Neural networks can separate non-separable data using feature maps.
problem Non-separable data in neural networks.
method Characterization of feedforward neural networks and use of feature maps.
result ReLU neural networks can separate concentric data.
A new Gaussian process framework uses neural feature maps for scalable, accurate inference.
problem Efficient and accurate Gaussian process inference for diverse data types.
method Neural feature maps to construct expressive kernels, with theoretical guarantees and practical scalability.
result The approach outperforms existing methods in accuracy and efficiency across various data modalities.
Proposes a new method to prevent overfitting in deep neural networks.
problem Overfitting in deep neural networks with many trainable parameters.
method Randomly replaces elements in feature maps with specific values during training.
result Improves the testing performance of deep neural networks on benchmark datasets.
Characterizes test error in learning with deep, structured feature maps.
problem Characterizing test error in learning with deep, structured feature maps.
method Asymptotic analysis of feature covariance and population covariance.
result Closed-form formula for feature covariance in Gaussian rainbow neural networks.
The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite the rapid development in its application, deep neural networks remain analytically unexplained, because the feature maps are nested and param…
Training shapes the geometry of neural network feature maps, revealing local area magnification.
problem Understanding how training affects the geometric structure of neural network feature maps.
method Analyzing the Riemannian geometry induced by neural network feature maps at infinite width and after training.
result Training breaks the symmetry of the geometry induced by random neural network feature maps, magnifying local areas along decision boundaries.
Deep neural features identify unique vehicles from dash-cam feeds.
problem Identifying unique vehicles in dash-cam feeds for self-driving cars.
method Used pretrained YOLO network feature maps to create deep integrated feature signatures (DIFS) for 700 images of 35 vehicles and 340 images of 17 vehicles.
result Correctly identified unique vehicles at 96.7% for high resolution data and 86.8% for lower resolution data.
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explaine…
The paper studies Lipschitz bounds for integral kernels under differentiability assumptions.
problem Understanding the Lipschitz continuity of feature maps associated with integral kernels.
method Analyzes differentiability assumptions to derive explicit formulas for Lipschitz constants and conditions for non-Lipschitz continuity.
result Explicit formulas and conditions for Lipschitz continuity of feature maps associated with various kernels.
A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.
problem Efficiently pruning deep neural networks to reduce computation while maintaining accuracy.
method Presented a novel mathematical formulation (Discriminant Information, DI) to quantify feature-map discriminativeness, enabling efficient pruning and intra-layer mixed precision quantization.
result Our pruned ResNet50 achieves 44% FLOPs reduction without any Top-1 accuracy loss.
Efficiently applies NTK to large-scale datasets using random features.
problem Computational limitations of kernel methods for large-scale datasets.
method Proposes a sketching-based algorithm combining random features of arc-cosine kernels to construct an efficient feature map of the NTK.
result Achieves comparable error bounds to exact kernel methods but with significantly reduced feature dimensionality.
Deep neural-kernel models combine neural networks and kernel machines for scalable large datasets.
problem Combining neural networks and kernel machines for efficient large-scale learning.
method Hybrid neural-kernel architecture using explicit feature mapping and pooling layers.
result The deep neural-kernel models are effective and scalable on benchmark datasets.
This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible learning for generating and learning latent features using the network itself. By generating latent features corresponding to hard samples an…
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs). The networks perform feature mapping between the spectral features of reverberant and clean speech. Long short term memory recurrent neural networks (LSTMs) are trained to map corrupted…
Random feature maps improve forecasting with cheaper computation.
problem Improving forecasting accuracy with random feature maps.
method Developed a hit-and-run algorithm to select optimal internal weights.
result Optimal internal weights lead to superior forecasting skill.
Each year, around 6 million car accidents occur in the U.S. on average. Road safety features (e.g., concrete barriers, metal crash barriers, rumble strips) play an important role in preventing or mitigating vehicle crashes. Accurate maps of road safety features is an important component of safety management systems for…
Many practical machine learning tasks employ very deep convolutional neural networks. Such large depths pose formidable computational challenges in training and operating the network. It is therefore important to understand how fast the energy contained in the propagated signals (a.k.a. feature maps) decays across laye…
Graph matching with feature vectors is solved using a two-layer graph neural network.
problem Graph matching in the presence of sparse binary features.
method Two-layer graph neural network with graph structure.
result Graph neural network can recover correct mapping with high probability under certain conditions.
Study identifies and estimates causal LSNM models, proving feature maps are consistent.
problem Identifying causal direction in LSNM models.
method Proposed two estimators: feature maps and neural networks.
result Feature maps estimator is consistent and concave.
AGOP mechanism explains deep neural collapse in neural networks.
problem Explaining the rigid structure of data representations in deep neural networks.
method Introducing AGOP and Deep RFM to demonstrate DNC.
result AGOP mechanism causes deep neural collapse in neural networks.
Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irrelevant variables often leads to overfitting. In an attempt to circumvent this issue, a prior knowledge pertaining to what features are relev…
Agent learns to navigate uncertain 3D maps using a hybrid planner.
problem Planning in 3D environments with uncertain topological maps.
method Hierarchical strategy combining graph planner and local policy, data-driven learning with neural network.
result Machine learning can overcome missing information in probabilistic topological maps.
Derives a biologically plausible neural network for Slow Feature Analysis.
problem Learning latent features from time series data.
method Starting from an SFA objective, derives Bio-SFA with a biologically plausible neural network implementation.
result Validates Bio-SFA on naturalistic stimuli, reproducing interesting properties of brain cells.
Lower bound proves ridgeless regression performs poorly near interpolation threshold.
problem Proving performance of ridgeless regression near interpolation threshold.
method Distribution-independent lower bound for mean squared error in noisy ridgeless linear regression.
result Lower bound implies ridgeless regression performs poorly near interpolation threshold.
Markov blanket feature selection, while theoretically optimal, is generally challenging to implement. This is due to the shortcomings of existing approaches to conditional independence (CI) testing, which tend to struggle either with the curse of dimensionality or computational complexity. We propose a novel two-step a…
Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architect…
This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects. First, ACNet employs a flexible way to switch global and local inference in processing the internal feature representations by adaptively determining the connection s…
Large models follow power laws in performance with dataset size or parameters.
problem Understanding neural scaling laws in large language models.
method Joint generative data model and random feature model.
result Modeling and solving the dual limit reveals insights into scaling laws.
Poor approximators found in neural networks and random feature models.
problem Understanding why certain neural networks and models perform poorly in approximating functions.
method Established a scale separation of Kolmogorov width type and applied it to neural networks and random feature models.
result Reproducing kernel Hilbert spaces and two-layer neural networks are poor L2-approximators for certain functions. Even though Deep Neural Networks (DNNs) are widely celebrated for their practical performance, they possess many intriguing properties related to depth that are difficult to explain both theoretically and intuitively. Understanding how weights in deep networks coordinate together across layers to form useful learners h…
Bayesian deep learning improves geostatistical mapping with auxiliary data.
problem Traditional geostatistical methods are limited in feature learning and uncertainty estimation.
method Deep neural networks learn complex relationships from auxiliary data for probabilistic mapping.
result Deep learning produces detailed, probabilistic maps with uncertainty estimates.
Novel method combines neural network features with survival models for ICU infections.
problem Improving predictive models of ICU infections while maintaining interpretability.
method Semi-parametric approach combining low-resolution and high-resolution data.
result Improved predictive power with interpretability maintained.
Paper generalizes teacher-student model for realistic data.
problem Capturing learning curves for realistic datasets.
method Introduces a Gaussian covariate generalization of the teacher-student model.
result Generalized model captures learning curves for various realistic data sets.
A new method integrates Fourier basis expansion and mapping for improved time series forecasting.
problem Inconsistent starting cycles and series length issues in Fourier-based methods.
method Fourier Basis Mapping (FBM) method that integrates time-frequency features through Fourier basis expansion and mapping.
result FBM addresses inconsistencies and preserves temporal characteristics, achieving SOTA performance.
New random feature maps for Laplacian and related kernels.
problem Challenges in approximating the Laplacian kernel and its generalizations.
method Developed random feature maps for Laplacian and related kernels, providing efficient sampling schemes.
result Demonstrated the efficacy of these random feature maps on real datasets.
A new hybrid framework reduces quantum runtime and noise effects.
problem Challenges in deploying deep QFMs on real quantum hardware.
method Iterative Quantum Feature Maps (IQFMs) combining shallow QFMs and classical augmentation weights.
result Numerical experiments show IQFMs outperforming quantum convolutional neural networks.
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous ana…
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks represent fields on a homogeneous base space, and layers are equivariant maps between spaces of fields. The theory enables a systematic cla…
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning. While saliency maps may help identify relevant features (e.g., p…
Designs a neural network to reduce training cost by mapping to higher dimensions.
problem High training cost in neural networks.
method Maps feature vectors to higher dimensional space, designs weight matrices to reduce cost, uses convex constraints.
result Reduces training cost as the number of layers increases, without cross-validation.
Gradient descent aligns neural feature matrices with pre-activation tangent features.
problem Understanding neural feature learning mechanisms.
method Analytical proof of alignment between weight matrices and pre-activation tangent features.
result Derivative alignment occurs almost surely in high-dimensional settings.
Proposes HBGNN for better recommendation systems using graph neural networks.
problem Sparse structured data in recommendation systems lacking feature richness.
method Hierarchical BiGraph Neural Network (HBGNN) using bigraph framework.
result Competitive performance compared to current methods.
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
problem CNNs lack accurate data representation in their built-in prototypes.
method Introduces k-means-based post-hoc explanations for CNNs, leveraging spatial consistency of convolutional receptive fields.
result Using shallower, less compressed feature activations improves semantic fidelity at the cost of slight predictive performance.
Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity …
KPCA improves OoD detection by separating InD and OoD data.
problem Insufficiency of PCA in detecting OoD data from InD data.
method Kernel PCA (KPCA) with task-specific kernels.
result KPCA achieves superior OoD detection performance.
Effective feature representation is key to the predictive performance of any algorithm. This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the universal approximation property (UAP) into most model classes while only outputting fea…
Graph neural network predicts optimal coarse-grained mapping operators.
problem Optimal coarse-grained mapping operators selection for molecular dynamics simulations.
method Graph Neural Network (DSGPM) trained on expert-annotated data.
result DSGPM outperforms state-of-the-art methods in graph segmentation.