Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 46 for “"information bottleneck"”.
-
Generalized Information Bottleneck
… rate of a source signal due to the capacity bottleneck of an information channel. Classical rate-distortion theory and information bottleneck method lay the theoretical foundations for lossy data compression from an information-theoretic perspective. However, in reality there are a wide …
-
Unsupervised connectivity-based cortex parcellation using the information bottleneck method
In this dissertation, we embody an information-theoretic framework to compress and therefore cluster anatomical connectivity data that avoids many assumptions and drawbacks imposed by previous methods.
-
Information Bottleneck Methods for Fairness and Privacy in Machine Learning
… and also private, not revealing users’ personal information, has become of paramount importance for society to accept the widespread use of artificial intelligence (AI) for critical applications. In this thesis, we investigate the use of variational Information Bottleneck (IB) methods for fair …
-
Efficient Deep Learning Models with Autoencoder Regularization and Information Bottleneck Compression
… and compression to improve speed. Due to the information-restricting nature of regularization, these two methods are related. Firstly we present a novel autoencoder architecture as a method of regularization for Pedestrian Detection. Secondly, we present a hyperparameter-free, iterative …
-
A pilot study of web-based information bottleneck identification in AEC projects
… heavily on the effective communication and information exchange between project team members. A prominent reason for delays and progress shortcomings in AEC project teams is information bottlenecks, defined as missing project information bits which can be due to large influx of information …
-
The impact of Web technology on customer information flow
… School's Housing Welcome Center is stymied by an information bottleneck at the junction of its counselors and customers. Incoming classes decry housing for its poor communication and lack of information. Housing counselors, ever aware of customer satisfaction, spend too much time transacting …
-
Rate-Limited Quantum-To-Classical Optimal Transport
… is to realize a transport mapping through an information bottleneck. As the optimal mapping may induce infinite mutual information between the source and the destination, the existence of an information bottleneck forces one to resort to some suboptimal mappings. Investigating this type of …
-
Hilbert-Space Quantum Neural Representation Learning for NISQ-Era Quantum Computing
… addresses the challenge of the ”Representation Bottleneck” by establishing a framework for resource-efficient quantum representation learning. The research demonstrates that effective learning on near-term devices can be achieved by optimizing circuit architectures and objective functions to …
-
Study of Fundamental Tradeoff Between Deliverable and Private Information in Statistical Inference
… tradeoff between deliverable and private information in statistical inference. My research was partly motivated by arising and prevailing privacy concerns of users in many machine learning problems. In this dissertation, I begin by introducing examples where I am concerned of privacy …
-
Aggregated Learning: An Information Theoretic Framework to Learning with Neural Networks
… a novel approach to solve this problem under the Information Bottleneck (IB) principle. Based on the IB principle, we associate with the classification problem a representation learning problem, which we call ``IB learning". A careful investigation shows there is an unconventional quantization …
-
Emotionally Intelligent Voice Language Models For Mental Health Therapy
… a process that discards crucial paralinguistic information. This information bottleneck limits the AI's ability to perceive critical emotional cues and broader psychological states, hindering its capacity to reason over human voice and provide effective therapy. This thesis details the …
-
Electrophysiological, Behavioral, and Histological Assessment of the Thalamocortical Network as a Stimulation Target for Central Auditory Neuroprostheses
… geniculate body (MGV). Thalamus represents an information bottleneck through which many sensory systems send information. Primary (MGV) and non-primary (MGD, MGM) subdivisions provide parallel auditory inputs to cortex and receive feedback excitation and inhibition from cortex and thalamic …
-
Explaining Deep Neural Networks using Information Theory and Geometry
… of giants and explore two extensions to the information bottleneck (IB) principle, which formalises the idea that DNNs are ultimately compression machines which turn input data into minimal sufficient representations. The first extension is based on geometry and replaces the …
-
Domain Adaptation and Privileged Information for Visual Recognition
… knowledge is better identified by additional information, available during training. Depending on the nature of such information, the learning problem may turn into domain adaptation (DA), domain generalization (DG), leaning using privileged information (LUPI), or domain adaptation with …
-
Analysis and applications of deep cascade learning
… the process of learning using Tishby et al.s’ Information Bottleneck theory, we derive an empirical rule (Information Transition Ratio) to automatically determine a satisfactory depth for Deep Neural Networks. We suggest that Cascade Learning packs information in a hierarchical manner, with …
-
An Empirical Comparison of Multi-Agent LLM Architectural Patterns for Automated Unit Test Generation
… hierarchical pattern suffered from supervisor information bottleneck according to the qualitative results confirmed by 100% of the failing tasks of the architecture. These results come from a single LLM, a single benchmark, and non-optimized prompts per architecture, which means replication is …
-
Chest X-Ray Image Classification with Deep Learning
… ConsultNet consists of a variational selective information bottleneck branch and a spatial-and-channel encoding branch. These two branches learn discriminative features collaboratively. In addition, each of the proposed methods is comprehensively verified and analysed by conducting various …
-
Towards Secure and Privacy-Preserving Machine Learning Systems
… a novel membership inference attack based on information bottleneck theory to compromise confidentiality. Second, in the physical domain, I explore integrity threats by crafting physically realizable adversarial examples against automatic speech recognition systems deployed in video …
-
Object Segmentation Reasoning
… that this disjoint architecture imposes an information bottleneck and limits end-to-end optimization. To overcome these structural limitations, the project pivots to a second, novel approach: End-to-End VLM Segmentation. This method fine-tunes a VLM to directly generate structured geometric …
-
Information theoretic clustering of astrobiology documents
… without the aid of labeled data samples. The Information Bottleneck method [43] was employed for this project because it has been shown to be one of the most accurate and robust methods of clustering unlabeled multi-dimensional data such as text [40, 4]. Within this same framework, it also is …
Page 1 of 3