Related references
Note: Only part of the references are listed.
Review
Computer Science, Artificial Intelligence
Pengzhi Li et al.
Summary: Autoencoder is an unsupervised learning model that automatically learns data features and acts as a dimensionality reduction method. This paper explains the principle and development process of a conventional autoencoder, proposes a taxonomy of autoencoders based on their structures and principles, analyzes and discusses various autoencoder models, introduces their applications in different fields, and summarizes the shortcomings of the current autoencoder algorithm while addressing future development directions.
APPLIED SOFT COMPUTING
(2023)
Review
Computer Science, Artificial Intelligence
Andreas Bahmer et al.
Summary: Machine learning tools, especially artificial neural networks (ANN), have become widely used in various scientific fields. This is due to the improved computational power, availability of labeled datasets, advanced training algorithms, and refined topologies of ANN. In neuroscience, the introduction of multichannel recordings has allowed for the study of complex network activity in biological neural networks (BNN) and comparison with state-of-the-art ANN.
NEURAL COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Mei Liu et al.
Summary: This article proposes a novel method of using gradient activation function to address issues in deep neural networks. Theoretical and experimental evidence demonstrate the effectiveness of this method, which can be applied to various neural networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lucas Francisco Amaral Orosco Pellicer et al.
Summary: Data augmentation methods have shown remarkable success in computer vision tasks but have limited success in natural language processing tasks. There is still a lack of practical understanding of the relationship between different data augmentation methods and their impact on important aspects of the output. In this study, a comprehensive analysis of NLP data augmentation techniques is performed to compare their performance and evaluate the quality of the generated synthetic data.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Raghda Awad Shaban Naseri et al.
Summary: The growth of IoMT enables data collection and processing in healthcare systems. Mask-wearing is considered an efficient preventive measure, thus the need for an automated mask identification model. The proposed model uses a hybrid deep learning approach and optimization algorithm to achieve accurate mask detection results.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Hui Xu et al.
Summary: Due to the nonlinearity and non-stationarity of EEG signals, the manifold has become a new direction for analyzing EEG signals. A manifold transfer learning method based on divergence alignment (MTLDA) is proposed to overcome the problem of imbalanced epileptic seizure data and limited labeling data. Additionally, a Riemannian manifold fuzzy clustering (RMFC) method is proposed for unsupervised pattern recognition on the manifold. Both MTLDA and RMFC use Riemannian distance and mean, and show better performance compared to other algorithms.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Chunlei Li et al.
Summary: This paper proposes a novel acceleration method called 2D Entropy-based Adaptive Filter Search (2EAFS), which determines the importance of filters by quantifying the amount of information in feature maps. It combines a sparse constraint equation and the Nelder-Mead search algorithm to determine the optimal pruning architecture. Experimental results demonstrate that this method achieves considerable accuracy improvements while reducing FLOPs and parameters.
APPLIED SOFT COMPUTING
(2023)
Article
Multidisciplinary Sciences
Ruxandra Barbulescu et al.
Summary: Given the complexity of the human nervous system, studying simpler organisms like C. elegans can provide insight into brain activity. This paper investigates the use of data-driven models to simulate the neural system of C. elegans using different neural network architectures, and compares their properties, accuracy, and complexity.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Christian Flores Verga et al.
Summary: This study proposes a method called EEG-TCFNet, which combines temporal convolutional networks (TCNs), LSTM cells, and fuzzy neural blocks (FNB), to process electroencephalographic signals (EEG). The experimental results show that this method achieves high classification accuracy in smart home interaction, and the inclusion of FNB improves the performance.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Jingdong Yang et al.
Summary: A novel lightweight CNN model, CodnNet, is proposed in this paper for quick detection of COVID-19 infection. The model improves feature reuse and receptive field range through effective dense connections and depthwise separable convolution, resulting in better classification accuracy and generalization performance.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Meenu Gupta et al.
Summary: A face mask identification model called DTLMV2 is proposed in this paper, which utilizes the MobileNetV2 lightweight Convolutional Neural Network (CNN) to determine whether an individual is wearing a mask. The model achieves high accuracy on validation, training, and testing data, with 97.01%, 98%, and 97.45% accuracy respectively.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Alessia Amelio et al.
Summary: Colors play a crucial role in Artificial Intelligence, but the study of fabric colors is still limited. This paper introduces a new Convolutional Neural Network-based model for identifying fabric colors and demonstrates its superiority through experiments.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Arpit Kapoor et al.
Summary: The major challenge in Bayesian neural networks is to develop effective sampling methods for addressing deep neural networks and big data-related problems. This paper proposes a synergy of neuroevolution and Bayesian neural networks, utilizing particle swarm optimization as efficient proposal distributions in tempered MCMC sampling. The results demonstrate improved prediction accuracy and reduced computational time compared to traditional methods for time-series and pattern classification problems.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Zakariya Ghalmane et al.
Summary: Networks are used to model and analyze complex systems, but understanding large-scale networks with millions of nodes and billions of connections is challenging. This study proposes a filter-based method that utilizes overlapping community structures to extract the backbone of weighted networks, focusing on influential nodes and edges for information dissemination while preserving network complexity.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Enrico Lanza et al.
Summary: Despite the lack of knowledge on the excitatory or inhibitory character of synaptic connections in the C. elegans connectome, a recurrent neural network model was proposed to replicate known escape behaviors by iteratively updating synaptic characters until the behaviors were reproduced. By conducting a meta-study on stimulus-response behaviors of C. elegans, the model's accuracy was validated, confirming its predictive power.
Article
Neurosciences
Dana T. Byrd et al.
Summary: The completion of Caenorhabditis elegans connectomics four decades ago has guided mechanistic investigation of neuronal circuits. Recent technological advances have aided re-examination of this connectomics, uncovering previously unreported synaptic connections and generating models for neural networks underlying behaviors. Combining molecular information and cell-specific manipulation tools has enhanced the ability to investigate individual neurons in behaving animals precisely.
CURRENT OPINION IN NEUROBIOLOGY
(2021)
Review
Neurosciences
Francesco Randi et al.
CURRENT OPINION IN NEUROBIOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Mathias Lechner et al.
NATURE MACHINE INTELLIGENCE
(2020)
Article
Multidisciplinary Sciences
Steven J. Cook et al.
Editorial Material
Neurosciences
William R. Schafer
TRENDS IN NEUROSCIENCES
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Biochemical Research Methods
Karol A. Bacik et al.
PLOS COMPUTATIONAL BIOLOGY
(2016)
Article
Biochemical Research Methods
Aharon Azulay et al.
PLOS COMPUTATIONAL BIOLOGY
(2016)
Article
Computer Science, Artificial Intelligence
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2015)
