This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into the learning process of the network. But this strategy can not be applied for E…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “hidden nodes”
RBMs model binary interactions with hidden node activation effects.
problem Understanding how RBM hidden node activation affects binary variable distributions.
method Investigated RBM marginal distributions with different hidden node activation functions.
result Found exact expressions for RBM marginals as interacting binary variables.
We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for incoming weight vec…
Vanishing nodes cause hidden nodes to behave similarly, complicating deep neural network training.
problem Complicating deep neural network training due to hidden nodes behaving similarly.
method Introduced vanishing node indicator (VNI) to quantify node redundancy and correlated behavior.
result The effective number of nodes vanishes to one as VNI increases, indicating a challenging training scenario.
CoulGAT interprets GAT models by analyzing node interactions.
problem Understanding and interpreting the complex interactions within graph attention networks.
method Developed a CoulGAT framework to analyze and interpret GAT model layers and datasets.
result Extracted node-node and node-feature interactions to define a standard model for graph structure.
A new model captures diffusion dynamics in networks using hidden states.
problem Capturing temporal relationships and hidden content trajectories in network diffusion.
method A topological recurrent neural model that embeds diffusion history as hidden states.
result Good experimental performances for diffusion modeling and prediction.
The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar…
ELMs benefit from using equal number of hidden nodes to training samples.
problem Overfitting and underfitting in ELMs with hidden nodes.
method ELMs with hidden nodes equal to training samples achieve perfect training.
result ELMs with larger hidden nodes outperform traditional ELMs.
New method improves random parameter generation in neural networks.
problem Standard method of generating random weights and biases in neural networks has drawbacks.
method Proposes a new method to generate random parameters ensuring nonlinear sigmoids remain in the input hypercube and uniformly distributed slope angles for activation functions.
result Ensures the most useful nonlinear fragments of sigmoids remain in the input hypercube.
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping a…
New method uncovers hidden causal connections in multivariate point process networks.
problem Unobserved hidden variables confound causal discovery in high-dimensional point process networks.
method Proposes a deconfounding procedure to estimate causal interactions among observed nodes with unknown unobserved processes.
result The method accurately identifies causal interactions among observed processes, even with hidden variables.
Learning with hidden variablesq-bio.NC
Learning and inferring features that generate sensory input is a task continuously performed by cortex. In recent years, novel algorithms and learning rules have been proposed that allow neural network models to learn such features from natural images, written text, audio signals, etc. These networks usually involve de…
The study examines how the choice of activation function affects the hidden node distribution in deep networks.
problem The effect of activation function on the distribution of hidden nodes in deep networks.
method Analysis of joint probability distribution of hidden variables in deep networks with random weights and biases.
result The convergence of hidden node lengths to a simple function of network parameters and activation function under minimal assumptions.
New results on inferring hidden states in trackable weak models.
problem Inferring hidden states in trackable weak models.
method Analyzing strongly-connected trackable weak models and reconstructing branch choices.
result The number of hypotheses in strongly-connected trackable models is bounded by a constant.
Two new inverse-free ELM algorithms for incremental and decremental learning are proposed.
problem Efficiently updating and removing multiple hidden nodes in ELM.
method Improved inverse-free recursive algorithms for Tikhonov regularization.
result Inverse-free algorithms for ELM with multiple hidden nodes and redundant nodes.
3-layer ReLU networks with Ω(√N) nodes can memorize most datasets.
problem Understanding memorization capacity of ReLU networks.
method Analyzing depth and width requirements for memorization.
result Width Θ(√N) is necessary and sufficient for memorizing N data points.
This paper unifies observability notions for colored graphs and identifies graph modifications to improve observability.
problem Observability of colored graphs and its relationship to graph properties.
method Unified framework of observability notions, graph modifications, and NP-completeness results.
result Identification of graph modifications to improve observability and NP-completeness of one modification problem.
DAG models with hidden variables present many difficulties that are not present when all nodes are observed. In particular, fully observed DAG models are identified and correspond to well-defined sets ofdistributions, whereas this is not true if nodes are unobserved. Inthis paper we characterize exactly the set of dist…
Deep belief networks can approximate any multivariate density with binary hidden units.
problem Approximating multivariate probability densities with binary hidden units.
method Sharp quantitative bounds on approximation error in terms of hidden units.
result Deep belief networks can approximate any multivariate density with binary hidden units under mild integrability requirements.
Paper introduces a new method to compute pseudoinverse for ELM with large datasets.
problem Efficient computation of pseudoinverse for ELM with large datasets.
method Rank-based matrix decomposition of the hidden layer matrix.
result Optimal training time and reduced computational complexity for large hidden nodes.
We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables. This approximation can be used to select models given large samples of data. The standard BIC as well as our extension punishes the complexity of a model according to …
RVFL NNs perform well without direct links and output bias for regression.
problem Effect of direct links and output bias on RVFL performance.
method Classical and two new methods for generating hidden nodes' parameters tested.
result Direct links and output bias do not significantly improve RVFL accuracy for typical nonlinear regression problems.
Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters. We explore these landscapes using optimisation tools developed for potential energy landscapes in molecular science. The number of local minima and transition sta…
Theoretical study shows adversarial training improves robustness in deep learning models.
problem Ensuring robustness in pre-trained deep learning models.
method Theoretical analysis of adversarial training and feature purification in two-layer neural networks.
result Adversarial training leads to feature purification, making models more robust to attacks.
Guided Dropoutcs.LG
Guided dropout improves neural network performance by selectively dropping nodes.
problem Overfitting in deep neural networks.
method Guided selection of nodes for dropout based on their strength.
result Guided dropout leads to better generalization compared to conventional dropout.
CoMGNN models heterogeneous graphs with evolving nodes and edges.
problem Modeling complex, evolving graphs with diverse information.
method Meta graph attention on co-evolving heterogeneous graphs.
result Significant improvement over state-of-the-art methods.
Optimal rates for learning hidden tree structures are determined.
problem Learning hidden tree structures from noisy data.
method Study of the (noisy) information threshold and the Chow-Liu algorithm.
result Optimal rates for structure recovery are inversely proportional to the information threshold squared.
Autoencoder identifies cancer cells from normal ones using gene expression data.
problem Distinguishing between normal and cancer cells using gene expression profiles.
method Autoencoder trained on large tumor dataset to capture latent representations, using HPC toolkit for efficiency.
result Autoencoder node saliency identifies key differentiating features between normal and cancer cells.
Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular technique to avoid overfitting in deep learning. For single hidden-layer linear neural …
In many real-world networks, nodes have class labels, attributes, or variables that affect the network's topology. If the topology of the network is known but the labels of the nodes are hidden, we would like to select a small subset of nodes such that, if we knew their labels, we could accurately predict the labels of…
New model detects hidden group structures in criminal networks.
problem Challenges in identifying group structures in criminal networks with noisy data.
method Developed an extended stochastic block model (ESBM) to infer group structures.
result Unveiled complex block structures in an Italian mafia network.
We present and implement two algorithms for analytic asymptotic evaluation of the marginal likelihood of data given a Bayesian network with hidden nodes. As shown by previous work, this evaluation is particularly hard for latent Bayesian network models, namely networks that include hidden variables, where asymptotic ap…
We study the problem of learning a latent tree graphical model where samples are available only from a subset of variables. We propose two consistent and computationally efficient algorithms for learning minimal latent trees, that is, trees without any redundant hidden nodes. Unlike many existing methods, the observed …
DIFNET tackles the suspended animation problem in deep graph neural networks.
problem Deep graph neural networks suffer from the suspended animation problem.
method DIFNET uses neural gates and graph residual learning for node hidden state modeling, and includes an attention mechanism for node neighborhood information diffusion.
result DIFNET effectively addresses the suspended animation problem and improves learning performance.
This paper studies node embeddings of networks, revealing their geometric properties.
problem Understanding the geometric properties of node embeddings in random networks.
method Characterization of ergodic limits, generalization, and convex relaxations of random walk node embedding objectives.
result The optimal node embedding Grammians have rank 1 for a nuclear norm relaxation of the non-randomized objective.
Study of deep neural networks with dependent weights leading to new model limits and properties.
problem Characterizing deep neural networks with dependent weights in the infinite-width limit.
method Modeling weights as a mixture of Gaussian distributions and analyzing the infinite-width limit.
result Characterization of neural network layers by scalar parameters and Lévy measures, leading to new model limits.
Study reveals how initial weights influence convergence in deep ReLU networks.
problem Understanding the dynamics and generalization of deep ReLU networks.
method Teacher-student setting, gradient analysis, and activation assumptions.
result Initial weights close to teacher nodes lead to faster convergence, and fan-out weights of other nodes converge to zero in over-parameterized cases.
New algorithm reduces sample complexity for learning CNNs.
problem Learning one-hidden-layer CNNs with various activation functions.
method Approximate gradient descent algorithm for training CNNs.
result Sample complexity matches information-theoretic lower bound for linear activation functions.
Deep Stacked Stochastic Configuration Networks for Lifelong Learning of Non-Stationary Data Streamscs.LG
The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters advancing conventional randomized approaches constrained with a fixed scope of rand…
Wide neural networks with asymmetrical node scaling converge globally and learn features.
problem Global convergence and feature learning in over-parameterised shallow networks.
method Gradient-based optimisation of wide, shallow neural networks with asymmetrical node scaling.
result Gradient flow and gradient descent converge to a global minimum and learn features, unlike in the NTK parameterisation.
EPFGNN models graph connections for better node classification.
problem Graph node classification issues due to feature aggregation.
method EPFGNN models graph as a Markov Random Field with explicit pairwise factors and a GNN backbone.
result EPFGNN improves semi-supervised node classification performance.
CgNN uses network structure as IVs to estimate causal effects in networks.
problem Hidden confounders complicate causal effect estimation in network data.
method CgNN combines GNNs and attention mechanisms to leverage network structure as IVs.
result CgNN effectively mitigates hidden confounder bias and improves causal effect estimation.
Paper studies vertex correspondence recovery in correlated graphs with node features.
problem Recovering hidden vertex correspondence between two correlated graphs with observed edge weights and node features.
method Introduced featured correlated Gaussian Wigner model and proposed QPAlign algorithm for quadratic programming relaxation.
result Characterized optimal information-theoretic thresholds for exact and partial recovery of latent mapping.
New method constructs neural network architecture iteratively to optimize learning.
problem Difficulty in setting optimal random weights and biases for feedforward neural networks.
method Iteratively constructs hidden nodes, accepting only those that significantly reduce training error.
result Faster convergence and more compact network architecture with fewer significant neurons.
Generalization of an Upper Bound on the Number of Nodes Needed to Achieve Linear Separabilitystat.ML
An important issue in neural network research is how to choose the number of nodes and layers such as to solve a classification problem. We provide new intuitions based on earlier results by An et al. (2015) by deriving an upper bound on the number of nodes in networks with two hidden layers such that linear separabili…
Improved covariate shift handling with node-based Bayesian neural networks.
problem Improving generalization under covariate shift in neural networks.
method Introduced node-based Bayesian neural networks that learn latent noise variables to represent input corruptions.
result Node-based BNNs perform well under covariate shift due to input perturbations, improving uncertainty estimation and robustness.
We investigate the problem of factorizing a matrix into several sparse matrices and propose an algorithm for this under randomness and sparsity assumptions. This problem can be viewed as a simplification of the deep learning problem where finding a factorization corresponds to finding edges in different layers and valu…
New method detects corporate fraud in noisy financial networks.
problem Detecting corporate fraud in rich yet noisy financial networks.
method Knowledge-enhanced GCN with Robust Two-stage Learning (KeGCN_R)
result KeGCN_R outperforms baselines in fraud detection effectiveness and robustness.