2026-09-19T22:36:28Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1590902025-10-04T03:17:47Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Katz, Boris
Duitama Cortes, Juan Sebastian
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-04-14T14:04:58Z
2025-04-14T14:04:58Z
2025-02
2025-04-03T14:06:13.351Z
https://hdl.handle.net/1721.1/159090
This work makes two contributions: the evaluation of early stop guidance for deep Fully Connected Networks (FCNs) and the introduction of guidance as an initialization method (GIM). Network initialization has been a meaningful and challenging topic in the field of machine learning (ML) for a long time. Many initialization methods exist, ranging from data-independent to data-dependent approaches. Initializations allow for a better understanding of model behavior and improvements in model performance. The novel guidance tool enabled us to propose GIM, a new technique that initializes a model by leveraging representational similarity with respect to models of different architectures. A model with an architecture that performs poorly in a specific task can be initialized with guidance from a model with an architecture that performs well in the respective task. We focus on the case of FCNs in the task of image classification and provide experimental results to validate our approach.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
GIM: Guidance as Initialization Method
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="e7f7f64e-1933-4e9b-9abb-6ab942038b9f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>GIM: Guidance as Initialization Method</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Duitama Cortes, Juan Sebastian</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>This work makes two contributions: the evaluation of early stop guidance for deep Fully Connected Networks (FCNs) and the introduction of guidance as an initialization method (GIM). Network initialization has been a meaningful and challenging topic in the field of machine learning (ML) for a long time. Many initialization methods exist, ranging from data-independent to data-dependent approaches. Initializations allow for a better understanding of model behavior and improvements in model performance. The novel guidance tool enabled us to propose GIM, a new technique that initializes a model by leveraging representational similarity with respect to models of different architectures. A model with an architecture that performs poorly in a specific task can be initialized with guidance from a model with an architecture that performs well in the respective task. We focus on the case of FCNs in the task of image classification and provide experimental results to validate our approach.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>