{"title":"Investigating the generative dynamics of energy-based neural networks","authors":"Lorenzo Tausani, Alberto Testolin, M. Zorzi","doi":"10.48550/arXiv.2305.06745","DOIUrl":"https://doi.org/10.48550/arXiv.2305.06745","url":null,"abstract":"Generative neural networks can produce data samples according to the statistical properties of their training distribution. This feature can be used to test modern computational neuroscience hypotheses suggesting that spontaneous brain activity is partially supported by top-down generative processing. A widely studied class of generative models is that of Restricted Boltzmann Machines (RBMs), which can be used as building blocks for unsupervised deep learning architectures. In this work, we systematically explore the generative dynamics of RBMs, characterizing the number of states visited during top-down sampling and investigating whether the heterogeneity of visited attractors could be increased by starting the generation process from biased hidden states. By considering an RBM trained on a classic dataset of handwritten digits, we show that the capacity to produce diverse data prototypes can be increased by initiating top-down sampling from chimera states, which encode high-level visual features of multiple digits. We also found that the model is not capable of transitioning between all possible digit states within a single generation trajectory, suggesting that the top-down dynamics is heavily constrained by the shape of the energy function.","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"1 1","pages":"96-108"},"PeriodicalIF":0.0,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86687934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Understanding Syntax Structure of Language After a Head Injury","authors":"Marisol Roldán-Palacios, A. López-López","doi":"10.1007/978-3-031-15037-1_24","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_24","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"385 1","pages":"288-300"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81279362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Root-Cause Analysis of Activation Cascade Differences in Brain Networks","authors":"Qihang Yao, M. Chandrasekaran, C. Dovrolis","doi":"10.1007/978-3-031-15037-1_8","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_8","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"81 1","pages":"86-98"},"PeriodicalIF":0.0,"publicationDate":"2022-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88192536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Changwei Gong, Changhong Jing, Ju-dong Pan, Shuqiang Wang
{"title":"Feature-selected Graph Spatial Attention Network for Addictive Brain-Networks Identification","authors":"Changwei Gong, Changhong Jing, Ju-dong Pan, Shuqiang Wang","doi":"10.48550/arXiv.2207.00583","DOIUrl":"https://doi.org/10.48550/arXiv.2207.00583","url":null,"abstract":". Functional alterations in the relevant neural circuits occur from drug addiction over a certain period. And these significant alterations are also revealed by analyzing fMRI. However, because of fMRI’s high dimensionality and poor signal-to-noise ratio, it is challenging to encode efficient and robust brain regional embeddings for both graph-level identification and region-level biomarkers detection tasks between nicotine addiction (NA) and healthy control (HC) groups. In this work, we represent the fMRI of the rat brain as a graph with biological attributes and propose a novel feature-selected graph spatial attention network(FGSAN) to extract the biomarkers of addiction and identify from these brain networks. Specially, a graph spatial attention encoder is employed to capture the features of spatiotemporal brain networks with spatial information. The method simultaneously adopts a Bayesian feature selection strategy to optimize the model and improve classification task by constraining features. Experiments on an addiction-related neural imaging dataset show that the proposed model can obtain su-perior performance and detect interpretable biomarkers associated with addiction-relevant neural circuits. for exploiting effective and interpretable regional brain biomarkers and utilizing features of these biomarkers to identify the addiction-related brain network patterns. Detailed model discussions were conducted to","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"29 1","pages":"316-326"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84252176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Estimating the Temporal Evolution of Synaptic Weights from Dynamic Functional Connectivity","authors":"Marco Celotto, S. Lemke, S. Panzeri","doi":"10.1007/978-3-031-15037-1_1","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_1","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"102 1","pages":"3-14"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76962148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of Alpha Band Decomposition in Different Level-k Scenarios with Semantic Processing","authors":"Dor Mizrahi, Inon Zuckerman, Ilan Laufer","doi":"10.1007/978-3-031-15037-1_6","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_6","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"134 1","pages":"65-73"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88911026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kashfia Sailunaz, Deniz Bestepe, Sleiman Alhajj, Tansel Özyer, J. Rokne, R. Alhajj
{"title":"Convex Hull in Brain Tumor Segmentation","authors":"Kashfia Sailunaz, Deniz Bestepe, Sleiman Alhajj, Tansel Özyer, J. Rokne, R. Alhajj","doi":"10.1007/978-3-031-15037-1_18","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_18","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"15 1","pages":"210-225"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90876820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Computer-Aided Diagnosis Framework for ADHD Detection Using Quantitative EEG","authors":"Ruchi Holker, Seba Susan","doi":"10.1007/978-3-031-15037-1_19","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_19","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"34 1","pages":"229-240"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88930258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. A. Rahman, David J. Brown, N. Shopland, Matthew C. Harris, Z. Turabee, N. Heym, A. Sumich, B. Standen, David Downes, Yangang Xing, Carolyn Thomas, Sean Haddick, P. Premkumar, Simona Nastase, A. Burton, James Lewis, M. Mahmud
{"title":"Towards Machine Learning Driven Self-guided Virtual Reality Exposure Therapy Based on Arousal State Detection from Multimodal Data","authors":"M. A. Rahman, David J. Brown, N. Shopland, Matthew C. Harris, Z. Turabee, N. Heym, A. Sumich, B. Standen, David Downes, Yangang Xing, Carolyn Thomas, Sean Haddick, P. Premkumar, Simona Nastase, A. Burton, James Lewis, M. Mahmud","doi":"10.1007/978-3-031-15037-1_17","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_17","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"38 1","pages":"195-209"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83686216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Christoforou, Timothy C. Papadopoulos, Maria Theodorou
{"title":"Toward the Study of the Neural-Underpinnings of Dyslexia During Final-Phoneme Elision: A Machine Learning Approach","authors":"C. Christoforou, Timothy C. Papadopoulos, Maria Theodorou","doi":"10.1007/978-3-031-15037-1_7","DOIUrl":"https://doi.org/10.1007/978-3-031-15037-1_7","url":null,"abstract":"","PeriodicalId":77475,"journal":{"name":"Zhonghua er bi yan hou ke za zhi","volume":"26 1","pages":"74-85"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76363309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}