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 9 of 9 for “"Information Bottleneck"”.

  1. 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.

    cape-town Repository record for Unsupervised connectivity-based cortex parcellation using the information bottleneck method (opens in a new tab)

  2. Information Retrieval with Dense and Sparse Representations

    Information retrieval, at the core of numerous applications such as search engines and open-domain question-answering systems, relies on effective textual representation and semantic matching. However, current approaches can lose nuanced lexical detail information due to an information bottleneck

    mit Repository record for Information Retrieval with Dense and Sparse Representations (opens in a new tab)

  3. 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 …

    ottawa-retro Repository record for Aggregated Learning: An Information Theoretic Framework to Learning with Neural Networks (opens in a new tab)

  4. 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 …

    uts Repository record for Chest X-Ray Image Classification with Deep Learning (opens in a new tab)

  5. Statistical Methods for Out-of-distribution Detection

    … auxiliary network to capture the OOD-sensitive information for the network? This thesis systematically studies how to effectively solve the aforementioned issues with experimental and theoretical support. Due to the significant difference between ID and OOD samples, it is essential to consider …

    uts Repository record for Statistical Methods for Out-of-distribution Detection (opens in a new tab)

  6. Speech perception in a sparse domain

    … dynamic range of hearing. Thus there is an information bottleneck, whereby these devices must transform acoustical sounds with a large dynamic range into the smaller range of hearing impaired listeners. The limited dynamic range problem can be thought of as a communication channel with …

    soton Repository record for Speech perception in a sparse domain (opens in a new tab)

  7. Large Scale Machine Learning in Biology

    … used in spectral clustering and the relevance information as defined in the Information Bottleneck method. For fast-mixing graphs, we show that the regularized min-cut cost functions introduced by Shi and Malik over a decade ago can be well approximated as the rate of loss of predictive …

    columbia-diss Repository record for Large Scale Machine Learning in Biology (opens in a new tab)

  8. Deep concept reasoning: beyond the accuracy-interpretability trade-off

    … enables Concept Embedding Models to overcome the information bottleneck, enabling them to achieve state-of-the-art accuracy without sacrificing model transparency. The fourth work addresses the limitations of Concept Embeddings Models which are unable to provide concept-based logic explanations …

    cambridge Repository record for Deep concept reasoning: beyond the accuracy-interpretability trade-off (opens in a new tab)

  9. The complexity of joint computation

    … methods for this model. First, we study an information-theoretic lower-bound method due to Cherukhin, which gave the first improvement over the lower bounds provided by the well-known superconcentrator technique for constant depths. (The lower bounds are still barelysuperlinear, however) …

    mit Repository record for The complexity of joint computation (opens in a new tab)