22 papers · ranked by Valyu relevance
Qian Li, Sanyang Liu, Xin‐She Yang
All metaheuristic optimization algorithms require some initialization, and the initialization for such optimizers is usually carried out randomly. However, initialization can have some significant influence on the performance of such algorithms. This paper presents a systematic comparison of 22 different initialization…
Marius Pachitariu, Lin Zhong, Alexa Gracias, Amanda Minisi + 2 more
Artificial neural networks learn faster if they are initialized well. Good initializations can generate high-dimensional macroscopic dynamics with long timescales. It is not known if biological neural networks have similar properties. Here we show that the eigenvalue spectrum and dynamical properties of large-scale…
Xiaohao Wen, Mengchu Zhou, Aiiad Albeshri, Lukui Huang + 3 more
'Dan Ning' 'Marcin Woźniak'] A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a novel initialization method specifically designed to…
Oluwatumininu Emmanuel Ayo-Ojo, Akpevweoghene Ogheneowho Ugono, Nkosinathi Dlamini
Accurate initialization of polymer architectures remains a critical yet underappreciated determinant of reliability in molecular dynamics simulations of soft matter systems. Errors in coordinate generation and connectivity assignment frequently introduce artificial stresses, topological inconsistencies, and numerical…
S. Westerhof, T. Hofman
This paper presents an optimization framework for Spatial Packaging of Interconnected Systems with Physical Interactions (SPI2) that addresses the geometric challenges of three-dimensional component placement and routing. While SPI2 generally includes physical interactions, this study isolates the spatial optimization…
Verusca Severo, Felipe B. S. Ferreira, Rodrigo Spencer, Arthur Nascimento + 2 more
'Arthur Nascimento' 'Francisco Madeiro' 'Steve Vanlanduit'] Vector Quantization (VQ) is a technique with a wide range of applications. For example, it can be used for image compression. The codebook design for VQ has great significance in the quality of the quantized signals and can benefit from the use of swarm…
Jie You, Zhaoxuan Li, Junli Du, Praveen Kumar Donta
Gaussian mixture model (GMM) is a very useful tool, which is widely used in complex probability distribution modeling, such as data classification , image classification and segmentation , speech recognition , etc. The Gaussian mixture model is composed of K single Gaussian distributions. For a single Gaussian…
Hexuan Dou, Bo Liu, Yinghao Jia, Changhong Wang + 1 more
Two-view epipolar initialization for feature-based monocular SLAM with the RANSAC approach is challenging in dynamic environments. This paper presents a universal and practical method for improving the automatic estimation of initial poses and landmarks across multiple frames in real time. Image features corresponding…
Richard N. M. Rudd-Orthner, Lyudmila Mihaylova, Abir Hussain, Dhiya Al-Jumeily + 2 more
'Dhiya Al-Jumeily' 'Hissam Tawfik' 'Panos Liatsis'] A repeatable and deterministic non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM). Using the FSGM approach as a technique to measure the initialization effect with controlled…
Mengyu Huang, Yuxing Zhong, Huiwen Yang, Jiazheng Wang + 3 more
'Bo Bai' 'Ling Shi'] The simplex method is one of the most fundamental technologies for solving linear programming (LP) problems and has been widely applied to different practical applications. In the past literature, how to improve and accelerate the simplex method has attracted plenty of research. One important way…
Abdol Aziz Ould Ismail, Drew Parker, Moises Hernandez-Fernandez, Ronald Wolf + 6 more
Characterization of healthy versus pathological tissue is a key concern when modeling tissue microstructure in the peritumoral area, confounded by the presence of free water (e.g., edema). Most methods that model tissue microstructure are either based on advanced acquisition schemes not readily available in the clinic…
Dmitry Kobak, George C. Linderman
One of the most ubiquitous analysis tools employed in single-cell transcriptomics and cytometry is t-distributed stochastic neighbor embedding (t-SNE) [1], used to visualize individual cells as points on a 2D scatter plot such that similar cells are positioned close together. Recently, a related algorithm, called…
Authors not listed
Bayesian Optimization (BO) has become a standard tool for hyperparameter tuning in machine learning due to its sample efficiency when exploring expensive black-box functions. While most BO pipelines begin with uniform random initialization, default hyperparameter values shipped with popular ML libraries such as…
Alejandro Mata Ali, Iñigo Perez Delgado, Marina Ristol Roura, Aitor Moreno-Fernández-de-Leceta
'Aitor Moreno-Fernández-de-Leceta'] We present a novel method for initializing layers of tensorized neural networks in a way that avoids the explosion of the parameters of the matrix it emulates. The method is intended for layers with a high number of nodes in which there is a connection to the input or output of all…
Min Zhong, Yiqing Yao, Xiaosu Xu, Hongyu Wei + 1 more
In order to improve the initialization robustness of visual inertial SLAM, the complementarity of the optical flow method and the feature-based method can be used in vision data processing. The parallel initialization method is proposed, where the optical flow inertial initialization and the monocular feature-based…
Tao Chen, Jingtong Zhang, Jing Liu, Youjin Deng + 1 more
Tao Chen,1, 2, ∗ Jingtong Zhang,3, 4, ∗ Jing Liu,3, † Youjin Deng,1, 2, ‡ and Pan Zhang3, § 1 Hefei National Laboratory for Physical Sciences at the Microscale and Department of Modern Physics, University of Science and Technology of China, Hefei 230026, China 2 Hefei National Laboratory, University of Science and…
Authors not listed
With the ever-increasing demand for atomistic structures representative of real-life systems as well as the ad-vent of exascale computers, it has now become necessary and possible to use advanced global optimization (GO) techniques to intelligently sample the potential energy surface (PES). Given the previous studies…
Heike Rudolf, Christine Zellner, Ezzat El-Sherif
Recently, it was shown that anterior-posterior patterning genes in the red flour beetle Tribolium castaneum are expressed sequentially in waves. However, in the fruit fly Drosophila melanogaster, an insect with a derived mode of embryogenesis compared to Tribolium, anterior-posterior patterning genes quickly and…
Denis Turcu, Jonathan Cornford, Sven Dorkenwald, Stefan Mihalas
Hebbian-like learning has been repeatedly confirmed experimentally, yet computational models usually require non-local signals, such as backpropagating errors, to solve complex cognitive tasks. Recent cortical electron microscopy data suggests a model where synapses follow different plasticity rules depending on…
Lucian Chan, Geoffrey Hutchison, Garrett Morris
Generating low-energy molecular conformers is a key task for many areas of computational chemistry, molecular modeling and cheminformatics. Most current conformer generation methods primarily focus on generating geometrically diverse conformers rather than finding the most probable or energetically lowest minima. Here…
John D. Chodera
Molecular simulations intended to compute equilibrium properties are often initiated from configurations that are highly atypical of equilibrium samples, a practice which can generate a distinct initial transient in mechanical observables computed from the simulation trajectory. Traditional practice in simulation data…
Authors not listed
We present a novel, flexible framework for electronic structure interfaces designed for nonadiabatic dynamics simulations, implemented in Python 3 using concepts of object-oriented programming. This framework streamlines the development of new interfaces by providing a reusable and extendable code base. It supports the…