{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:29:34Z","timestamp":1760236174521,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The design of neural network architectures is carried out using methods that optimize a particular objective function, in which a point that minimizes the function is sought. In reported works, they only focused on software simulations or commercial complementary metal-oxide-semiconductor (CMOS), neither of which guarantees the quality of the solution. In this work, we designed a hardware architecture using individual neurons as building blocks based on the optimization of n-dimensional objective functions, such as obtaining the bias and synaptic weight parameters of an artificial neural network (ANN) model using the gradient descent method. The ANN-based architecture has a 5-3-1 configuration and is implemented on a 1.2 \u03bcm technology integrated circuit, with a total power consumption of 46.08 mW, using nine neurons and 36 CMOS operational amplifiers (op-amps). We show the results obtained from the application of integrated circuits for ANNs simulated in PSpice applied to the classification of digital data, demonstrating that the optimization method successfully obtains the synaptic weights and bias values generated by the learning algorithm (Steepest-Descent), for the design of the neural architecture.<\/jats:p>","DOI":"10.3390\/s21217071","type":"journal-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T21:42:05Z","timestamp":1635198125000},"page":"7071","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["CMOS Implementation of ANNs Based on Analog Optimization of N-Dimensional Objective Functions"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4468-9850","authenticated-orcid":false,"given":"Alejandro","family":"Medina-Santiago","sequence":"first","affiliation":[{"name":"Department of Computer Science, CONACYT-INAOE (Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica), Santa Mar\u00eda Tonanzintla, Puebla 72840, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0267-6306","authenticated-orcid":false,"given":"Carlos Arturo","family":"Hern\u00e1ndez-Gracidas","sequence":"additional","affiliation":[{"name":"Physical-Mathematical Science Department, CONACYT-BUAP, Puebla 72570, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-9375","authenticated-orcid":false,"given":"Luis Alberto","family":"Morales-Rosales","sequence":"additional","affiliation":[{"name":"Faculty of Civil Engineering, CONACYT-Universidad Michoacana de San Nicol\u00e1s de Hidalgo, Morelia 58000, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4748-3500","authenticated-orcid":false,"given":"Ignacio","family":"Algredo-Badillo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, CONACYT-INAOE (Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica), Santa Mar\u00eda Tonanzintla, Puebla 72840, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3575-9861","authenticated-orcid":false,"given":"Monica","family":"Amador Garc\u00eda","sequence":"additional","affiliation":[{"name":"Instituto Tecnol\u00f3gico Superior de Rioverde, Tecnol\u00f3gico Nacional de M\u00e9xico, San Luis Potosi 79610, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3725-1674","authenticated-orcid":false,"given":"Jorge Antonio","family":"Orozco Torres","sequence":"additional","affiliation":[{"name":"Campus Tuxtla Guti\u00e9rrez, Tecnol\u00f3gico Nacional de M\u00e9xico, Tuxtla Guti\u00e9rrez 29050, Mexico"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,25]]},"reference":[{"key":"ref_1","unstructured":"Baker, R.J. (2019). CMOS: Circuit Design, Layout, and Simulation, Wiley-IEEE Press. [4th ed.]."},{"key":"ref_2","unstructured":"Razavi, B. (2016). Design of Analog CMOS Integrated Circuits, McGraw-Hill Education. [2nd ed.]."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Abbas, K. (2020). Handbook of Digital CMOS Technology, Circuits, and Systems, Springer International Publishing.","DOI":"10.1007\/978-3-030-37195-1"},{"key":"ref_4","first-page":"66","article-title":"Design of a CMOS OR Gate using Artificial Neural Networks (ANNs)","volume":"21","author":"Mandal","year":"2016","journal-title":"AMSE J. Ser. Adv. D"},{"key":"ref_5","first-page":"87","article-title":"Application of Artificial Neural Networks in Electronics","volume":"21","author":"Miona","year":"2017","journal-title":"Electronics"},{"key":"ref_6","unstructured":"Cichocki, A., and Unbehauen, R. (1993). Neural Networks for Optimization and Signal Processing, John Wiley & Sons, Inc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1007\/s11063-017-9761-9","article-title":"Approximate Solutions of Initial Value Problems for Ordinary Differential Equations Using Radial Basis Function Networks","volume":"48","author":"Rizaner","year":"2018","journal-title":"Neural Process. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"020070","DOI":"10.1063\/1.5041601","article-title":"Solving ordinary differential equations using neural networks","volume":"1974","author":"Tan","year":"2018","journal-title":"AIP Conf. Proc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2318","DOI":"10.1109\/TAC.2016.2615360","article-title":"Scalable Design of Heterogeneous Networks","volume":"62","author":"Pates","year":"2017","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_10","unstructured":"Haug, Y., Guo, N., Seok, M., Tsividis, Y., Mandli, K., and Sethumadhavan, S. (2017, January 14\u201318). Hybrid Analog-Digital Solution of Nonlinear Partial Differential Equations. Proceedings of the 2017 50th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), Cambridge, MA, USA."},{"key":"ref_11","unstructured":"Hagan, M.T., Demuth, H.B., and Beale, M.H. (2014). Neural Network Design, PWS Publishing Company. [2nd ed.]."},{"key":"ref_12","unstructured":"Adolphs, L., Daneshmand, H., Lucchi, A., and Hofmann, T. (2019, January 16\u201318). Local Saddle Point Optimization: A Curvature Exploitation Approach. Proceedings of Machine Learning Research. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, Naha, Japan."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Rhinehart, R.R. (2018). Engineering Optimization: Applications, Methods and Analysis, John Wiley & Sons.","DOI":"10.1115\/1.861OPT"},{"key":"ref_14","unstructured":"French, M. (2018). Fundamentals of Optimization Methods, Minimum Principles and Applications for Making Things Better, Springer."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bogdan, M., Wilamowski, J., and David, I. (2018). Intelligent Systems, CRC Press.","DOI":"10.1201\/9781315218427"},{"key":"ref_16","unstructured":"Li, Y. (2018). Deep Reinforcement Learning: An Overview, Neural Networks, Elsevier."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s40092-016-0146-x","article-title":"On the use of back propagation and radial basis function neural networks in surface roughness prediction","volume":"12","author":"Markopoulos","year":"2016","journal-title":"J. Ind. Eng. Int."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"54","DOI":"10.2174\/1874088X01610010054","article-title":"Design Ratio-Memory Cellular Neural Network (RMCNN) in CMOS Circuit Used in Association-Memory Applications for 0.25 mm Silicon Technology","volume":"10","author":"Lai","year":"2016","journal-title":"Open Mater. Sci. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3737","DOI":"10.1109\/TIE.2016.2540582","article-title":"Linearization of Bipolar Amplifier Based on Neural-Network Training Algorithm","volume":"63","author":"Su","year":"2016","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_20","first-page":"89","article-title":"Neuromorphic computing using non-volatile memory","volume":"2","author":"Burr","year":"2017","journal-title":"Adv. Phys. X"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1109\/TCSI.2017.2729787","article-title":"Memristor-Based Circuit Design for Multilayer Neural Networks","volume":"65","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Regul. Pap."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Krestinskaya, O., Salama, K.N., and James, A.P. (2018, January 27\u201330). Analog Backpropagation Learning Circuits for Memristive Crossbar Neural Networks. Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy.","DOI":"10.1109\/ISCAS.2018.8351344"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"479","DOI":"10.26599\/TST.2019.9010019","article-title":"Hardware Implementation of Spiking Neural Networks on FPGA","volume":"25","author":"Han","year":"2020","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"79","DOI":"10.21608\/mjeer.2015.64132","article-title":"Summary of memristor up to 2015","volume":"24","author":"Nafea","year":"2015","journal-title":"Menoufia J. Electron. Eng. Res."},{"key":"ref_25","unstructured":"Wang, Y., Cao, S., Jin, X., Peng, Y., and Luo, J. (2020). Semiconductor Science and Technology, IOP Publishing Ltd."},{"key":"ref_26","unstructured":"Yener, \u015e., and Kuntman, H. (2012, January 5\u20137). New CMOS based memristor implementation. Proceedings of the 2012 International Conference on Applied Electronics, Pilsen, Czech Republic."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abunahla, H., and Mohammad, B. (2018). Memristor Technology: Synthesis and Modeling for Sensing and Security Applications, Chapter 1 Memristor Device Overview and Chapter 6 Memristor Device Modeling, Springer.","DOI":"10.1007\/978-3-319-65699-1_1"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/21\/7071\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:23:08Z","timestamp":1760167388000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/21\/7071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,25]]},"references-count":27,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["s21217071"],"URL":"https:\/\/doi.org\/10.3390\/s21217071","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,10,25]]}}}