{"id":{"repo_id":"freiburg-diss","oai_identifier":"oai:freidok.uni-freiburg.de:203"},"canonical_url":"https://search.dev.ndltd.org/etd/freiburg-diss/oai:freidok.uni-freiburg.de:203","repository":{"repo_id":"freiburg-diss","name":"University of Freiburg","base_url":"https://freidok.uni-freiburg.de/oai/oai2.php"},"display":{"title":"Probabilistic Learning of Indexed Families under Monotonicity Constraints: Hierarchy Results and Complexity Aspects","abstract":"In our work, we deal with a formalization of inductive inference. We investigate a class of probabilistic inductive inference models, namely probabilistic inductive inference of indexed families under <br>monotonicity constraints. All these inference models are based <br>on the inductive inference model introduced by Gold. We <br>discuss in detail how powerful these probabilistic learning models <br>are in contrast to their deterministic counterparts and introduce <br>a complexity measure in order to measure the additional power of <br>the probabilistic machines in qualitative terms.","abstract_html":"In our work, we deal with a formalization of inductive inference. We investigate a class of probabilistic inductive inference models, namely probabilistic inductive inference of indexed families under &lt;br&gt;monotonicity constraints. All these inference models are based &lt;br&gt;on the inductive inference model introduced by Gold. We &lt;br&gt;discuss in detail how powerful these probabilistic learning models &lt;br&gt;are in contrast to their deterministic counterparts and introduce &lt;br&gt;a complexity measure in order to measure the additional power of &lt;br&gt;the probabilistic machines in qualitative terms.","abstract_has_math":false,"creators":["Meyer, Lea"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Schinzel, Britta"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T02:21:30Z","subjects":["Induktive Inferenz","Probabilistisches Lernen","Formale Sprachen","Inductive Inference","Probabilistic Learning","Complexity Theory"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://freidok.uni-freiburg.de/data/203","outbound_label":"Repository record","outbound_source":"source_url"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schinzel, Britta"]},{"key":"dc:creator","label":"Author","values":["Meyer, Lea"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["DoctoralThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Induktive Inferenz","Probabilistisches Lernen","Formale Sprachen","Inductive Inference","Probabilistic Learning","Complexity Theory"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In our work, we deal with a formalization of inductive inference. We investigate a class of probabilistic inductive inference models, namely probabilistic inductive inference of indexed families under <br>monotonicity constraints. All these inference models are based <br>on the inductive inference model introduced by Gold. We <br>discuss in detail how powerful these probabilistic learning models <br>are in contrast to their deterministic counterparts and introduce <br>a complexity measure in order to measure the additional power of <br>the probabilistic machines in qualitative terms."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Probabilistic Learning of Indexed Families under Monotonicity Constraints: Hierarchy Results and Complexity Aspects","Probabilistisches Lernen von indizierten Familien unter Monotoniekriterien: Hierarchie-Ergebnisse und Komplexitätsaspekte"]}]}],"canonical_facts":{"dc:contributor":["Schinzel, Britta"],"dc:creator":["Meyer, Lea"],"dc:description.abstract":["In our work, we deal with a formalization of inductive inference. We investigate a class of probabilistic inductive inference models, namely probabilistic inductive inference of indexed families under <br>monotonicity constraints. All these inference models are based <br>on the inductive inference model introduced by Gold. We <br>discuss in detail how powerful these probabilistic learning models <br>are in contrast to their deterministic counterparts and introduce <br>a complexity measure in order to measure the additional power of <br>the probabilistic machines in qualitative terms."],"dc:format.medium":["application/pdf"],"dc:subject":["Induktive Inferenz","Probabilistisches Lernen","Formale Sprachen","Inductive Inference","Probabilistic Learning","Complexity Theory"],"dc:title":["Probabilistic Learning of Indexed Families under Monotonicity Constraints: Hierarchy Results and Complexity Aspects","Probabilistisches Lernen von indizierten Familien unter Monotoniekriterien: Hierarchie-Ergebnisse und Komplexitätsaspekte"],"dc:type":["DoctoralThesis"]},"updated_at":"2026-07-24T02:21:30Z"}