Deep learning techniques for music recommendation (doctoral work)
E786387
"Deep learning techniques for music recommendation (doctoral work)" is Sander Dieleman’s PhD thesis that pioneered the application of deep neural networks to improve automated music recommendation and discovery.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Deep learning techniques for music recommendation (doctoral work) canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T9245168 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deep learning techniques for music recommendation (doctoral work) Context triple: [Sander Dieleman, notableWork, Deep learning techniques for music recommendation (doctoral work)]
-
A.
Human Jukebox
Human Jukebox is the renowned marching band of Southern University, celebrated for its high-energy performances, intricate formations, and influential role in HBCU band culture.
-
B.
Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
-
C.
The Well-Tempered Synthesizer
The Well-Tempered Synthesizer is a pioneering 1969 electronic music album by Wendy Carlos that features Baroque and classical works performed on Moog synthesizers, helping to popularize synthesized music.
-
D.
Music Genome Project
The Music Genome Project is a comprehensive music analysis system that categorizes songs by hundreds of musical attributes to power personalized listening recommendations.
-
E.
Neural Filters
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Deep learning techniques for music recommendation (doctoral work) Target entity description: "Deep learning techniques for music recommendation (doctoral work)" is Sander Dieleman’s PhD thesis that pioneered the application of deep neural networks to improve automated music recommendation and discovery.
-
A.
Human Jukebox
Human Jukebox is the renowned marching band of Southern University, celebrated for its high-energy performances, intricate formations, and influential role in HBCU band culture.
-
B.
Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
-
C.
The Well-Tempered Synthesizer
The Well-Tempered Synthesizer is a pioneering 1969 electronic music album by Wendy Carlos that features Baroque and classical works performed on Moog synthesizers, helping to popularize synthesized music.
-
D.
Music Genome Project
The Music Genome Project is a comprehensive music analysis system that categorizes songs by hundreds of musical attributes to power personalized listening recommendations.
-
E.
Neural Filters
Neural Filters are Adobe Photoshop’s AI-powered tools that apply advanced, machine-learning-based adjustments and creative effects to images with minimal manual editing.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
PhD thesis
ⓘ
doctoral thesis ⓘ |
| academicDegree | Doctor of Philosophy ⓘ |
| aim |
to improve personalization in music recommendation
ⓘ
to learn music representations directly from audio ⓘ to reduce reliance on hand-crafted audio features ⓘ |
| author | Sander Dieleman ⓘ |
| availableAs | PDF ⓘ |
| completionYear | 2016 ⓘ |
| contribution |
improved automated music recommendation quality
ⓘ
improved music discovery in large catalogs ⓘ pioneered application of deep learning to music recommendation ⓘ |
| country | Belgium ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ music information retrieval ⓘ recommender systems ⓘ |
| focusesOn |
automated recommendation
ⓘ
music discovery ⓘ music recommendation ⓘ |
| hasAuthor |
Dieleman, Sander
ⓘ
linked to:
Sander Dieleman
|
| hasAuthorAffiliationAtTimeOfThesis | Department of Electronics and Information Systems, Ghent University ⓘ |
| hasAuthorORCID | 0000-0002-4974-0043 ⓘ |
| hasKeyword |
audio analysis
ⓘ
deep learning ⓘ music recommendation ⓘ neural networks ⓘ recommender systems ⓘ representation learning ⓘ |
| institution | Ghent University ⓘ |
| language | English ⓘ |
| relatedTo |
collaborative filtering
ⓘ
content-based filtering ⓘ hybrid recommendation systems ⓘ music streaming services ⓘ |
| repository |
Ghent University Academic Bibliography
ⓘ
linked to:
Ghent University Library
|
| supervisor | Benjamin Schrauwen ⓘ |
| topic |
audio feature learning
ⓘ
large-scale music catalogs ⓘ music similarity modeling ⓘ user–item recommendation ⓘ |
| type | dissertation ⓘ |
| usesMethod |
content-based recommendation
ⓘ
convolutional neural networks ⓘ deep neural networks ⓘ representation learning ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Deep learning techniques for music recommendation (doctoral work) Description of subject: "Deep learning techniques for music recommendation (doctoral work)" is Sander Dieleman’s PhD thesis that pioneered the application of deep neural networks to improve automated music recommendation and discovery.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.