Multi-modal learning with generalizable nonlinear dimensionality reduction

Kaya, Semih
Thanks to significant advancements in information technologies, people can acquire various types of data from the universe. This data may include multiple features in different domains. Widespread machine learning methods benefit from distinctive features of data to reach desired outputs. Numerous studies demonstrate that machine learning algorithms that make use of multi-modal representations of data have more potential than methods with single modal structure. This potential comes from the mutual agreement of modalities and the existence of additional information. In this thesis, we introduce a multi-modal supervised learning algorithm to represent the data in lower dimensions. We intend to increase within-class similarity and between-class discrimination for intra- and inter-modal exemplars by a generalizable nonlinear interpolator, which satisfies Lipschitz continuity. In order to measure the performance of the proposed supervised learning algorithm, we have conducted several multi-modal face recognition and image-text retrieval experiments on frequently used multi-modal data sets in the literature and achieved quite satisfactory classification and retrieval accuracy in comparison with existing multi-modal learning approaches. These experimental findings suggest that the incorporation of the generalizability of the embedding to the whole ambient space and unseen test data in the learning objective yields promising performance gains in multi-modal representation learning.


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...
Explainable Security in SDN-Based IoT Networks
Sarica, Alper Kaan; Angın, Pelin (2020-12-01)
The significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networking (SDN) and network functions virtualization for achieving the promised quality of service. The prevalence of IoT and the large attack surface that it has created calls for SDN-based intelligent security solut...
Gökalp, Mert Onuralp; Kayabay, Kerem; Eren, Pekin Erhan; Koçyiğit, Altan (2016-12-17)
Exponential growth in data volume originating from Internet of Things sources and information services drives the industry to develop new models and distributed tools to handle big data. In order to achieve strategic advantages, effective use of these tools and integrating results to their business processes are critical for enterprises. While there is an abundance of tools available in the market, they are underutilized by organizations due to their complexities. Deployment and usage of big data analysis t...
Cross-modal Representation Learning with Nonlinear Dimensionality Reduction
KAYA, SEMİH; Vural, Elif (2019-08-22)
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 e...
Biological data integration and relation prediction by matrix factorization
Abay, Gökçe; Acar, Aybar Can; Department of Bioinformatics (2020)
The available molecular sequence data has increased greatly in the last decades, thanks to the new technological developments in the field of life-sciences. In order for this data to be useful to the scientific community, it should be characterized. Traditionally, this characterization is done manually, where the experimentally produced molecular data is curated and stored in the biological databases. The huge volume of the currently available data summons the need for the automatic and systematic analysis....
Citation Formats
S. Kaya, “Multi-modal learning with generalizable nonlinear dimensionality reduction,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Electrical and Electronics Engineering., Middle East Technical University, 2019.