2026-09-19T14:25:15Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1445822022-08-30T03:40:50Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

del Alamo, Jesús A. Onen, O. Murat Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2022-08-29T15:57:14Z 2022-08-29T15:57:14Z 2022-05 2022-06-21T19:15:52.870Z https://hdl.handle.net/1721.1/144582 0000-0002-9078-2901 Efforts to realize analog processors have skyrocketed over the last decade as having energy-efficient deep learning accelerators became imperative for the future of information processing. However, the absence of two entangled components creates an impasse before their practical implementation: devices satisfying algorithm-imposed requirements and algorithms running on nonideality-tolerant routines. This thesis demonstrates a near-ideal device technology and a superior neural network training algorithm that can ultimately propel analog computing when combined together. The CMOS-compatible nanoscale protonic devices demonstrated here show unprecedented characteristics, incorporating the benefits of nanoionics with extreme acceleration of ion transport and reactions under strong electric fields. Enabled by a material-level breakthrough of utilizing phosphosilicate glass (PSG) as a proton electrolyte, this operation regime achieves controlled shuttling and intercalation of protons in nanoseconds at room temperature in an energy-efficient manner. Then, a theoretical analysis is carried out to explain the infamous incompatibility between asymmetric device modulation and conventional neural network training algorithms. By establishing a powerful analogy with classical mechanics, a novel method, Stochastic Hamiltonian Descent, is developed to exploit device asymmetry as a useful feature. Overall, devices and algorithms developed in this thesis have immediate applications in analog deep learning, whereas the overarching methodology provides further insight for future advancements. Ph.D. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ Devices and Algorithms for Analog Deep Learning Thesis application/pdf Doctoral Doctor of Philosophy Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="64cf4063-bb4d-4d85-ae7d-70ccd89d803e"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Devices and Algorithms for Analog Deep Learning</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2022-05</PublicationDate> <Authors> <Author> <DisplayName>Onen, O. Murat</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>Efforts to realize analog processors have skyrocketed over the last decade as having energy-efficient deep learning accelerators became imperative for the future of information processing. However, the absence of two entangled components creates an impasse before their practical implementation: devices satisfying algorithm-imposed requirements and algorithms running on nonideality-tolerant routines. This thesis demonstrates a near-ideal device technology and a superior neural network training algorithm that can ultimately propel analog computing when combined together. The CMOS-compatible nanoscale protonic devices demonstrated here show unprecedented characteristics, incorporating the benefits of nanoionics with extreme acceleration of ion transport and reactions under strong electric fields. Enabled by a material-level breakthrough of utilizing phosphosilicate glass (PSG) as a proton electrolyte, this operation regime achieves controlled shuttling and intercalation of protons in nanoseconds at room temperature in an energy-efficient manner. Then, a theoretical analysis is carried out to explain the infamous incompatibility between asymmetric device modulation and conventional neural network training algorithms. By establishing a powerful analogy with classical mechanics, a novel method, Stochastic Hamiltonian Descent, is developed to exploit device asymmetry as a useful feature. Overall, devices and algorithms developed in this thesis have immediate applications in analog deep learning, whereas the overarching methodology provides further insight for future advancements.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>