IEEE Trans Magn. 2002;38:2444–2446.
   Google Scholar
• Madabhushi R, Gomez RD, Burke ER, et al. Magnetic biasing and MFM image reconstruction. IEEE Trans Magn. 1996;32:4147–4149.
   Google Scholar
• Rawlings C, Durkan C. The inverse problem in magnetic force microscopy (MFM) – inferring sample magnetization from MFM images. Nanotechnology. 2013;24:305705.
   Google Scholar
• Zhao T, Fujiwara H, Mankey J, et al. Reconstruction of in-plane magnetization distributions from magnetic force microscope images. J Appl Phys. 2001;89:7230–7232.
   Google Scholar
• Montúfar G, Pascanu R, Cho K, et al. On the number of linear regions of deep neural networks. In: Ghahramani, Z, Welling, M, Cortes, C, editors. NIPS'14 Proceedings of the 27th International Conference on Neural Information Processing Systems, Vol 2; MIT Press: Cambridge, USA; 2014. p. 2924–2932.
   Google Scholar
• Keras Google group. Keras Documentation. https://keras.io/ (accessed on 11 December 2019).
   Google Scholar
• Keras Google group. Keras losses source. https://github.com/keras-team/keras/blob/master/keras/losses.py (accessed on 9 October 2018).
   Google Scholar
• Stanley RP. An Introduction to Hyperplane Arrangements. 2006. https://www.cis.upenn.edu/∼cis610/sp06stanley.pdf (accessed on 28 October 2019).
   Google Scholar
• Keras Google group. Keras optimizer source. https://github.com/keras-team/keras/blob/master/keras/optimizers.py#L392 (accessed on 9 October 2018).
   Google Scholar
• Kingma DP, Ba JA. A method for stochastic optimizer. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015); San Diego, USA, 2015; pp. 1–15.
   Google Scholar
• Murray W, Ng KM. An algorithm for nonlinear optimization problems with binary variables. Comput Optim Appl. 2010;47:257–288.
   Google Scholar
• Mitchell JE, Pardalos PM, Resende GC. Interior point methods for combinatorial optimization. In: Du DZ, Pardalos PM, editors. Handbook of Combinatorial Optimization, Vol 1; Kluwer Academic Publishers: Dordrecht, Netherlands; 1999. p. 189–298.
   Google Scholar
• Ng KM. A continuation approach for solving nonlinear optimization problems with discrete variables [PhD thesis]. Stanford: Dept. Management Science and Engineering of Stanford Univ., 2002.
   Google Scholar
• Dembo RS, Steihaug T. Truncated-Newton algorithms for large-scale unconstrained optimization. Math Program. 1983;26:190–212.
   Google Scholar
• Groetsch CW. Inverse problems in the mathematical sciences. Braunschweig-Wiesbaden: Friedr. Vieweg & Sohn; 1993.
   Google Scholar
• Sampietro D and Sansò F. Uniqueness theorems for inverse gravimetric problems. In: Sneeuw N, et al., editors. VII Hotine-Marussi Symposium on Mathematical Geodesy, International Association of Geodesy Symposia 137. Springer-Verlag: Berlin, Heidelberg; 2012. p. 111–115.
   Google Scholar