This paper analyzes how normalization layers improve neural network training.
problem Improving generalization performance and training speed of neural networks.
method Global convergence analysis of two-layer neural networks with ReLU activations and Weight Normalization.
result Introduction of normalization layers changes the optimization landscape, enabling faster convergence.
We improve neural network explainability by bypassing batch normalization.
problem Lack of transparency in neural networks.
method Layer-wise Relevance Propagation with a method to include normalization layers.
result Heatmaps are more accurate for convolutional layers with our method.
The paper extends mean field results to three-layer neural networks using SGD.
problem Understanding the dynamics of training three-layer neural networks with SGD.
method Extending mean field results from two-layer networks to three-layer networks with two hidden layers, using non-linear partial differential equations.
result The distributions of weights in the two hidden layers are independent.
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.
Three-layer networks learn more complex features than two-layer networks.
problem Understanding feature learning in deep neural networks.
method Analysis of three-layer neural networks trained with gradient descent.
result Three-layer networks can learn functions that two-layer networks cannot.
New layer sparsity concept improves neural networks.
problem Improving neural network efficiency and interpretability.
method Formulated layer sparsity, introduced regularization and refitting schemes.
result Generated more compact and accurate neural networks.
New GM layers improve neural network performance.
problem Improving neural network performance.
method Employing Gaussian mixture models and Wasserstein gradient flows.
result GM layers achieve comparable performance to two-layer networks.
New proof shows neural networks can represent all multivariate functions.
problem Representing all multivariate functions with neural networks.
method Proved that three-layer neural networks can represent both continuous and discontinuous functions.
result Three-layer neural networks can represent all multivariate functions, including discontinuous ones.
A method to analyze neural network performance by measuring layer saturation.
problem Understanding which layers contribute to network performance.
method Layer saturation method: restricts layer output to eigenspace of variance matrix.
result Layer saturation indicates which layers contribute to network performance.
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.
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.
This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.
problem Understanding the loss landscape of sparse neural networks, especially one-hidden-layer networks.
method Analyzes sparse networks with dense and sparse final layers, focusing on linear and non-linear models.
result Sparse networks can have no spurious valleys under certain conditions, but spurious valleys and minima can exist for wide sparse networks.
The paper analyzes how low-rank layers in neural networks improve generalization.
problem Understanding how low-rank layers affect generalization in neural networks.
method Applying Maurer's chain rule for Gaussian complexity to analyze rank and spectral norm constraints.
result Deep networks with low-rank layers achieve better generalization than those with full-rank layers.
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.
Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its inte…
Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.
Proposes BN layers for neural networks on complex domains, improving training stability and accuracy.
problem Training stability and accuracy issues in neural networks on complex domains.
method Developed Riemannian batch normalization (BN) layers with connections to existing layers.
result Demonstrated improved performance on radar clutter classification, node classification, and action recognition.
Graph Metanetworks process diverse neural architectures efficiently.
problem Processing diverse neural architectures efficiently.
method Builds metanetworks using graph neural networks to process graphs representing input neural networks.
result Proves GMNs are expressive and equivariant to parameter permutation symmetries.
Paper proposes a method to interpret neural networks by decomposing them into simpler tasks.
problem Understanding the complex nonlinear relationships in trained neural networks.
method Non-negative matrix factorization applied to a trained layered neural network.
result Reveals the roles of hidden units in terms of their contribution to each principal task.
New loss functions reveal layer roles in deep neural networks.
problem Understanding the role of individual layers in deep neural networks.
method Derived Deep Gaussian Layer-wise loss functions (DGLs) using Gaussian Processes and SGD.
result First explicit and competitive layer-wise loss functions for deep neural networks.
Gradient descent achieves fast convergence for approximating functions with two-layer neural networks.
problem Approximating continuous functions with two-layer neural networks.
method Gradient descent combined with generic chaining technique from probability theory.
result Gradient descent yields an exponential convergence rate for two-layer neural networks without needing a large width relative to the number of data points.
PHP connects to ReLU neural networks for scalable Bayesian inference.
problem Scalability and Bayesian inference in two-layer ReLU neural networks.
method PHP with Gaussian prior, decomposition propositions, annealed sequential Monte Carlo.
result PHP provides an alternative scalable representation for two-layer ReLU neural networks.
This work analyzes how different layers in deep neural networks contribute to generalization error.
problem Understanding the role of each layer in deep neural networks for generalization.
method Spectral analysis, Neural Tangent Kernel, Hermite polynomials, Spherical Harmonics.
result Initial layers in deep neural networks have a larger bias towards high-frequency functions.
Improved uncertainty estimation in neural networks with VBLL.
problem Improving uncertainty estimation in neural networks.
method Deterministic variational formulation for training Bayesian last layer neural networks.
result Improves predictive accuracy, calibration, and out-of-distribution detection.
A new neural network initialization method is proposed for faster and more accurate training.
problem Efficient initialization for training multi-layer feedforward neural networks.
method Initialization based on Stein's identity, using eigenvectors of cross-moment matrix.
result The SteinGLM method is faster and more accurate than other initialization methods.
Extends capacity analysis to neural networks, showing how capacity is distributed across layers.
problem How capacity is distributed in neural networks with non-linear layers.
method Introduces layer decoupling to quantify non-linear activation's impact, and uses a markovian rule for capacity propagation in deep networks.
result Shows that under certain conditions, capacity allocation in neural networks is equivalent to linear capacity allocation in an extended input space.
New algorithm learns two-layer neural networks under symmetric input distributions.
problem Learning two-layer neural networks with symmetric inputs.
method Method-of-moments framework, spectral algorithms.
result Guaranteed to recover parameters of ground-truth network under certain conditions.
Bayesian Layers adds uncertainty to neural networks, enabling faster experimentation and scalability.
problem Enabling neural networks to quantify uncertainty in predictions.
method Drop-in replacements for common layers, capturing uncertainty over weights, activations, etc.
result Bayesian Layers can fit large models like 5-billion parameter Bayesian Transformers.
Two-layer neural networks learn efficiently using kernel methods in mean-field analysis.
problem Feature learning ability of two-layer neural networks in the mean-field regime.
method Mean-field analysis through kernel methods, focusing on dynamics of the first layer's kernel.
result Two-layer neural networks can learn a union of multiple reproducing kernel Hilbert spaces more efficiently than kernel methods.
Reveals the first layer of deep networks with high activation thresholds.
problem Learning guarantees for deep neural networks with multiple layers.
method Strengthening parameter recovery guarantees for deep networks with a high threshold assumption.
result Reveals the first layer of a deep neural network under specific activation conditions.
The study characterizes sets for which one-layer neural networks are positive.
problem Characterizing sets of points for which one-layer neural networks are positive.
method Investigation of subsets of the real plane for one-layer ReLU neural networks.
result Full characterization of such sets for cones, and necessary condition for any subset of \(\mathbb{R}^d\).
A new neural network model MDRBM improves noise-robustness in classification.
problem Improving noise-robustness in classification problems.
method Stacking a probabilistic-ELM layer on a discriminative restricted Boltzmann machine (DRBM).
result MDRBM outperforms other models, especially in noise-robustness.
A new metric measures saturation of neural network layers.
problem Analyzing the quality of latent representations in neural networks.
method Layer Saturation metric based on spectral analysis.
result Saturation is related to generalization and predictive performance.
Hybrid Bayesian neural networks use function uncertainty for probabilistic inference.
problem Uncertainty in neural network weights is hard to specify and interpret.
method Integrates probabilistic layers with standard deterministic layers for function uncertainty.
result Improves probabilistic inference by encoding function uncertainty.
Study on SGD for overparameterized neural networks, focusing on convergence rates.
problem Understanding convergence rates of SGD in overparameterized two-layer neural networks.
method Combines NTK approximation with RKHS analysis to explore SGD dynamics.
result Established sharp convergence rates for SGD in overparameterized two-layer neural networks.
Speeds up deep neural networks training by 10x using GPU concurrency.
problem Training deep residual neural networks efficiently.
method Layer-wise parallel training with GPU concurrency and Nonlinear Multigrid.
result 10.2x speedup over traditional techniques.
CW normalizes and decorrelates neural network layers for better concept understanding.
problem Challenges in understanding neural network hidden layers.
method Introducing concept whitening (CW) to alter neural network layers.
result CW provides clearer understanding of how networks learn concepts over layers.
This paper introduces a new method for neural networks that doesn't need a global coordinate system.
problem The lack of a global coordinate system in neural networks limits their performance and explainability.
method Proposes a learnable topological layer that works in a general metric space (Hilbert space) without requiring a Euclidean space.
result The proposed method eliminates the need for a costly parametrization stage and achieves optimal network performance.
Our paper explains deep neural collapse in multiple layers.
problem Understanding deep neural collapse in multi-layered neural networks.
method Generalized unconstrained features model for deep networks.
result Deep unconstrained features model exhibits deep neural collapse.
New algorithm trains deep neural networks with adaptive learning rates.
problem Inconsistent gradient magnitudes across layers in SGD.
method Back-matching propagation with approximations for layer-wise adaptive learning rates.
result Achieves favorable results over standard SGD in training deep neural networks.
Proposes a balanced multi-component and multi-layer neural network for efficient function approximation.
problem Accurately and efficiently approximating complex functions with high degrees of freedom and computational cost.
method Inspired by a multi-component approach, MMNN combines single-layer networks with a multi-layer decomposition strategy.
result Significant reduction in training parameters, more efficient training process, and improved accuracy compared to FCNNs or MLPs.
We analyze deep neural networks using convex duality to reveal hidden layer structures.
problem Understanding the structure of deep neural networks.
method Introducing a convex analytic framework to characterize hidden layer weights.
result Optimal hidden layer weights align with previous layers via duality.
Layer fusion reduces deep neural network layers with minimal loss in accuracy.
problem Model compression to reduce neural network size and computation.
method Fusion of similar layers to reduce model size with minimal performance loss.
result Deep networks can be compressed up to 3.33x with minimal accuracy loss.
This paper presents a phase diagram for two-layer neural networks under different initialization scales.
problem Understanding the behavior of neural networks under varying scales of initialization.
method Analysis of a phase diagram for two-layer neural networks.
result Condensation of weight vectors on isolated orientations during training.
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.
Wavelets help compress neural networks efficiently.
problem Efficiently compressing linear layers in neural networks.
method Learnable wavelet transforms to compress RNNs.
result Wavelet compressed RNNs have fewer parameters and perform competitively.
Tensor regression networks improve neural network compression and regularization.
problem Improving neural network compression and regularization with low-rank tensor approximations.
method Investigating various low-rank tensor approximations in tensor regression networks.
result Tensor regression networks with Global Average Pooling layer outperformed in deep CNNs, while shallow CNNs with tensor regression and dropout achieved lower test error.
Global convergence proved for three-layer neural networks in mean field regime.
problem Optimization efficiency of multilayer neural networks in the mean field regime.
method Developed a rigorous framework for mean field limit of three-layer networks using stochastic gradient descent and neuronal embedding.
result Global convergence guarantee for unregularized feedforward three-layer networks in the mean field regime.