Copertina

Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Altarabichi, Mohammed Ghaith, Nowaczyk, Sławomir, Pashami, Sepideh, Mashhadi, Peyman Sheikholharam, Handl, Julia
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Neural and Evolutionary Computing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fast Genetic Algorithm for feature selection -- A qualitative approximation approach
di: Altarabichi, Mohammed Ghaith, et al.
Pubblicazione: (2024)

Designing deep neural networks for driver intention recognition
di: Vellenga, Koen, et al.
Pubblicazione: (2024)

Reconstructing shared dynamics with a deep neural network
di: Benkő, Zsigmond, et al.
Pubblicazione: (2021)

Teaching signal synchronization in deep neural networks with prospective neurons
di: Zucchet, Nicoas, et al.
Pubblicazione: (2025)

Improved weight initialization for deep and narrow feedforward neural network
di: Lee, Hyunwoo, et al.
Pubblicazione: (2023)

A computational approach to visual ecology with deep reinforcement learning
di: Sokoloski, Sacha, et al.
Pubblicazione: (2024)

Asymmetrically connected reservoir networks learn better
di: Rathor, Shailendra K., et al.
Pubblicazione: (2024)

DelRec: learning delays in recurrent spiking neural networks
di: Queant, Alexandre, et al.
Pubblicazione: (2025)

Synchronization and semantization in deep spiking networks
di: Oberste-Frielinghaus, Jonas, et al.
Pubblicazione: (2025)

Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
di: Wu, Kun
Pubblicazione: (2024)

Elucidating the theoretical underpinnings of surrogate gradient learning in spiking neural networks
di: Gygax, Julia, et al.
Pubblicazione: (2024)

Who invented deep residual learning?
di: Schmidhuber, Juergen
Pubblicazione: (2025)

An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
di: Keisler, Julie, et al.
Pubblicazione: (2023)

A survey on learning models of spiking neural membrane systems and spiking neural networks
di: Paul, Prithwineel, et al.
Pubblicazione: (2024)

A developmental approach for training deep belief networks
di: Zambra, Matteo, et al.
Pubblicazione: (2022)

Robustness and Invariance of Hybrid Metaheuristics under Objective Function Transformations
di: Sroka, Grzegorz, et al.
Pubblicazione: (2025)

From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks
di: Russin, Jacob, et al.
Pubblicazione: (2024)

Evolutionary feature selection for spiking neural network pattern classifiers
di: Valko, Michal, et al.
Pubblicazione: (2026)

Physics-informed neural network for modeling dynamic linear elasticity
di: Kag, Vijay, et al.
Pubblicazione: (2023)

Genetically programmable optical random neural networks
di: Çarpınlıoğlu, Bora, et al.
Pubblicazione: (2024)

Effects of structural properties of neural networks on machine learning performance
di: Arya, Yash, et al.
Pubblicazione: (2025)

Internal noise in hardware deep and recurrent neural networks helps with learning
di: Kolesnikov, Ivan, et al.
Pubblicazione: (2025)

Universality of shallow and deep neural networks on non-Euclidean spaces
di: Ismailov, Vugar
Pubblicazione: (2026)

Three factor delay learning rules for spiking neural networks
di: Vassallo, Luke, et al.
Pubblicazione: (2026)

Flexible inference for animal learning rules using neural networks
di: Liu, Yuhan Helena, et al.
Pubblicazione: (2025)

Optimal feature rescaling in machine learning based on neural networks
di: Vitrò, Federico Maria, et al.
Pubblicazione: (2024)

Exploiting heterogeneous delays for efficient computation in low-bit neural networks
di: Sun, Pengfei, et al.
Pubblicazione: (2025)

TDE-3: An improved prior for optical flow computation in spiking neural networks
di: Yedutenko, Matthew, et al.
Pubblicazione: (2024)

A two-stage algorithm in evolutionary product unit neural networks for classification
di: Tallón-Ballesteros, Antonio J., et al.
Pubblicazione: (2024)

TESO Tabu Enhanced Simulation Optimization for Noisy Black Box Problems
di: Soykan, Bulent, et al.
Pubblicazione: (2025)

Towards free-response paradigm: a theory on decision-making in spiking neural networks
di: Zhu, Zhichao, et al.
Pubblicazione: (2024)

A Spiking Neural Network Implementation of Gaussian Belief Propagation
di: Adamiat, Sepideh, et al.
Pubblicazione: (2025)

When Spiking neural networks meet temporal attention image decoding and adaptive spiking neuron
di: Qiu, Xuerui, et al.
Pubblicazione: (2024)

STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion
di: Xu, Changqing, et al.
Pubblicazione: (2023)

Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
di: Nhan, Luu Trong, et al.
Pubblicazione: (2025)

APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning
di: Kumar, Ravin
Pubblicazione: (2022)

Implementation of high-efficiency, lightweight residual spiking neural network processor based on field-programmable gate arrays
di: Yue, Hou, et al.
Pubblicazione: (2025)

CMOS-based area-and-power-efficient neuron and synapse circuits for time-domain analog spiking neural networks
di: Chen, Xiangyu, et al.
Pubblicazione: (2022)

Decentralised self-organisation of pivoting cube ensembles using geometric deep learning
di: Dobreva, Nadezhda, et al.
Pubblicazione: (2025)

Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks
di: Ravichandran, Naresh, et al.
Pubblicazione: (2024)