Cross-modal Representation Learning with Nonlinear Dimensionality Reduction

2019-08-22
KAYA, SEMİH
Vural, Elif
In many problems in machine learning there exist relations between data collections from different modalities. The purpose of multi-modal learning algorithms is to efficiently use the information present in different modalities when solving multi-modal retrieval problems. In this work, a multi-modal representation learning algorithm is proposed, which is based on nonlinear dimensionality reduction. Compared to linear dimensionality reduction methods, nonlinear methods provide more flexible representations especially when there is high discrepancy between the structures of different modalities. In this work, we propose to align different modalities by mapping same-class training data from different modalities to nearby coordinates, while we also learn a Lipschitz-continuous interpolation function that generalizes the learnt representation to the whole data space. Experiments in image-text retrieval applications show that the proposed method yields high performance when compared to multi-modal learning methods in the literature.

Suggestions

Multi-Modal Learning With Generalizable Nonlinear Dimensionality Reduction
KAYA, SEMİH; Vural, Elif (2019-08-26)
In practical machine learning settings, there often exist relations or links between data from different modalities. The goal of multimodal learning algorithms is to efficiently use the information available in different modalities to solve multi-modal classification or retrieval problems. In this study, we propose a multi-modal supervised representation learning algorithm based on nonlinear dimensionality reduction. Nonlinear embeddings often yield more flexible representations compared to linear counterpa...
On numerical optimization theory of infinite kernel learning
Ozogur-Akyuz, S.; Weber, Gerhard Wilhelm (2010-10-01)
In Machine Learning algorithms, one of the crucial issues is the representation of the data. As the given data source become heterogeneous and the data are large-scale, multiple kernel methods help to classify "nonlinear data". Nevertheless, the finite combinations of kernels are limited up to a finite choice. In order to overcome this discrepancy, a novel method of "infinite" kernel combinations is proposed with the help of infinite and semi-infinite programming regarding all elements in kernel space. Look...
MODELLING OF KERNEL MACHINES BY INFINITE AND SEMI-INFINITE PROGRAMMING
Ozogur-Akyuz, S.; Weber, Gerhard Wilhelm (2009-06-03)
In Machine Learning (ML) algorithms, one of the crucial issues is the representation of the data. As the data become heterogeneous and large-scale, single kernel methods become insufficient to classify nonlinear data. The finite combinations of kernels are limited up to a finite choice. In order to overcome this discrepancy, we propose a novel method of "infinite" kernel combinations for learning problems with the help of infinite and semi-infinite programming regarding all elements in kernel space. Looking...
Probability learning in normal and parkinson subjects: the effect of reward, context, and uncertainty
Erdeniz, Burak; Gökçay, Didem; Department of Cognitive Sciences (2007)
In this thesis, the learning of probabilistic relationships between stimulus-action pairs is investigated under the probability learning paradigm. The effect of reward is investigated in the first three experiments. Additionally, the effect of context and uncertainty is investigated in the second and third experiments, respectively. The fourth experiment is the replication of the second experiment with a group of Parkinson patients where the effect of dopamine medication on probability learning is studied. ...
Nonlinear supervised dimensionality reduction via smooth regular embeddings
Ornek, Cem; Vural, Elif (2019-03-01)
The recovery of the intrinsic geometric structures of data collections is an important problem in data analysis. Supervised extensions of several manifold learning approaches have been proposed in the recent years. Meanwhile, existing methods primarily focus on the embedding of the training data, and the generalization of the embedding to initially unseen test data is rather ignored. In this work, we build on recent theoretical results on the generalization performance of supervised manifold learning algori...
Citation Formats
S. KAYA and E. Vural, “Cross-modal Representation Learning with Nonlinear Dimensionality Reduction,” 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48311.