MCLNN improves music genre classification with automated feature exploration.
problem Music genre classification using neural networks.
method MCLNN uses a mask to enforce sparseness and learn time-frequency representations.
result MCLNN achieves competitive accuracy compared to state-of-the-art methods.
Neural networks are vulnerable to adversarial examples due to ill-conditioned weight matrices.
problem Vulnerability of neural networks to adversarial examples.
method Used orthogonal regularization to ensure the weight matrix's condition number remains low.
result Orthogonal regularization increases adversarial accuracy on MNIST and F-MNIST datasets.
Neural networks improve Bermudan option pricing accuracy.
problem Pricing Bermudan options with conditional expectation challenges.
method Neural network approximations of conditional expectations.
result Longstaff and Schwartz algorithm convergence with neural networks.
MCLNN improves sound recognition by learning frequency bands.
problem Sound recognition from neural networks often misses environmental sound specifics.
method MCLNN incorporates filterbank behavior and automates feature combination exploration.
result MCLNN outperforms state-of-the-art methods on ESC-10 dataset.
Symmetric functions learn better with strategic initial conditions.
problem Understanding how to improve learning efficiency for symmetric functions in neural networks.
method Investigates the impact of initial conditions on SGD training for symmetric functions in neural networks with one hidden layer.
result Strategic initial conditions can lead to efficient generalization guarantees for learning symmetric functions.
Generative neural networks generate complex geological patterns with conditioning.
problem Generating complex geological patterns with spatial observations.
method Extending a generator network with a second inference network to learn conditioning.
result Parametrization for direct generation of conditional realizations.
Paper develops neural network for Mandarin polyphone disambiguation.
problem Homograph problem in Mandarin Chinese text-to-speech.
method Bidirectional RNN for context, prediction network for mapping embeddings to pronunciations.
result Achieves 94.69% accuracy on polyphonic character dataset.
Study shows depth improves trainability of neural networks by improving kernel conditioning.
problem Improving trainability of neural networks with random initialization and overparameterization.
method Analyzes the role of depth in training neural networks, proving that depth improves conditioning of kernel matrices.
result General result showing depth improves trainability of neural networks by improving the conditioning of kernel matrices.
Method learns conditional distributions using neural entropic optimal transport.
problem Challenges in learning multiple conditional distributions.
method Neural entropic optimal transport method with two networks and regularization.
result Effective learning of conditional distributions with limited samples.
New theory for local parameterization of deep ReLU networks.
problem Determining local parameters of deep ReLU neural networks.
method Introducing local lifting operators and charts of a manifold, deriving necessary and sufficient conditions for local identifiability.
result Sharp and testable conditions for local identifiability of deep ReLU networks.
NCP uses neural networks to efficiently learn conditional distributions.
problem Learning conditional distributions for statistical inference.
method Neural Conditional Probability (NCP) approach.
result NCP efficiently handles complex probability distributions and matches leading methods.
A neural network derived from first principles using MaxEnt.
problem Developing a neural network from first principles.
method Derived a neural network using the principle of Maximum Entropy, with linear dimension-reducing transformations and conditional mean estimators.
result Unified theoretical justification for activation functions like sigmoid, softplus, and relu.
The paper characterizes neural network landscapes for gradient dominance and regularity.
problem Understanding the landscape of neural network loss functions.
method Characterization of gradient dominance and regularity conditions for neural networks.
result Explicit characterization of global minimizers and landscape properties for different neural network types.
New metric predicts neural network reliability under novel conditions.
problem Verifying neural networks' safety in novel scenarios.
method ML Dependability metric, Task Undependability, Harmful Undependability.
result Accurately predicts reliability under novel conditions.
Softmax emerges naturally in neural networks as a measure of conditional mutual information.
problem The artificial nature of softmax in neural networks.
method Information-theoretic perspective to derive log-softmax and evaluate conditional mutual information.
result Training deterministic neural networks through log-softmax maximises conditional mutual information.
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss surface is still incomplete. For deep linear networks, we present necessary and s…
MCLNN improves music genre classification by learning frequency bands.
problem Classifying music genres using neural networks adapted from image recognition.
method MCLNN learns frequency bands, reducing susceptibility to frequency shifts and enabling concurrent exploration of feature combinations.
result MCLNN outperforms state-of-the-art Convolutional Neural Networks on the Ballroom music dataset.
GMNN combines conditional random fields and graph neural networks for relational data.
problem Semi-supervised object classification in relational data.
method Combines conditional random fields and graph neural networks. Uses variational EM algorithm for training.
result GMNN achieves state-of-the-art results on object classification, link classification, and unsupervised node representation learning.
Estimates conditional distribution function using neural networks for censored and uncensored data.
problem Estimating conditional distribution function for censored and uncensored data.
method Neural network algorithm based on Cox regression with time-dependent covariates, using full likelihood with unconstrained optimization.
result Proposed method yields more accurate estimates than existing methods when model assumptions are violated.
The study characterizes the conditioning of the Gauss-Newton matrix in neural networks.
problem Understanding the conditioning of the Gauss-Newton matrix in neural networks.
method Theoretical analysis of the GN matrix in deep linear and ReLU networks, extending to residual connections and convolutional layers.
result Established tight bounds on the condition number of the GN matrix in neural networks.
Engression uses neural networks to learn conditional distributions, analyzing its error components.
problem Analyzing the error in neural-network-based engression.
method Engression decomposes excess risk into approximation, stochastic, and Monte Carlo errors.
result Established convergence rates under compositional smoothness assumptions.
Neural IVP solves IVPs with neural networks, overcoming scaling and conditioning issues.
problem Solving initial value PDEs with neural networks is challenging due to numerical errors and limited scalability.
method Developed an ODE-based approach to solve IVPs with neural networks, preventing ill-conditioning and scaling issues.
result Neural IVP solves challenging PDEs with neural networks efficiently and accurately.
Unified neural network for linear and nonlinear dimension reduction.
problem Efficiently perform linear and nonlinear sufficient dimension reduction.
method Belted and Ensembled Neural Network (BENN) framework.
result Unified framework for both linear and nonlinear dimension reduction.
SGD converges with positive probability for non-convex deep neural networks under specific conditions.
problem Convergence of SGD for non-convex deep neural networks.
method Established local convergence with positive probability under local Łojasiewicz condition and additional structural assumption.
result SGD converges with positive probability for non-convex deep neural networks under specific conditions.
The paper proves neural network identifiability for a broad range of nonlinearities.
problem Can a neural network's architecture, weights, and biases be uniquely determined by its input-output map?
method Derive necessary genericity conditions for identifiability of neural networks of arbitrary depth and connectivity with an arbitrary nonlinearity.
result Construct a family of nonlinearities for which these genericity conditions are minimal, necessary, and sufficient.
Fixed points of nonnegative neural networks are analyzed using fixed point theory.
problem Analyzing fixed points in nonnegative neural networks.
method Fixed point theory, nonlinear Perron-Frobenius theory, monotonic and scalable mappings.
result Conditions for the existence of fixed points in nonnegative neural networks are provided.
MCLNN improves audio classification with binary masks.
problem Improving audio classification accuracy.
method Binary mask applied to CLNN for feature preservation and combination exploration.
result Competitive recognition accuracies on GTZAN and ISMIR2004 datasets.
StrNN uses neural network structures to learn conditional independencies.
problem Learning conditional independencies in neural networks.
method Designing masks for neural networks based on binary matrix factorization.
result StrNN improves density estimation and causal inference.
Advances conditions for neural networks to learn connected decision regions.
problem Conditions for neural networks to learn connected decision regions.
method Developed sufficient and necessary conditions for connected decision regions using a wider class of activation functions.
result Proven neural networks with pyramidal structure and certain activation functions produce connected decision regions.
Deep neural networks' Jacobian spectrum becomes well-conditioned with orthogonal weights.
problem Understanding and handling the Jacobian spectrum of deep neural networks.
method Applying free probability theory to show almost sure asymptotic freeness of Jacobians in the wide limit.
result Layer-wise Jacobians of deep neural networks with orthogonal weights are almost surely asymptotically free.
Meta-learning neural networks to solve diverse PDEs efficiently.
problem Efficiently solving new PDE problems with minimal training.
method Neural network meta-learning of PDE problem representations.
result Meta-learned neural networks predict PDE solutions with high accuracy.
GNPs use graph neural networks to predict target points with uncertainty quantification.
problem Predicting points on graphs with uncertainty.
method Graph Neural Processes (GNP) that operate on graph data, taking context features and outputting a target point distribution.
result GNPs can quantify uncertainty in graph data predictions.
We compress large neural networks for quick adaptation to specific contexts.
problem How to quickly adapt a pretrained large neural network to specific contexts.
method Propose a Bayesian hypernetwork framework to compress the network and encourage sparsity.
result Generated compressed networks are significantly smaller than baseline methods.
CSPNs combine SPNs and neural networks for tractable probabilistic modeling.
problem Combining tractable SPNs with neural networks' expressiveness.
method Developed CSPNs by conditioning SPN parameters on inputs and learning structure from data.
result CSPNs outperform other models in multilabel image classification.
New method solves PDEs for any initial condition without retraining.
problem Solving PDEs for different initial conditions requires retraining neural solvers.
method Formulate solution as conditional probability distribution.
result Approximates PDE solution for arbitrary initial conditions.
A neural network approach for efficient conditional SHAP calculations.
problem Efficiently calculating conditional SHAP values for various models.
method Surrogate neural network approach for conditional SHAP.
result Efficiently calculates conditional SHAP values for neural networks and other regression models.
Generative neural network designs novel 3D molecules with specified properties.
problem Designing molecules with desired properties in chemistry.
method Conditional generative neural network for 3D molecular structures.
result Demonstrated utility in generating novel molecules with specified motifs or composition.
A study on preventing catastrophic forgetting in neural networks using conditional computation.
problem Catastrophic forgetting in connectionist neural networks.
method Conditional computation framework where parameters are conditioned on each input example.
result Proposed conditional rehearsal to prevent forgetting of previously learned examples.
Enhances neural network solvers for PDEs with complex boundary conditions.
problem Challenges in solving PDEs with high accuracy and complex boundary conditions.
method Integrates natural gradient optimization with numerical time-stepping schemes to enforce Dirichlet boundary conditions.
result Superior accuracy and computational efficiency of the proposed methods for solving PDEs.
MCLNN improves sound event recognition with fewer parameters.
problem Improving sound event recognition with deep neural networks.
method Developed MCLNN to enforce sparseness and frequency shift invariance.
result MCLNN achieved competitive performance with 12% fewer parameters.
Neural GARCH models financial time series with time-varying coefficients.
problem Modeling conditional heteroskedasticity in financial time series.
method Neural network adaptation of GARCH and BEKK models with time-varying coefficients parameterized by a recurrent neural network.
result Neural Students t model consistently outperforms other models on financial time series.
Simplified neural network EFTs reveal a single critical condition.
problem Understanding neuron statistics in neural networks at initialization.
method Diagrammatic approach to effective field theories (EFTs).
result A single condition governs criticality of all neuron preactivations.
DGNN predicts financial margin calls under stress tests.
problem Forecasting margin calls in dynamic financial networks.
method Dynamic Graph Neural Network (DGNN) architecture.
result DGNN produces accurate forecasts up to 21 days.
Neural-Kernelized method estimates conditional densities without parametric assumptions.
problem Estimating conditional densities on large datasets with neural networks.
method Score matching with neural networks and neural-kernelized approach.
result Consistent in conditional density estimation, compares favorably with existing methods.
The paper improves neural network-based conditional density estimation for finance.
problem Capturing statistical relationships between variables using neural networks.
method Best practices and benchmarks for conditional density estimation with noise regularization and data normalization.
result Proposed methodology outperforms other estimators in various benchmarks.
Automatically designs neural network structure using matrix conditioning.
problem Choosing an effective size and structure of neural networks for new datasets is time-consuming.
method Adjusts neuron proportions and scales network size using matrix conditioning.
result Small networks achieve high accuracy on various datasets.
Optimizes neural networks using hypernetworks for better likelihood.
problem Maximizing conditional likelihood of neural networks.
method Optimizes hypernetworks to directly maximize likelihood.
result Competitive results on regression and classification benchmarks.
HCNAF models complex conditional distributions for probabilistic occupancy forecasting.
problem Modeling complex conditional probability density functions for occupancy forecasting.
method Hyper-Conditioned Neural Autoregressive Flow (HCNAF) combining AF and hyper-network.
result HCNAF achieves state-of-the-art performance in self-driving datasets.