-
Discovery of Dynamics via Deep Learning
The dataset used in the paper is a collection of time series data from a dynamical system, which is used to test the performance of the network-based LMMs for discovering... -
Synthetic dataset for multiplicative interactions
A synthetic dataset that exhibits multiplicative interactions between inputs. The function to be approximated is a multi-variate polynomial or multinomial. -
Model of Learning in C. elegans
A mathematical model of the fundamental roots of learning mechanisms within the brain of Caenorhabditis elegans. -
State Space Representations of Deep Neural Networks
This paper deals with neural networks as dynamical systems governed by finite difference equations. It shows that the introduction of k-many skip connections into network... -
Linear Frequency-Principle (LFP) model for two-layer neural networks
The dataset used in this paper is a collection of training data and target functions for two-layer neural networks. The dataset is used to test the performance of the Linear... -
Overparametrised Shallow ReLU Networks
The dataset used in the paper is a high-dimensional dataset for supervised learning, with a focus on shallow neural networks and overparametrization. -
Multidimensional Cascade Neuro-Fuzzy System with Neuron Pool Optimization in ...
The dataset used in this paper is a multidimensional cascade neural network with neuron pool optimization in each cascade. -
Disentangle Sample Size and Initialization Effect on Perfect Generalization f...
The dataset used in the paper is a two-layer neural network with a single-neuron target function. -
Restricted Boltzmann Machine for Combinatorial Optimization and Integer Facto...
The dataset used in this paper is a Restricted Boltzmann Machine (RBM) for combinatorial optimization and integer factorization. -
Two-Layer Neural Networks
The dataset is used to analyze the convergence of stochastic gradient descent for two-layer neural networks. -
Size and Width of the Decoder of a Boolean Threshold Autoencoder
The dataset is used to study the size and width of autoencoders consisting of Boolean threshold functions. -
Nonlinear controllability and function representation by neural stochastic di...
The dataset is used to test the capability of neural stochastic differential equations to represent nonlinear functions of their initial condition. -
Interaction Networks
Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms -
Simulated dataset
The dataset used in this paper is a simulated dataset with 200 variables and 50 observations. The variables are generated from a multivariate normal distribution with a... -
MNIST and CIFAR-10 datasets
The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions. -
Retrieving Labels for Noisy Input Patterns
Retrieving labels for noisy input patterns. -
Self-Organization to Exponential Capacity
Self-organization to exponential capacity. -
Robust Exponential Memory in Hopfield Networks
Robust exponential memory in Hopfield networks. -
Associative Content-Addressable Memory with Exponentially Many Robust Stable ...
Associative content-addressable memory with exponentially many robust stable states and robust error correction. -
Benchmarking neural network robustness to common corruptions and perturbations
Benchmarking neural network robustness to common corruptions and perturbations.
