{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-3799"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-3799","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"One-shot Learning In Deep Sequential Generative Models","abstract":"Regardless of the Deep Learning community's continuous advancements, the challenging domain of one-shot learning still persists. While the human brain is capable of learning a new visual concept with ease, sometimes even at a glance, Deep Learning-based techniques show serious drawbacks in handling problems with small datasets. Much of the existing work on one-shot learning employs a variety of sophisticated network algorithms, prior domain knowledge, and data manipulation to address the generalization challenges presented in such problems. In this work, we demonstrate a one-shot learning method that contains three learning networks â€” a deep sequential generative model, a candidate network, and a Matching Network â€” thus offering an alternative approach to solving the one-shot classification problem. The proposed framework does not require domain knowledge, making it potentially portable to other domains. We show that our algorithm improves accuracy from 95.5% to 96.1% on the Omniglot dataset 20-way one-shot learning compared to current state-of-the-art.","abstract_html":"Regardless of the Deep Learning community&#x27;s continuous advancements, the challenging domain of one-shot learning still persists. While the human brain is capable of learning a new visual concept with ease, sometimes even at a glance, Deep Learning-based techniques show serious drawbacks in handling problems with small datasets. Much of the existing work on one-shot learning employs a variety of sophisticated network algorithms, prior domain knowledge, and data manipulation to address the generalization challenges presented in such problems. In this work, we demonstrate a one-shot learning method that contains three learning networks â€” a deep sequential generative model, a candidate network, and a Matching Network â€” thus offering an alternative approach to solving the one-shot classification problem. The proposed framework does not require domain knowledge, making it potentially portable to other domains. We show that our algorithm improves accuracy from 95.5% to 96.1% on the Omniglot dataset 20-way one-shot learning compared to current state-of-the-art.","abstract_has_math":false,"creators":["Guo, Hanyu"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering (Holcomb Dept. of)","degree_department":null,"school":null,"contributors":["Dr. Melissa C. Smith, Committee Chair","Dr. Walter B. Ligon III","Dr. Adam W. Hoover"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:16:45Z","subjects":["generative model","meta learning","metric learning","one-shot learning","sequential model"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/2792","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/2792","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-3799","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Melissa C. Smith, Committee Chair","Dr. Walter B. Ligon III","Dr. Adam W. Hoover"]},{"key":"dc:creator","label":"Author","values":["Guo, Hanyu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2017-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering (Holcomb Dept. of)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["generative model","meta learning","metric learning","one-shot learning","sequential model"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/2792"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Regardless of the Deep Learning community's continuous advancements, the challenging domain of one-shot learning still persists. While the human brain is capable of learning a new visual concept with ease, sometimes even at a glance, Deep Learning-based techniques show serious drawbacks in handling problems with small datasets. Much of the existing work on one-shot learning employs a variety of sophisticated network algorithms, prior domain knowledge, and data manipulation to address the generalization challenges presented in such problems. In this work, we demonstrate a one-shot learning method that contains three learning networks â€” a deep sequential generative model, a candidate network, and a Matching Network â€” thus offering an alternative approach to solving the one-shot classification problem. The proposed framework does not require domain knowledge, making it potentially portable to other domains. We show that our algorithm improves accuracy from 95.5% to 96.1% on the Omniglot dataset 20-way one-shot learning compared to current state-of-the-art."]},{"key":"dc:title","label":"Title","values":["One-shot Learning In Deep Sequential Generative Models"]}]}],"canonical_facts":{"dc:contributor":["Dr. Melissa C. Smith, Committee Chair","Dr. Walter B. Ligon III","Dr. Adam W. Hoover"],"dc:creator":["Guo, Hanyu"],"dc:date.created":["2017-12-01T08:00:00Z"],"dc:description.abstract":["Regardless of the Deep Learning community's continuous advancements, the challenging domain of one-shot learning still persists. While the human brain is capable of learning a new visual concept with ease, sometimes even at a glance, Deep Learning-based techniques show serious drawbacks in handling problems with small datasets. Much of the existing work on one-shot learning employs a variety of sophisticated network algorithms, prior domain knowledge, and data manipulation to address the generalization challenges presented in such problems. In this work, we demonstrate a one-shot learning method that contains three learning networks â€” a deep sequential generative model, a candidate network, and a Matching Network â€” thus offering an alternative approach to solving the one-shot classification problem. The proposed framework does not require domain knowledge, making it potentially portable to other domains. We show that our algorithm improves accuracy from 95.5% to 96.1% on the Omniglot dataset 20-way one-shot learning compared to current state-of-the-art."],"dc:identifier":["https://open.clemson.edu/all_theses/2792"],"dc:subject":["generative model","meta learning","metric learning","one-shot learning","sequential model"],"dc:title":["One-shot Learning In Deep Sequential Generative Models"],"thesis:degree_discipline":["Electrical and Computer Engineering (Holcomb Dept. of)"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:16:45Z"}