Spiking neural networks play an important role in brainlike neuromorphic computations and in studying working mechanisms of neural circuits. One drawback of training a large-scale spiking neural network is that updating all weights is quite expensive. Furthermore, after training, all information related to the computational task is hidden into the weight matrix, prohibiting us from a transparent understanding of circuit mechanisms. Therefore, in this work, we address these challenges by proposing a spiking mode-based training protocol, where the recurrent weight matrix is explained as a Hopfield-like multiplication of three matrices: input modes, output modes, and a score matrix. The first advantage is that the weight is interpreted by input and output modes and their associated scores characterizing the importance of each decomposition term. The number of modes is thus adjustable, allowing more degrees of freedom for modeling the experimental data. This significantly reduces the training cost because of significantly reduced space complexity for learning. Training spiking networks is thus carried out in the mode-score space. The second advantage is that one can project the high-dimensional neural activity (filtered spike train) in the state space onto the mode space which is typically of a low dimension, e.g., a few modes are sufficient to capture the shape of the underlying neural manifolds. We successfully apply our framework in two computational tasks-digit classification and selective sensory integration tasks. Our method thus accelerates the training of spiking neural networks by a Hopfield-like decomposition, and moreover this training leads to low-dimensional attractor structures of high-dimensional neural dynamics.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1103/PhysRevE.110.024306 | DOI Listing |
Digit Health
December 2024
School of Public Administration, Central South University, Changsha, Hunan, China.
Objective: To evaluate the service quality of integrated health and social care institutions for older adults in residential settings in China, addressing a critical gap in the theoretical and empirical understanding of service quality assurance in this rapidly expanding sector.
Methods: This study employs three machine learning algorithms-Backpropagation Neural Networks (BPNN), Feedforward Neural Networks (FNN), and Support Vector Machines (SVM)-to train and validate an evaluative item system. Comparative indices such as Mean Squared Error, Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and predictive performance metrics were employed to assess the models.
Digit Health
December 2024
School of Computer Science, University of Birmingham, Birmingham, UK.
Objective: The study aims to present an active learning approach that automatically extracts clinical concepts from unstructured data and classifies them into explicit categories such as Problem, Treatment, and Test while preserving high precision and recall and demonstrating the approach through experiments using i2b2 public datasets.
Methods: Initially labeled data are acquired from a lexical-based approach in sufficient amounts to perform an active learning process. A contextual word embedding similarity approach is adopted using BERT base variant models such as ClinicalBERT, DistilBERT, and SCIBERT to automatically classify the unlabeled clinical concept into explicit categories.
Phys Rev Res
April 2024
Department of Physics, University of Washington, 3910 15th Avenue Northeast, Seattle, Washington 98195, USA.
Group-equivariant neural networks have emerged as an efficient approach to model complex data, using generalized convolutions that respect the relevant symmetries of a system. These techniques have made advances in both the supervised learning tasks for classification and regression, and the unsupervised tasks to generate new data. However, little work has been done in leveraging the symmetry-aware expressive representations that could be extracted from these approaches.
View Article and Find Full Text PDFAdvances in magnetic resonance imaging (MRI) have revolutionized disease detection and treatment planning. However, as the volume and complexity of MRI data grow with increasing heterogeneity between institutions in imaging protocol, scanner technology, and data labeling, there is a need for a standardized methodology to efficiently identify, characterize, and label MRI sequences. Such a methodology is crucial for advancing research efforts that incorporate MRI data from diverse populations to develop robust machine learning models.
View Article and Find Full Text PDFProteins
December 2024
Institute of Computing, University of Campinas, Campinas, Brazil.
Recent technological advancements have enabled the experimental determination of amino acid sequences for numerous proteins. However, analyzing protein functions, which is essential for understanding their roles within cells, remains a challenging task due to the associated costs and time constraints. To address this challenge, various computational approaches have been proposed to aid in the categorization of protein functions, mainly utilizing amino acid sequences.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!