English
Related papers

Related papers: Renormalization-Group Geometry of Homeostatically …

200 papers

We consider quantum states under the renormalization-group (RG) transformations introduced by Verstraete et al. [Phys. Rev. Lett. 94, 140601 (2005)] and propose a quantification of entanglement under such RG (via the geometric measure of…

Quantum Physics · Physics 2010-06-17 Tzu-Chieh Wei

The convolutional neural network (CNN) has become a basic model for solving many computer vision problems. In recent years, a new class of CNNs, recurrent convolution neural network (RCNN), inspired by abundant recurrent connections in the…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Jianfeng Wang , Xiaolin Hu

The Renormalization Group (RG) is a set of methods that have been instrumental in tackling problems involving an infinite number of degrees of freedom. What all these methods have in common -- which is what explains their success -- is that…

Statistical Mechanics · Physics 2020-04-30 Pedro Pessoa , Ariel Caticha

Central Pattern Generators (CPGs) are biological neural circuits capable of producing coordinated rhythmic outputs in the absence of rhythmic input. As a result, they are responsible for most rhythmic motion in living organisms. This…

Machine Learning · Computer Science 2019-01-21 Vincent Liu , Ademi Adeniji , Nathaniel Lee , Jason Zhao , Mario Srouji

The family of Green's function methods based on the $GW$ approximation has gained popularity in the electronic structure theory thanks to its accuracy in weakly correlated systems combined with its cost-effectiveness. Despite this,…

Chemical Physics · Physics 2023-08-31 Antoine Marie , Pierre-François Loos

Reconstructing under-sampled k-space measurements in Compressed Sensing MRI (CS-MRI) is classically solved with regularized least-squares. Recently, deep learning has been used to amortize this optimization by training reconstruction…

Image and Video Processing · Electrical Eng. & Systems 2021-01-07 Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

In the present paper the Renormalization Group (RG) method is adopted as a tool for a constructive analysis of the properties of the Frobenius-Perron Operator. The renormalization group reduction of a generic symplectic map in the case,…

Chaotic Dynamics · Physics 2007-05-23 Stephan I. Tzenov

Biological visual systems exhibit abundant recurrent connectivity. State-of-the-art neural network models for visual recognition, by contrast, rely heavily or exclusively on feedforward computation. Any finite-time recurrent neural network…

Neurons and Cognition · Quantitative Biology 2020-12-09 Ruben S. van Bergen , Nikolaus Kriegeskorte

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye

Discrete amorphous materials are best described in terms of arbitrary networks which can be embedded in three dimensional space. Investigating the thermodynamic equilibrium as well as non-equilibrium behavior of such materials around second…

Statistical Mechanics · Physics 2013-12-10 Eser Aygun , Ayse Erzan

We compute numerically the sequence of successive pinned configurations of an elastic line pulled quasi-statically by a spring in a random bond (RB) and random field (RF) potential. Measuring the fluctuations of the center of mass of the…

Disordered Systems and Neural Networks · Physics 2009-11-11 Alberto Rosso , Pierre Le Doussal , Kay Joerg Wiese

The key idea behind the renormalization group (RG) transformation is that properties of physical systems with very different microscopic makeups can be characterized by a few universal parameters. However, finding the optimal RG…

Disordered Systems and Neural Networks · Physics 2021-06-30 Jui-Hui Chung , Ying-Jer Kao

We studied the correlated quasi-one-dimensional systems by one-loop renormalization group techniques in weak coupling. In contrast to conventional g-ology approach, we formulate the theory in terms of bilinear currents and obtain all…

Strongly Correlated Electrons · Physics 2009-11-11 Ming-Shyang Chang , Wei Chen , Hsiu-Hau Lin

We propose rectified factor networks (RFNs) to efficiently construct very sparse, non-linear, high-dimensional representations of the input. RFN models identify rare and small events in the input, have a low interference between code units,…

Machine Learning · Computer Science 2018-01-31 Djork-Arné Clevert , Andreas Mayr , Thomas Unterthiner , Sepp Hochreiter

Recurrent neural networks (RNNs) are brain-inspired models widely used in machine learning for analyzing sequential data. The present work is a contribution towards a deeper understanding of how RNNs process input signals using the response…

Machine Learning · Statistics 2021-02-15 Soon Hoe Lim

We model quantum space-time on the Planck scale as dynamical networks of elementary relations or time dependent random graphs, the time dependence being an effect of the underlying dynamical network laws. We formulate a kind of geometric…

General Relativity and Quantum Cosmology · Physics 2011-07-19 Manfred Requardt

We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity. Unlike Transformer architectures that employ dense attention mechanisms with O(n^2)…

Machine Learning · Computer Science 2026-01-27 Hasi Hays

We develop an algorithmic, system-specific renormalization group (RG) procedure that is adapted from model reductions techniques from engineering control theory. The resulting "generalized" RG is a consistent generalization of the Wilsonian…

Statistical Mechanics · Physics 2007-05-23 David E. Reynolds

We develop a statistical theory of temporal learnability in recurrent neural networks, quantifying the maximal temporal horizon $\mathcal{H}_N$ over which gradient-based learning can recover lag-dependent structure at finite sample size…

Machine Learning · Computer Science 2026-03-31 Lorenzo Livi

A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning of such hyperparameters may be difficult and, typically, based on a trial-and-error…

Neural and Evolutionary Computing · Computer Science 2017-02-22 Filippo Maria Bianchi , Lorenzo Livi , Cesare Alippi , Robert Jenssen
‹ Prev 1 8 9 10 Next ›