In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients. In particular, we train and test both methods on early stage disease patients, to verify their performance in challenging conditions, mo…
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 “Shallow Architectures”
This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep…
Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noisecs.LG
Deep neural networks are over-parameterized, which implies that the number of parameters are much larger than the number of samples used to train the network. Even in such a regime deep architectures do not overfit. This phenomenon is an active area of research and many theories have been proposed trying to understand …
MAML adapts faster with deeper architectures, especially in shallow tasks.
problem Understanding and improving MAML's fast adaptation.
method Empirical and theoretical studies on MAML's properties and optimization.
result MAML adapts better with deep architectures even for shallow tasks.
This paper classifies -invariant shallow neural networks.
problem Designing optimal -invariant neural architectures for -invariant target functions.
method Proving theorems about the classification and morphisms of -invariant single-hidden-layer neural networks.
result Classification of -invariant shallow neural networks and characterization of morphisms.
NAS favors wide and shallow cell structures, leading to fast convergence but not necessarily better generalization.
problem Understanding and improving the architectures generated by NAS algorithms.
method Empirical and theoretical study of existing NAS algorithms (DARTS, ENAS) and their architectures.
result Existing NAS algorithms favor wide and shallow cell structures, leading to fast convergence but not necessarily better generalization.
Deep ReLU networks approximate as well as shallow ones in kernel regimes.
problem Understanding the limitations of kernel methods for deep ReLU networks.
method Characterizing eigenvalue decays of kernels derived from deep ReLU networks.
result Deep ReLU networks and shallow two-layer networks have equivalent approximation properties in kernel regimes.
Deep Learning the Ising Model Near Criticalitycond-mat.dis-nn
It is well established that neural networks with deep architectures perform better than shallow networks for many tasks in machine learning. In statistical physics, while there has been recent interest in representing physical data with generative modelling, the focus has been on shallow neural networks. A natural ques…
PathCapsNet improves CapsNet by reducing parameters and enhancing performance.
problem Limitations of CapsNet, including excessive parameters and shallow architecture.
method Introducing a deep parallel multi-path version of CapsNet, incorporating depth, max-pooling, regularization, and new routing techniques.
result Better or comparable results to CapsNet with significantly reduced parameter count.
New deep ESN architectures improve memory capacity and prediction accuracy.
problem Improving memory capacity and prediction accuracy of ESNs.
method Two new deep ESN architectures: parallel and series. Analysis of memory capacity and prediction accuracy.
result Parallel deep ESNs have equivalent memory capacity to shallow ESNs, while series deep ESNs have smaller memory capacity.
CHOOSE enhances shallow Transformers for wireless symbol detection.
problem Improving wireless symbol detection with shallow Transformers.
method Introducing autoregressive latent reasoning steps within hidden space.
result Lightweight Transformers achieve comparable performance to deep models.
We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding mod…
It has long been conjectured that hypotheses spaces suitable for data that is compositional in nature, such as text or images, may be more efficiently represented with deep hierarchical networks than with shallow ones. Despite the vast empirical evidence supporting this belief, theoretical justifications to date are li…
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
problem Adversarial robustness of gradient-trained shallow networks.
method Analysis of neuron alignment and polynomial ReLU activation.
result Gradient-trained shallow networks with polynomial ReLU activation are robust to small-radius adversarial attacks.
Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distributioncs.LG
Shallow neural nets classify objects perfectly if their distribution is linearly separable.
problem Designing efficient neural networks for classification.
method Constructed shallow sigmoid-type neural networks.
result Achieves 100% accuracy for datasets following a linear separability condition.
On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensionsmath.OC
Study shows overparameterization helps shallow neural networks recover signals in high dimensions.
problem Signal recovery in shallow neural networks with overparameterization.
method Gradient flow on population risk, Gaussian distribution assumption, high-dimensional limit analysis.
result Minimal overparameterization is sufficient for strong recovery of signals.
SCAN divides deep neural networks into shallow classifiers for efficient deployment.
problem Explosive growth in storage and computation limits deep neural networks on edge devices.
method SCAN divides networks into shallow classifiers, uses attention modules and knowledge distillation, and employs a threshold-controlled scalable inference mechanism.
result SCAN achieves significant performance gain on CIFAR100 and ImageNet without hyper-parameter adjustments.
By establishing a connection between bi-directional Helmholtz machines and information theory, we propose a generalized Helmholtz machine. Theoretical and experimental results show that given \textit{shallow} architectures, the generalized model outperforms the previous ones substantially.
Theory explains why DARTS favors deep architectures over shallow ones.
problem DARTS selects architectures with dominated skip connections, leading to performance degradation.
method Theoretical analysis of operations' effects on network optimization; introduces sparse binary gates and path-depth-wise regularization.
result Theoretical proof that architectures with more skip connections converge faster.
Paper proves bounds for shallow networks without dimensionality issues.
problem Avoiding curse of dimensionality and estimating approximation degree.
method Abstract theorem for -networks on compact metric measure spaces.
result Dimension independent bounds for approximation by shallow networks.
Deep nets improve function approximation and learning in high dimensions.
problem Designing neural networks for rotation-invariant function approximation.
method Developed deep neural networks with multiple hidden layers for radial function approximation.
result Deep nets achieve near-optimal function approximation and learning rates not possible by shallow nets.
Greedy approach constructs efficient neural networks with ReLU.
problem Constructing efficient neural networks with limited resources.
method Greedy algorithm with integral representation of the network using ridgelet transform.
result Proposed approach constructs efficient shallow neural networks.
Deep neural networks define suitable reproducing kernel Banach spaces.
problem Characterizing the function spaces of deep neural networks.
method Reproducing kernel Banach spaces and variational results.
result Deep neural networks define suitable reproducing kernel Banach spaces.
Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We present a supervised discriminative High-Order Parametric Embedding (HOPE) approach to data visualization and compression. Compared to deep emb…
Review of neural network expressivity and architectures.
problem Understanding neural network expressivity across different architectures.
method Comprehensive overview of approximation results for various neural network types.
result Deep neural networks offer advantages over shallow ones for specific function classes.
Gradient descent converges to global optima in shallow overparameterized networks.
problem Understanding the level of overparameterization required for gradient descent to converge to a global optimum in shallow neural networks.
method Stochastic gradient descent starting from random initialization, focusing on shallow neural nets and smooth activations.
result Gradient descent converges geometrically to a nearby global optima as soon as the square-root of the number of parameters exceeds the size of the training data.
HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Networkcs.LG
HighwayGraph models long-distance node relations in GNNs with improved performance.
problem Limited-layer information propagation in GNNs hinders long-distance node relation modeling.
method Proposes two solutions: implicit and explicit modeling of long-distance node relations using shallow GNN architectures and a self-training framework.
result HighwayGraph achieves consistent and significant improvements over four GNNs on three benchmark datasets.
Convolutional networks outperform shallow classifiers on certain tasks due to hierarchical structure.
problem Understanding why convolutional networks outperform shallow classifiers on specific tasks.
method Approximation theory, visual tasks with deterministic scrambling, and network performance evaluation.
result Hierarchical structure is crucial for convolutional networks' performance on certain tasks, but not all.
This work explains neural collapse in shallow neural networks and its impact on generalization.
problem Understanding neural collapse in shallow neural networks and its effect on generalization.
method Analysis of two and three-layer ReLU neural networks, focusing on data dimension, sample size, and signal-to-noise ratio.
result Neural collapse occurs in shallow ReLU networks under certain conditions related to data properties and network architecture.
A new method reduces computational cost for gene expression inference in large microarray data sets.
problem Efficiently predicting gene expression in large datasets with limited resources.
method Adaptive Lipschitz constant inspired learning rate, random sub-sampling, and A-ReLU activation function.
result Remarkable improvement in saving computational cost while maintaining prediction accuracy.
Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuit…
Shallow diffusion models learn hidden low-dimensional structures effectively.
problem Learning from high-dimensional signals like images and video.
method Analysis of shallow diffusion models over the Barron space of single layer neural networks.
result Shallow diffusion models can adapt to simple low-dimensional structures, overcoming the curse of dimensionality.
Expressive efficiency refers to the relation between two architectures A and B, whereby any function realized by B could be replicated by A, but there exists functions realized by A, which cannot be replicated by B unless its size grows significantly larger. For example, it is known that deep networks are exponentially…
Deep weight factorization improves neural network training through smooth optimization of sparse penalties.
problem Challenges in applying sparse regularization in neural networks due to non-differentiability of penalties.
method Introduces deep weight factorization, decomposing weights into multiple factors for smooth optimization of -penalized networks.
result Deep weight factorization outperforms shallow factorization and pruning methods consistently across various architectures and datasets.
We consider deep neural networks, in which the output of each node is a quadratic function of its inputs. Similar to other deep architectures, these networks can compactly represent any function on a finite training set. The main goal of this paper is the derivation of an efficient layer-by-layer algorithm for training…
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problems requiring reasoning across a higher number of fa…
Paper introduces a new anomaly detection framework combining density estimation and deep learning.
problem Detecting anomalies in data with varying dimensions.
method Two versions: shallow approach using adaptive Fourier features and density matrices; deep approach using autoencoder.
result Both methods achieve comparable or superior performance compared to state-of-the-art methods.
The emergence of a concept in shallow neural networkscond-mat.dis-nn
RBMs learn archetypes when trained on blurred copies of them, revealing a critical sample size.
problem Determining the critical sample size for RBMs to learn archetypes.
method Formal equivalence between RBMs and Hopfield networks, statistical-mechanics of disordered systems, Monte Carlo simulations.
result A phase diagram highlights regions where learning can be accomplished.
Develops vector-valued RKBS for neural networks and operators.
problem Understanding function spaces of -valued neural networks and neural operators.
method Defines and constructs vector-valued RKBS (vv-RKBS) without restrictive assumptions.
result Establishes Representer Theorem for neural architectures.
MemNet optimizes neural architectures for memory efficiency.
problem Memory constraints in mobile devices limit the use of large neural networks.
method Augment-trim learning with memory consumption ranking score.
result MemNet finds architectures with 24.17% less memory usage compared to state-of-the-art methods.
New DNN boosts image retrieval efficiency.
problem Efficient compression of visual descriptors for large-scale image retrieval.
method Unsupervised multi-codebook quantization in a DNN architecture.
result Significantly outperforms existing methods on visual descriptor datasets.
System suggests clinical concepts in real-time for faster note creation.
problem Efficiently creating structured clinical notes with minimal keystrokes.
method Contextual autocompletion using shallow neural networks.
result Reduces keystrokes by 67% in real hospital environments.
Shallow supervised 1-hidden layer neural networks have a number of favorable properties that make them easier to interpret, analyze, and optimize than their deep counterparts, but lack their representational power. Here we use 1-hidden layer learning problems to sequentially build deep networks layer by layer, which ca…
The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In the context of weakly-supervised CNN segmentation, we demonstrate a well-motivated…
Shallow neural networks can represent polynomials efficiently.
problem Representing polynomials using shallow neural networks.
method Using shallow neural networks of width to represent -variate polynomials of degree .
result Derives minimax optimal convergence rate for shallow networks to unknown univariate regression functions.
We consider the problem of training generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this paper, we view the problem of training GAN…
Wide and shallow networks approximate convex functions well.
problem Understanding why wide and shallow neural networks perform well.
method Analyzing the epigraph of the input-output map of shallow and wide neural networks.
result The epigraph of the input-output map approximates a convex function.
BNAS improves neural architecture search with a scalable, fast, and efficient approach.
problem Efficiently searching for optimal neural architectures with high performance and low training time.
method Designing a broad scalable architecture (BCNN) with reinforcement learning and parameter sharing, and developing two variants.
result Significantly reduces training time and achieves state-of-the-art performance on CIFAR-10 and ImageNet.