Article
Computer Science, Artificial Intelligence
Francesca Elisa Leonelli, Elena Agliari, Linda Albanese, Adriano Barra
Summary: This study leverages the equivalence between RBMs and HNN to propose an effective weight initialization method and applies it in a simple auto-encoder model. Additionally, obtaining larger retrieval regions by applying Gram-Schmidt orthogonalisation to the patterns is demonstrated.
Article
Computer Science, Software Engineering
Ludwig Kampel, Michael Wagner, Ilias S. Kotsireas, Dimitris E. Simos
Summary: In this study, neural networks in the form of Boltzmann machines and Hopfield networks are used to construct a specific class of combinatorial designs called covering arrays. By adapting existing algorithms and conducting comprehensive experimental evaluations, the research demonstrates the first application of neural networks in the field of covering array generation and related discrete structures.
OPTIMIZATION METHODS & SOFTWARE
(2022)
Review
Physics, Multidisciplinary
Chiara Marullo, Elena Agliari
Summary: The Hopfield model and the Boltzmann machine are popular neural network examples used for classification, feature detection, and generative model learning. They are closely related and can be exactly mapped to each other, representing two sides of the same cognitive process.
Article
Computer Science, Artificial Intelligence
Xiangguang Dai, Jun Wang, Wei Zhang
Summary: This paper presents a collaborative neurodynamic algorithm for balanced clustering, which solves the combinatorial optimization problem of balanced clustering by using a population of discrete Hopfield networks or Boltzmann machines. Experimental results demonstrate that the proposed algorithm outperforms four existing balanced clustering algorithms in terms of balanced clustering quality.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Physics, Multidisciplinary
Adriano Barra, Giovanni Catania, Aurelien Decelle, Beatriz Seoane
Summary: In this paper, the equilibrium properties of bidirectional associative memories (BAMs) are investigated. The computational capabilities of a stochastic extension of BAM are characterized using statistical physics techniques. The phase diagram of the model at the replica symmetric level is provided, and the transition curves are analyzed as control parameters are tuned. The retrieval mechanism in BAM is explained by analogy with two interacting Hopfield models, and the potential equivalence with two coupled Restricted Boltzmann Machines is discussed.
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2023)
Article
Physics, Multidisciplinary
Won Sang Chung, Abdullah Algin
Summary: This work first develops a general procedure for obtaining the superstatistical density of states with nonzero variance in the probability density function. The microcanonical ensemble based on superstatistics with the free Hamiltonian as a stochastic variable is then discussed. Finally, the formalism presented here is applied and analyzed in detail within the framework of different probability distributions, such as three states distribution, the Gamma distribution, the q-deformed Dirac delta distribution, and the Poisson distribution.
EUROPEAN PHYSICAL JOURNAL PLUS
(2022)
Article
Materials Science, Multidisciplinary
Xiang Gao
Summary: This study reveals that the generalized Boltzmann distribution is mathematically consistent with thermodynamics and challenges the fundamental assumptions of statistical mechanics. It provides a new approach to derive the Boltzmann distribution and could have implications for non-Boltzmann-Gibbs statistical mechanics and philosophical studies on its foundations.
RESULTS IN PHYSICS
(2022)
Article
Physics, Multidisciplinary
Yichen Huang, Joel E. Moore
Summary: We study the representational power of Boltzmann machines in quantum many-body systems and prove that any local tensor network state can be represented by a local neural network. Despite difficulties in representing chiral topological states using local tensor networks, we successfully construct a quasilocal neural network representation for a chiral p-wave superconductor, demonstrating the strength of Boltzmann machines.
PHYSICAL REVIEW LETTERS
(2021)
Article
Physics, Fluids & Plasmas
M. Onorato, G. Dematteis, D. Proment, A. Pezzi, M. Ballarin, L. Rondoni
Summary: In this study, we predict the presence of negative temperature states in the discrete nonlinear Schodinger (DNLS) equation and provide exact solutions using the associated wave kinetic equation. We define an entropy within the wave kinetic approach that monotonically increases in time and reaches a stationary state in accordance with classical equilibrium statistical mechanics. Our analysis shows that fluctuations of actions at fixed wave numbers relax to their equilibrium behavior faster than the spectrum reaches equilibrium. Numerical simulations of the DNLS equation confirm our theoretical results. The boundedness of the dispersion relation is found to be critical for observing negative temperatures in lattices characterized by two invariants.
Article
Materials Science, Multidisciplinary
Sujie Li, Feng Pan, Pengfei Zhou, Pan Zhang
Summary: Restricted Boltzmann machines (RBMs) and deep Boltzmann machines (DBMs) are important models in machine learning, with recent applications in quantum many-body physics. This study establishes fundamental connections between RBMs and DBMs with tensor networks, and presents an efficient algorithm for computing their partition functions, showing improved accuracy compared to state-of-the-art methods. The research highlights potential applications in training DBMs and estimating the partition function of RBMs.
Article
Physics, Multidisciplinary
K. Baudin, J. Garnier, A. Fusaro, N. Berti, C. Michel, K. Krupa, G. Millot, A. Picozzi
Summary: This paper reports the observation of Rayleigh-Jeans thermalization of light waves to negative-temperature equilibrium states. The optical wave relaxes to the equilibrium state through its propagation in a multimode optical fiber, where high energy levels are more populated than low energy levels. Experimental results show that negative-temperature speckle beams have a nonmonotonic radial intensity profile.
PHYSICAL REVIEW LETTERS
(2023)
Article
Physics, Multidisciplinary
Constantino Tsallis
Summary: The Boltzmann-Gibbs-von Neumann-Shannon additive entropy and its nonextensive counterpart have provided a foundation for statistical mechanics in both classical and quantum systems. However, the increasing complexity of natural, artificial, and social systems has made it necessary to develop nonadditive entropic functionals. Among them, the nonextensive entropy Sq has played a special role in the study of complex systems.
Article
Mathematics, Applied
Francesco Alemanno, Luca Camanzi, Gianluca Manzan, Daniele Tantari
Summary: While Hopfield networks are widely used for memory storage and retrieval, this study explores the possibility of using Boltzmann machines for self-supervised learning. By generalizing the Hopfield model with structured patterns, the learning performance is analyzed based on the size of the training set, dataset noise, and weight regularization. The results show that with an informative dataset, the machine can learn through memorization, while with a noisy dataset, a critical number of examples is needed for generalization.
APPLIED MATHEMATICS AND COMPUTATION
(2023)
Article
Chemistry, Physical
Basile Herzog, Bastien Casier, Sebastin Lebegue, Dario Rocca
Summary: The configuration interaction approach is a powerful method for solving the Schrödinger equation in realistic molecules and materials, but it has a scalability issue that limits its practical use. In this study, we propose a machine learning approach to selectively generate important configurations, which leads to faster convergence to chemical accuracy compared to random sampling or Monte Carlo configuration interaction method. This work opens up new possibilities for using generative models to solve electronic structure problems.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Masaki Kobayashi
Summary: Information geometry is introduced to analyze hyperbolic-valued neural networks, proving that they form an exponential family and providing natural and mixture parameters, determining the Fisher metric, proving the existence of mixed parameters for all distributions, which are useful for learning algorithms.
Article
Physics, Mathematical
Diego Alberici, Pierluigi Contucci, Emanuele Mingione
JOURNAL OF STATISTICAL PHYSICS
(2015)
Article
Social Sciences, Interdisciplinary
Pierluigi Contucci, Emanuele Panizzi, Federico Ricci-Tersenghi, Alina Sirbu
QUALITY & QUANTITY
(2016)
Article
Multidisciplinary Sciences
Raffaella Burioni, Pierluigi Contucci, Micaela Fedele, Cecilia Vernia, Alessandro Vezzani
SCIENTIFIC REPORTS
(2015)
Article
Physics, Mathematical
Diego Alberici, Pierluigi Contucci, Micaela Fedele, Emanuele Mingione
COMMUNICATIONS IN MATHEMATICAL PHYSICS
(2016)
Article
Physics, Multidisciplinary
Diego Alberici, Pierluigi Contucci, Emanuele Mingione
Article
Mathematics, Interdisciplinary Applications
Pierluigi Contucci, Rickard Sandell, Seyedalireza Seyedi
JOURNAL OF MATHEMATICAL SOCIOLOGY
(2017)
Article
Physics, Multidisciplinary
Pierluigi Contucci, Rachele Luzi, Cecilia Vernia
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2017)
Article
Physics, Multidisciplinary
Adriano Barra, Pierluigi Contucci, Emanuele Mingione, Daniele Tantari
ANNALES HENRI POINCARE
(2015)
Article
Physics, Mathematical
Diego Alberici, Pierluigi Contucci
COMMUNICATIONS IN MATHEMATICAL PHYSICS
(2014)
Article
Social Sciences, Interdisciplinary
Pierluigi Contucci, Candia Riga
QUALITY & QUANTITY
(2015)
Article
Physics, Mathematical
Pierluigi Contucci, Emanuele Mingione
COMMUNICATIONS IN MATHEMATICAL PHYSICS
(2019)
Article
Physics, Multidisciplinary
Filippo Zimmaro, Pierluigi Contucci, Janos Kertesz
Summary: Social coordination and personal preferences are important factors shaping an individual's opinion. The topology of the network of interactions also plays a significant role. This study examines an extension of the voter model, where agents are divided into populations with opposite preferences, using both analytical and simulation methods. The results show that the modular structure of the network increases polarization, and the success of imposing one group's preferred opinion on the other depends on the segregation of the latter population rather than the topological structure of the former. The mean-field approach is compared with the pair approximation, and its predictions are validated on a real network.
Article
Physics, Fluids & Plasmas
Pierluigi Contucci, Godwin Osabutey, Cecilia Vernia
Summary: In this paper, we solve the inverse problem of the cubic mean-field Ising model by reconstructing the free parameters of the system from configuration data generated according to the model's distribution. We test the robustness of this inversion procedure in both the region of solution uniqueness and the region with multiple thermodynamic phases.
Article
Physics, Multidisciplinary
Diego Alberici, Pierluigi Contucci, Emanuele Mingione, Marco Molari
Article
Demography
Pierluigi Contucci, Rickard Sandell
DEMOGRAPHIC RESEARCH
(2015)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.