Matches in SemOpenAlex for { <https://semopenalex.org/work/W133093151> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W133093151 abstract "This thesis studies two properties—monotonicity and connectedness—in the context of machine learning. The first part of the thesis examines the role of monotonicity constraints in machine learning from both practical and theoretical perspectives. Two techniques for enforcing monotonicity in machine learning models are proposed. The first method adds to the objective function a penalty term measuring the degree to which the model violates monotonicity. The penalty term can be interpreted as a Bayesian prior favoring functions which obey monotonicity. This method has the potential to enforce monotonicity only approximately, making it appropriate for situations where strict monotonicity may not hold. The second approach consists of a model which is monotonic by virtue of functional form. This model is shown to have universal approximation capabilities with respect to the class M of monotonic functions. A variety of theoretical results are also presented regarding M. The generalization behavior of this class is shown to depend heavily on the probability distribution over the input space. Although the VC dimension of M is ∞, the VC entropy (i.e., the expected number of dichotomies) is modest for many distributions, allowing us to obtain bounds on the generalization error. Monte Carlo techniques for estimating the capacity and VC entropy of M are presented. The second part of the thesis considers broader issues in learning theory. Generalization error bounds based on the VC dimension describe a function class by counting the number of dichotomies it induces. In this thesis, a more detailed characterization is presented which takes into account the diversity of a set of dichotomies in addition to its cardinality. Many function classes in common usage are shown to possess a property called connectedness . Models with this property induce dichotomy sets which are highly clustered and have little diversity. We derive an improvement to the VC bound which applies to function classes with the connectedness property." @default.
- W133093151 created "2016-06-24" @default.
- W133093151 creator A5056504335 @default.
- W133093151 date "1998-12-01" @default.
- W133093151 modified "2023-09-26" @default.
- W133093151 title "Monotonicity and connectedness in learning systems" @default.
- W133093151 hasPublicationYear "1998" @default.
- W133093151 type Work @default.
- W133093151 sameAs 133093151 @default.
- W133093151 citedByCount "0" @default.
- W133093151 crossrefType "dissertation" @default.
- W133093151 hasAuthorship W133093151A5056504335 @default.
- W133093151 hasConcept C106301342 @default.
- W133093151 hasConcept C118615104 @default.
- W133093151 hasConcept C119322782 @default.
- W133093151 hasConcept C121332964 @default.
- W133093151 hasConcept C126255220 @default.
- W133093151 hasConcept C134306372 @default.
- W133093151 hasConcept C144237770 @default.
- W133093151 hasConcept C154945302 @default.
- W133093151 hasConcept C15744967 @default.
- W133093151 hasConcept C177148314 @default.
- W133093151 hasConcept C201943243 @default.
- W133093151 hasConcept C28826006 @default.
- W133093151 hasConcept C33923547 @default.
- W133093151 hasConcept C41008148 @default.
- W133093151 hasConcept C542102704 @default.
- W133093151 hasConcept C62520636 @default.
- W133093151 hasConcept C72169020 @default.
- W133093151 hasConceptScore W133093151C106301342 @default.
- W133093151 hasConceptScore W133093151C118615104 @default.
- W133093151 hasConceptScore W133093151C119322782 @default.
- W133093151 hasConceptScore W133093151C121332964 @default.
- W133093151 hasConceptScore W133093151C126255220 @default.
- W133093151 hasConceptScore W133093151C134306372 @default.
- W133093151 hasConceptScore W133093151C144237770 @default.
- W133093151 hasConceptScore W133093151C154945302 @default.
- W133093151 hasConceptScore W133093151C15744967 @default.
- W133093151 hasConceptScore W133093151C177148314 @default.
- W133093151 hasConceptScore W133093151C201943243 @default.
- W133093151 hasConceptScore W133093151C28826006 @default.
- W133093151 hasConceptScore W133093151C33923547 @default.
- W133093151 hasConceptScore W133093151C41008148 @default.
- W133093151 hasConceptScore W133093151C542102704 @default.
- W133093151 hasConceptScore W133093151C62520636 @default.
- W133093151 hasConceptScore W133093151C72169020 @default.
- W133093151 hasLocation W1330931511 @default.
- W133093151 hasOpenAccess W133093151 @default.
- W133093151 hasPrimaryLocation W1330931511 @default.
- W133093151 hasRelatedWork W136726725 @default.
- W133093151 hasRelatedWork W1479941284 @default.
- W133093151 hasRelatedWork W1590693676 @default.
- W133093151 hasRelatedWork W1967790881 @default.
- W133093151 hasRelatedWork W2047138585 @default.
- W133093151 hasRelatedWork W2102641994 @default.
- W133093151 hasRelatedWork W2134547831 @default.
- W133093151 hasRelatedWork W2143345670 @default.
- W133093151 hasRelatedWork W2641114818 @default.
- W133093151 hasRelatedWork W2906219218 @default.
- W133093151 hasRelatedWork W2934590717 @default.
- W133093151 hasRelatedWork W2950198771 @default.
- W133093151 hasRelatedWork W2953367795 @default.
- W133093151 hasRelatedWork W2962822332 @default.
- W133093151 hasRelatedWork W2963262705 @default.
- W133093151 hasRelatedWork W3045338440 @default.
- W133093151 hasRelatedWork W3096606498 @default.
- W133093151 hasRelatedWork W3128950307 @default.
- W133093151 hasRelatedWork W3141940925 @default.
- W133093151 hasRelatedWork W3201509537 @default.
- W133093151 isParatext "false" @default.
- W133093151 isRetracted "false" @default.
- W133093151 magId "133093151" @default.
- W133093151 workType "dissertation" @default.