3260 papers • 126 benchmarks • 313 datasets
Simulation of abstract or biophysical neural networks in silico
(Image credit: Papersgraph)
These leaderboards are used to track progress in neural-network-simulation
No benchmarks available.
Use these libraries to find neural-network-simulation models and implementations
No datasets available.
No subtasks available.
Simulation results show that the proposed network reconstruction and retraining recovers the inference accuracy of the original BNN, and the accuracy loss of the proposed scheme in the CIFAR-10 testcase was less than 1.1% compared to the original network.
A collection of three classes of AEM problems: metamaterials, nanophotonics, and color designs is developed and methods and models that generalize best over the three problems are identified to establish the best practice and baseline results upon.
This work presents a PINN approach to solving the equations of coupled flow and deformation in porous media for both single-phase and multiphase flow, and proposes a sequential training approach based on the stress-split algorithms of poromechanics.
This paper develops a DRL based algorithm, in which the joint design is obtained through trial-and-error interactions with the environment by observing predefined rewards, in the context of continuous state and action, and obtains the comparable performance compared with two state-of-the-art benchmarks.
This work considers several examples of inverse problems and compares the performance of each model to predict the unknown potentials and refractive indices respectively, from a given small set of the lowest eigenvalues.
It is argued that this package facilitates the use of spiking networks for large-scale machine learning problems and some simple examples by using BindsNET in practice are shown.
Adding a benchmark result helps the community track progress.