检索结果-内蒙古大学图书馆

Applications of the free energy principle to machine learning and neuroscience

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Millidge, Beren Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh

In this thesis, we explore and apply methods inspired by the free energy principle to two important areas in machine learning and neuroscience. The free energy principle is a general mathematical theory of the necessary information-theoretic behaviours of systems which maintain a separation from their environment. A core postulate of the theory is that complex systems can be seen as performing variational Bayesian inference and minimizing an information-theoretic quantity called the variational free energy. The free energy principle originated in, and has been extremely influential in theoretical neuroscience, having spawned a number of neurophysiologically realistic process theories, and maintaining close links with Bayesian Brain viewpoints. The thesis is split into three main parts where we apply methods and insights from the free energy principle to understand questions first in perception, then action, and finally learning. Specifically, in the first section, we focus on the theory of predictive coding, a neurobiologically plausible process theory derived from the free energy principle under certain assumptions, which argues that the primary function of the brain is to minimize prediction errors. We focus on scaling up predictive coding architectures and simulate large-scale predictive coding networks for perception on machine learning benchmarks;we investigate predictive coding's relationship to other classical filtering algorithms, and we demonstrate that many biologically implausible aspects of current models of predictive coding can be relaxed without unduly harming the performance of predictive coding models which allows for a potentially more literal translation of predictive coding theory into cortical microcircuits. In the second part of the thesis, we focus on the application of methods deriving from the free energy principle to action. We study the extension of methods of 'active inference', a neurobiologically grounded account of action through varia

关键词： Benchmarking

QuickQual: Lightweight, convenient retinal image quality scoring with off-the-shelf pretrained models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Engelmann, Justin Storkey, Amos Bernabeu, Miguel O. Centre for Medical Informatics Usher Institute University of Edinburgh Edinburgh United Kingdom Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh Edinburgh United Kingdom The Bayes Centre University of Edinburgh Edinburgh United Kingdom

Image quality remains a key problem for both traditional and deep learning (DL)-based approaches to retinal image analysis, but identifying poor quality images can be time consuming and subjective. Thus, automated methods for retinal image quality scoring (RIQS) are needed. The current state-of-the-art is MCFNet, composed of three Densenet121 backbones each operating in a different colour space. MCFNet, and the EyeQ dataset released by the same authors, was a huge step forward for RIQS. We present QuickQual, a simple approach to RIQS, consisting of a single "off-the-shelf" ImageNet-pretrained Densenet121 backbone plus a Support Vector Machine (SVM). QuickQual performs very well, setting a new state-of-the-art for EyeQ (Accuracy: 88.50% vs 88.00% for MCFNet;AUC: 0.9687 vs 0.9588). This suggests that RIQS can be solved with generic "perceptual" features learned on natural images, as opposed to requiring DL models trained on large amounts of fundus images. Additionally, we propose a Fixed Prior linearisation scheme, that converts EyeQ from a 3-way classification to a continuous logistic regression task. For this task, we present a second model, QuickQual MEga Minified Estimator (QuickQual-MEME), that consists of only 10 parameters on top of an off-the-shelf Densenet121 and can distinguish between gradable and ungradable images with an accuracy of 89.18% (AUC: 0.9537). Code and model are available on GitHub. QuickQual is so lightweight, that the entire inference code (and even the parameters for QuickQual-MEME) is already contained in this paper. Copyright © 2023, The Authors. All rights reserved.

关键词： Image quality

l KU_AIGEN_ICL_EDI@BC8 Track 3: Advancing Phenotype Named Entity Recognition and Normalization for Dysmorphology Physical Examination Reports

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kim, Hajung Kim, Chanhwi Sohn, Jiwoong Beck, Tim Rei, Marek Kim, Sunkyu Simpson, T. Ian Posma, Joram M. Lain, Antoine Sung, Mujeen Kang, Jaewoo Department of Computer Science and Engineering Korea University Korea Republic of Department of Metabolism Digestion and Reproduction Imperial College London United Kingdom AIGEN Sciences Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh United Kingdom School of Medicine University of Nottingham United Kingdom Department of Computer Science Imperial College London United Kingdom

The objective of BioCreative8 Track 3 is to extract phenotypic key medical findings embedded within EHR texts and subsequently normalize these findings to their Human Phenotype Ontology (HPO) terms. However, the presence of diverse surface forms in phenotypic findings makes it challenging to accurately normalize them to the correct HPO terms. To address this challenge, we explored various models for named entity recognition and implemented data augmentation techniques such as synonym marginalization to enhance the normalization step. Our pipeline resulted in an exact extraction and normalization F1 score 2.6% higher than the mean score of all submissions received in response to the challenge. Furthermore, in terms of the normalization F1 score, our approach surpassed the average performance by 1.9%. These findings contribute to the advancement of automated medical data extraction and normalization techniques, showcasing potential pathways for future research and application in the biomedical domain. © 2025, CC BY.

关键词： Text mining

Building population models for large-scale neural recordings: Opportunities and pitfalls

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hurwitz, Cole Kudryashova, Nina Onken, Arno Hennig, Matthias H. University of Edinburgh Institute for Adaptive and Neural Computation EdinburghEH8 9AB United Kingdom

Modern recording technologies now enable simultaneous recording from large numbers of neurons. This has driven the development of new statistical models for analyzing and interpreting neural population activity. Here we provide a broad overview of recent developments in this area. We compare and contrast different approaches, highlight strengths and limitations, and discuss biological and mechanistic insights that these methods provide. © 2021, CC0.

关键词：

Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Thornton, Christopher B. Kolehmainen, Niina Nazarpour, Kianoush Population Health Sciences Institute Faculty of Medical Sciences Newcastle University United Kingdom Great North Children's Hospital Newcastle upon Tyne NHS Hospitals Trust United Kingdom Institute for Adaptive and Neural Computation School of Informatics The University of Edinburgh United Kingdom

Accelerometers are widely used to measure physical activity behaviour, including in children. The traditional method for processing acceleration data uses cut points to define physical activity intensity, relying on calibration studies that relate the magnitude of acceleration to energy expenditure. However, these relationships do not generalise across diverse populations and hence they must be parametrised for each subpopulation (e.g., age groups) which is costly and makes studies across diverse populations and over time difficult. A data driven approach that allows physical activity intensity states to emerge from the data, without relying on parameters derived from external populations, and offers a new perspective on this problem and potentially improved results. We applied an unsupervised machine learning approach, namely a hidden semi Markov model, to segment and cluster the accelerometer data recorded from 279 children (9 to 38 months old) with a diverse range of physical and social-cognitive abilities (measured using the Paediatric Evaluation of Disability Inventory). We benchmarked this analysis with the cut points approach calculated using the best available thresholds for the population. Time spent active as measured by this unsupervised approach correlated more strongly with measures of the childs mobility, social-cognitive capacity, independence, daily activity, and age than that measured using the cut points approach. Unsupervised machine learning offers the potential to provide a more sensitive, appropriate, and cost-effective approach to quantifying physical activity behaviour in diverse populations, compared to the current cut points approach. This, in turn, supports research that is more inclusive of diverse or rapidly changing populations. © 2022, CC BY.

关键词： Accelerometers

Simulation-based Bayesian inference under model misspecification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kelly, Ryan P. Warne, David J. Frazier, David T. Nott, David J. Gutmann, Michael U. Drovandi, Christopher School of Mathematical Sciences Queensland University of Technology Australia Centre for Data Science Queensland University of Technology Australia Department of Econometrics and Business Statistics Monash University Australia Department of Statistics and Data Science National University of Singapore Singapore School of Informatics Institute for Adaptive & Neural Computation University of Edinburgh United Kingdom Centre of Excellence for the Mathematical Analysis of Cellular Systems Queensland University of Technology Australia

Simulation-based Bayesian inference (SBI) methods are widely used for parameter estimation in complex models where evaluating the likelihood is challenging but generating simulations is relatively straightforward. However, these methods commonly assume that the simulation model accurately reflects the true data-generating process, an assumption that is frequently violated in realistic scenarios. In this paper, we focus on the challenges faced by SBI methods under model misspecification. We consolidate recent research aimed at mitigating the effects of misspecification, highlighting three key strategies: i) robust summary statistics, ii) generalised Bayesian inference, and iii) error modelling and adjustment parameters. To illustrate both the vulnerabilities of popular SBI methods and the effectiveness of misspecification-robust alternatives, we present empirical results on an illustrative example. © 2025, CC BY.

关键词： neural network models

Detection of multiple retinal diseases in ultra-widefield fundus images using deep learning: data-driven identification of relevant regions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Engelmann, Justin McTrusty, Alice D. MacCormick, Ian J.C. Pead, Emma Storkey, Amos Bernabeu, Miguel O. UKRI CDT Biomedical AI University of Edinburgh United Kingdom Centre for Clinical Brain Sciences University of Edinburgh United Kingdom Institute for Adaptive and Neural Computation University of Edinburgh United Kingdom Centre for Medical Informatics University of Edinburgh United Kingdom

Ultra-widefield (UWF) imaging is a promising modality that captures a larger retinal field of view compared to traditional fundus photography. Previous studies showed that deep learning (DL) models are effective for detecting retinal disease in UWF images, but primarily considered individual diseases under less-than-realistic conditions (excluding images with other diseases, artefacts, comorbidities, or borderline cases;and balancing healthy and diseased images) and did not systematically investigate which regions of the UWF images are relevant for disease detection. We first improve on the state of the field by proposing a DL model that can recognise multiple retinal diseases under more realistic conditions. We then use global explainability methods to identify which regions of the UWF images the model generally attends to. Our model performs very well, separating between healthy and diseased retinas with an area under the curve (AUC) of 0.9206 on an internal test set, and an AUC of 0.9841 on a challenging, external test set. When diagnosing specific diseases, the model attends to regions where we would expect those diseases to occur. We further identify the posterior pole as the most important region in a purely data-driven fashion. Surprisingly, 10% of the image around the posterior pole is sufficient for achieving comparable performance to having the full images available. Copyright © 2022, The Authors. All rights reserved.

关键词： Poles

SLOctolyzer: Fully automatic analysis toolkit for segmentation and feature extracting in scanning laser ophthalmoscopy images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Burke, Jamie Gibbon, Samuel Engelmann, Justin Threlfall, Adam Giarratano, Ylenia Hamid, Charlene King, Stuart MacCormick, Ian J.C. MacGillivray, Tom School of Mathematics University of Edinburgh Edinburgh United Kingdom Robert O Curle Ophthalmology Suite Institute for Regeneration and Repair University of Edinburgh United Kingdom Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom School of Informatics University of Edinburgh Edinburgh United Kingdom Clinical Research Facility and Imaging University of Edinburgh Edinburgh United Kingdom Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh Edinburgh United Kingdom Centre for Clinical Brain Sciences University of Edinburgh Edinburgh United Kingdom

Purpose The purpose of this study was to introduce SLOctolyzer: an open-source analysis toolkit for en face retinal vessels in infrared reflectance scanning laser ophthalmoscopy (SLO) images. Methods SLOctolyzer includes two main modules: segmentation and measurement. The segmentation module uses deep learning methods to delineate retinal anatomy, and detects the fovea and optic disc, whereas the measurement module quantifies the complexity, density, tortuosity, and calibre of the segmented retinal vessels. We evaluated the segmentation module using unseen data and measured its reproducibility. Results SLOctolyzer’s segmentation module performed well against unseen internal test data (Dice for all-vessels = 0.91;arteries = 0.84;veins = 0.85;optic disc = 0.94;and fovea = 0.88). External validation against severe retinal pathology showed decreased performance (Dice for arteries = 0.72;veins = 0.75;and optic disc = 0.90). SLOctolyzer had good reproducibility (mean difference for fractal dimension = -0.001;density = -0.0003;calibre = -0.32 microns;and tortuosity density = 0.001). SLOctolyzer can process a 768 × 768 pixel macula-centred SLO image in under 20 seconds and a disc-centred SLO image in under 30 seconds using a laptop CPU. Conclusions To our knowledge, SLOctolyzer is the first open-source tool to convert raw SLO images into reproducible and clinically meaningful retinal vascular parameters. It requires no specialist knowledge or proprietary software, and allows manual correction of segmentations and re-computing of vascular metrics. SLOctolyzer is freely available at https://***/jaburke166/SLOctolyzer. Translational Relevance SLO images are captured simultaneous to optical coherence tomography (OCT), and we believe SLOctolyzer will be useful for extracting retinal vascular measurements from large OCT image sets and linking them to ocular or systemic diseases. © 2024, CC BY.

关键词： Fractal dimension

Hippocampal representations emerge when training recurrent neural networks on a memory dependent maze navigation task

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jude, Justin Hennig, Matthias H. Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh United Kingdom

Can neural networks learn goal-directed behaviour using similar strategies to the brain, by combining the relationships between the current state of the organism and the consequences of future actions? Recent work has shown that recurrent neural networks trained on goal based tasks can develop representations resembling those found in the brain, entorhinal cortex grid cells, for instance. Here we explore the evolution of the dynamics of their internal representations and compare this with experimental data. We observe that once a recurrent network is trained to learn the structure of its environment solely based on sensory prediction, an attractor based landscape forms in the network’s representation, which parallels hippocampal place cells in structure and function. Next, we extend the predictive objective to include Q-learning for a reward task, where rewarding actions are dependent on delayed cue modulation. Mirroring experimental findings in hippocampus recordings in rodents performing the same task, this training paradigm causes nonlocal neural activity to sweep forward in space at decision points, anticipating the future path to a rewarded location. Moreover, prevalent choice and cue-selective neurons form in this network, again recapitulating experimental findings. Together, these results indicate that combining predictive, unsupervised learning of the structure of an environment with reinforcement learning can help understand the formation of hippocampus-like representations containing both spatial and task-relevant information. © 2020, CC BY.

关键词： Neurons