Hidden Markov Neural Networks balance adaptation and forgetting in time-series data.
problem Balancing adaptation to new data and forgetting outdated information in time-series forecasting.
method Modeling weights as hidden states of a Hidden Markov model, using a filtering algorithm for learning a variational approximation of the posterior distribution over weights, and employing sequential Bayes by Backprop with variational DropConnect for regularization.
result Achieves strong predictive performance and effective uncertainty quantification on various tasks.
Randomly chosen primary hidden units and derived secondary units reduce neural network complexity.
problem Large number of hidden units in neural networks.
method Introducing primary and secondary hidden units with random weights for primary units and derived weights for secondary units.
result Significant reduction in the number of hidden units without compromising accuracy.
New findings on hidden symmetries in ReLU networks.
problem Understanding the redundancy and symmetries in ReLU network parameter space.
method Analyzing parameter settings and function classes for various network architectures.
result For certain network architectures, there are no hidden symmetries.
New insights into hidden minima in neural networks.
problem Identifying hidden minima in two-layer ReLU networks.
method Analyzing curves along which loss is minimized, focusing on eigenvalue contributions.
result Distinctive structural and symmetry properties of arcs emanating from hidden minima.
Formula found for neural network error with fixed weights.
problem Understanding error in neural networks with fixed weights.
method Provided an explicit formula for approximation error.
result Explicit formula for neural network error with fixed weights.
Chemical networks outperform spiking neural networks in classification tasks.
problem Learning tasks with spiking neural networks require hidden layers, which are computationally expensive.
method Used deterministic mass-action kinetics to prove chemical reaction networks without hidden layers can solve tasks previously solved by spiking neural networks.
result A chemical reaction network without hidden layers outperforms a spiking neural network with hidden layers in a handwritten digit classification task.
Algorithm approximates continuous functions using a neural network with one hidden layer.
problem Finding the weights/parameters for a neural network to approximate continuous functions.
method Algorithm outlines an approach to reconstruct any continuous function using a neural network with one hidden layer.
result Algorithm successfully reconstructs any continuous function using a neural network with one hidden layer.
Study on hidden units in finite Bayesian neural networks and their tail properties.
problem Understanding the behavior of hidden units in finite Bayesian neural networks.
method Introduced a generalized Weibull-tail property to describe hidden units tails.
result Unit priors become heavier-tailed going deeper, providing insights into finite Bayesian neural networks.
Study examines dependence properties of Bayesian neural network units in finite-width networks.
problem Understanding dependence properties of hidden units in practical finite-width Bayesian neural networks.
method Theoretical analysis and empirical evaluation of depth and width impacts.
result Hidden units in finite-width Bayesian neural networks are dependent, contrary to the infinite-width limit assumption.
New method amplifies hidden structure in complex networks.
problem Difficulty in uncovering hidden structure in complex networks.
method Iterative weakening of dominant structure through randomization.
result Theoretical support for the effectiveness of structure amplification.
A neural network with a single hidden layer can't represent certain multivariable functions.
problem Representing certain multivariable functions with a neural network having only one hidden layer.
method Developed a continuum version of a one-hidden-layer neural network with ReLU activation, and proved constraints on its parameters and second derivative.
result Existence of a smooth binary function that cannot be precisely represented by any such neural network.
Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from the training distribution, even if these differences are very small, as is the case with adversarial examples. We propose Fortified Networks,…
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.
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 …
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.
Two-hidden-layer networks can approximate any continuous function.
problem Proving the universal approximation property of two-hidden-layer feedforward neural networks.
method Constructive approach based on simplicial maps and triangulations.
result Concrete architecture and weights can be obtained for approximating continuous functions.
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.
A novel RNN model with shuffled hidden states.
problem Improving recurrent neural network performance.
method Permuting hidden states and applying learned functions.
result Competitive results compared to literature baselines.
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
The paper introduces an inference algorithm for graded Bayesian networks.
problem Inference in graded Bayesian networks.
method Tropicalization of the marginal distribution of observed variables, rank-by-rank evaluation of hidden variables.
result Established an inference algorithm for graded Bayesian networks.
Paper shows how to infer hidden states in neural networks analytically.
problem Intractability of Bayesian inference for neural networks.
method Leverage tractable approximate Gaussian inference (TAGI) for hidden states inference.
result Demonstrates inference of hidden states through constraints for various applications.
Study on neural networks' sample complexity with one hidden layer.
problem Understanding how sample complexity is affected by network architecture and norm constraints.
method Norm-based uniform convergence bounds for scalar-valued one-hidden-layer networks, focusing on spectral and Frobenius norms.
result Spectral norm control is insufficient for uniform convergence guarantees, but Frobenius norm control is sufficient, with conditions.
Deep neural networks can handle high dimensions without losing accuracy.
problem The curse of dimensionality in nonparametric regression.
method Least squares estimates on fully connected neural networks with ReLU activation functions.
result Similar convergence results to deep learning models with sparsity constraints can be achieved without such constraints.
We study how finite Bayesian neural networks adapt their hidden representations.
problem Understanding how finite Bayesian neural networks differ from infinite ones.
method We analyze the asymptotics of learned feature kernels for various network architectures.
result The leading finite-width corrections to feature kernels have a universal form.
End-to-end speaker recognition method using neural networks.
problem Speaker and session variability in speaker verification.
method Joint Factor Analysis with tied hidden variables, MAP adaptation, two-step backpropagation.
result Improved likelihood ratios and robust performance on RSR2015 database.
Neural networks learn more efficiently with hidden factorial structures.
problem Challenges in high-dimensional statistical learning.
method Controlled experimental framework to test neural networks' ability to exploit hidden factorial structures.
result Neural networks can leverage hidden factorial structures to learn discrete distributions more efficiently.
Enhanced BCPNN learns hidden representations without labels.
problem Unsupervised learning of hierarchical representations in neural networks.
method Extended BCPNN architecture with local Hebbian learning mechanisms.
result Demonstrated capability for unsupervised learning of salient hidden representations.
We establish upper bounds for the minimal number of hidden units for which a binary stochastic feedforward network with sigmoid activation probabilities and a single hidden layer is a universal approximator of Markov kernels. We show that each possible probabilistic assignment of the states of n output units, given t…
To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer. The GBN's hidd…
CONE evaluates treatment assignment functions using networked observational data to mitigate hidden confounding bias.
problem Evaluate treatment assignment functions using networked observational data with hidden confounders.
method CONE framework that learns partial representations of latent confounders and combines them for counterfactual evaluation.
result Network information mitigates hidden confounding bias in counterfactual evaluation.
Proves SQ lower bounds for learning two-hidden-layer neural networks.
problem Learning two-hidden-layer ReLU networks with Gaussian inputs.
method Refined lifting procedure to reduce Boolean PAC learning to Gaussian.
result Superpolynomial SQ lower bounds for Gaussian inputs.
Study reveals properties of local minima in ReLU networks.
problem Understanding the loss landscape of neural networks.
method Theoretical analysis of one-hidden-layer ReLU networks.
result All differentiable local minima are global within certain regions.
In recent years, there is a growing interest in learning Bayesian networks with continuous variables. Learning the structure of such networks is a computationally expensive procedure, which limits most applications to parameter learning. This problem is even more acute when learning networks with hidden variables. We p…
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \e…
This paper extends depth separation results to piece-wise oscillatory functions.
problem Approximating functions with piece-wise oscillatory structure using neural networks.
method Extends existing results to piece-wise oscillatory functions using proof strategy from (Eldan and Shamir, 2016).
result Approximation by one-hidden-layer networks holds at a poly(d) rate for functions with constant domain radius and oscillation rate.
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…
Kolmogorov neural networks can represent various types of functions.
problem Representing different types of functions with neural networks.
method Continuous, discontinuous bounded or unbounded activation functions in a two hidden layer model.
result Kolmogorov neural networks can represent continuous, discontinuous bounded and all unbounded multivariate functions.
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…
New method models unknown systems with hidden parameters using neural networks.
problem Modeling unknown dynamical systems with hidden parameters.
method Training a deep neural network (DNN) model using trajectory data of the unknown system.
result DNN model accurately predicts unknown dynamical systems with new initial conditions.
1-hidden layer networks lead to deep networks that outperform AlexNet on ImageNet.
problem Improving deep neural networks for image classification tasks.
method Sequentially building deep networks layer by layer using shallow networks as auxiliary problems.
result 11-layer network trained by this method exceeds several VGG models on ImageNet.
We introduce a new paradigm that is important for community detection in the realm of network analysis. Networks contain a set of strong, dominant communities, which interfere with the detection of weak, natural community structure. When most of the members of the weak communities also belong to stronger communities, t…
GenHMM combines neural networks with HMM for sequential data modeling.
problem Sequential data modeling challenges.
method Integrates neural network generative models into HMM framework.
result GenHMM improves likelihood computation and tractability.
ReLU activations lead to smoother learning curves compared to sigmoidal activations in neural networks.
problem Comparing the performance of ReLU and sigmoidal activations in neural networks.
method Analytical computation of learning curves in shallow networks with different activation functions.
result ReLU networks exhibit continuous transitions in performance, while sigmoidal networks show discontinuous transitions.
Revisits the connection between neural networks and the Kolmogorov-Arnold theorem.
problem Explains the limitations of using the Kolmogorov-Arnold theorem to explain neural networks with multiple hidden layers.
method Derives modifications of the Kolmogorov-Arnold representation that transfer smoothness properties to the outer function and can be well approximated by ReLU networks.
result Shows that a deep neural network with most layers approximating the interior function is a more natural interpretation of the Kolmogorov-Arnold representation.
Stable unactivated neurons reduce expressiveness in ReLU networks.
problem Reducing expressiveness in ReLU neural networks due to stably unactivated neurons.
method Investigated the probability of neurons being stably unactivated in ReLU networks with symmetric weight and bias distributions.
result Proved the probability of a neuron being stably unactivated in the second hidden layer of a ReLU network.
HMRNN combines HMMs and neural networks for Alzheimer's disease forecasting.
problem Improving disease progression modeling with hidden states not fully known.
method Developed HMRNN combining HMMs and recurrent neural networks.
result HMRNN improves disease forecasting and offers novel clinical interpretation.
Universal MLPs with a single hidden layer can learn any function.
problem Learning on various data structures like sequences, images, sets, and graphs.
method Using group theory, the paper proves the universality of a broad class of equivariant MLPs with a single hidden layer.
result Having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance).
To infer a multilayer representation of high-dimensional count vectors, we propose the Poisson gamma belief network (PGBN) that factorizes each of its layers into the product of a connection weight matrix and the nonnegative real hidden units of the next layer. The PGBN's hidden layers are jointly trained with an upwar…