{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/144582"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/144582","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Devices and Algorithms for Analog Deep Learning","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_html":"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_has_math":false,"creators":["Onen, O. Murat"],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["del Alamo, Jesús A."],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:21:27Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/144582","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["del Alamo, Jesús A."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Onen, O. Murat"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T15:57:14Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T15:57:14Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral","Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/144582"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Devices and Algorithms for Analog Deep Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["del Alamo, Jesús A."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Onen, O. Murat"],"dc:date.accessioned":["2022-08-29T15:57:14Z"],"dc:date.available":["2022-08-29T15:57:14Z"],"dc:date.issued":["2022-05"],"dc:description.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."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/144582"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Devices and Algorithms for Analog Deep Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral","Doctor of Philosophy"]},"updated_at":"2026-07-22T22:21:27Z"}