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.
Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of …
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
Single ReLU neuron's gradient dynamics reveal support vectors as key to generalization.
problem Understanding the generalization capability of ReLU networks.
method Examined gradient flow dynamics and support vectors in single ReLU neuron training.
result Support vectors play a crucial role in the generalization of ReLU networks.
DNPUs improve neural network performance with high-capacity nanoelectronic nodes.
problem Limited performance of single DNPUs in solving complex classification problems.
method Developed DNPUs as high-capacity neurons and implemented multi-DNPU networks.
result Feed-forward DNPU networks improve single DNPU performance from 77% to 94% test accuracy.
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of networks which generalize and those which do not remain unclear. Additionally, the tuning properties of single directions (defined as the activa…
New neural networks learn single-index models efficiently.
problem Learning low-dimensional structure in high-dimensional data.
method Shallow neural networks with frozen biases, studied via gradient flow.
result Generalization guarantees match near-optimal sample complexity.
New method learns cell trajectories and network interactions from single-cell data.
problem Network inference in systems biology from steady-state data.
method Min-entropy estimation for stochastic dynamics, leveraging both temporal and perturbational data.
result Jointly learns cellular trajectories and network interactions.
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 …
Tutorial on using neural networks for single cell data analysis.
problem Handling large sequencing datasets efficiently.
method Single cell variational inference using variational auto-encoder.
result Model learns data distribution for insights.
Single gradient step finds adversarial examples in random neural networks.
problem Finding adversarial examples in neural networks with random architectures.
method Gradient descent approach applied to random undercomplete and overcomplete two-layers neural networks.
result A single gradient step is sufficient to find adversarial examples in random neural networks.
Single-pass method estimates neural network uncertainty.
problem Uncertainty estimation in deep learning requires multiple passes.
method Probabilistic reasoning over neural network depths.
result Single forward pass for uncertainty estimation.
AugurOne trains single image generators without GANs using image warps.
problem Training end-to-end single image generators without GANs.
method Non-affine augmentations of single input images for training an upscaling neural network.
result End-to-end training yields state-of-the-art performance on conditional generation tasks.
The state of the art lung nodule detection studies rely on computationally expensive multi-stage frameworks to detect nodules from CT scans. To address this computational challenge and provide better performance, in this paper we propose S4ND, a new deep learning based method for lung nodule detection. Our approach use…
Graph Attention Networks predict disease state from single-cell data.
problem Predicting disease state from single-cell data.
method Graph Attention Networks (GAT) for learning from both features and graph structures.
result Achieved 92% accuracy in predicting MS from single-cell data.
Deep single-index Fréchet regression for metric space-valued outputs
problem Predicting outputs in non-Euclidean spaces
method DeSI (Deep Single-Index Fréchet Regression)
result Interpretable index direction for inputs
Single neural networks can match deep ensembles' benefits without the complexity.
problem The effectiveness and necessity of deep ensembles in neural network models.
method Demonstrated limitations of ensemble diversity and OOD performance in deep ensembles compared to a single larger model.
result A single neural network can replicate deep ensembles' benefits in uncertainty quantification and robustness.
A new network controls task execution in a single vision system.
problem Executing multiple tasks accurately and efficiently in a single network.
method A top-down control network modifies main recognition network activations based on selected task, image content, and spatial location.
result Significantly better results on four datasets compared to state-of-the-art approaches.
Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usu…
Single deep model detects out-of-distribution data with single forward pass.
problem Detecting out-of-distribution data points in neural networks.
method Deterministic uncertainty quantification (DUQ) using gradient penalty for reliable detection.
result Single model outperforms or matches ensemble methods in out-of-distribution detection.
Single wide layer followed by a pyramidal structure ensures global convergence in deep networks.
problem Ensuring global convergence in deep neural networks with limited width constraints.
method Proves that a single wide layer followed by a pyramidal structure guarantees global convergence for over-parameterized networks.
result Single wide layer of width N suffices for global convergence in deep networks with constant-width remaining layers. 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.
Study SGD dynamics in sequence models, revealing training phases and influence of sequence length.
problem Understanding SGD in sequence models like attention networks.
method Derived closed-form population loss and analyzed SGD dynamics for SSI models.
result Two distinct training phases: escape from uninformative initialization and alignment with target subspace.
Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an …
A fast single-shot MC dropout method for neural networks.
problem Inability of DNNs to provide uncertainty measures for new situations.
method Analytically approximates MC dropout for fully connected networks.
result Approach preserves BDNN advantages while being faster.
Overparameterized ensembles don't offer generalization benefits over single large models.
problem Theoretical limitations of ensembles in overparameterized settings.
method Using ensembles of random feature (RF) regressors, the paper clarifies how modern ensembles differ from underparameterized counterparts.
result Infinite ensembles of overparameterized RF regressors become pointwise equivalent to single infinite-width RF regressors, and finite width ensembles converge to single models with the same parameter budget.
A neural network, IHT-Net, improves DOA estimation with sparse arrays.
problem Single-snapshot DOA estimation with sparse arrays in dynamic settings.
method IHT-inspired neural network with recurrent neural network and autoencoders.
result IHT-Net achieves faster convergence and higher accuracy in DOA estimation.
Adding linear layers to ReLU networks favors functions with low mixed variation.
problem Understanding function space bias in overparameterized neural networks.
method Examined a family of networks with varying depths and same capacity but different representation costs, focusing on the effect of adding linear layers to the input side.
result Adding linear layers to shallow ReLU networks results in a bias towards functions with low mixed variation, which can be well approximated by single- or multi-index models.
Generative networks trained with sketching reduce computational burden.
problem Computational expense of training generative networks on large datasets.
method Compressive learning using a single sketch vector to approximate Maximum Mean Discrepancy.
result Cost-efficient optimization of generative networks on large datasets.
Lazy neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness issues in lazy training models.
method Extending recent work on adversarial examples to lazy training models.
result Over-parametrized neural networks that generalize well remain vulnerable to single-step gradient ascent attacks.
AuxiLearn combines auxiliary tasks into a single loss function.
problem Improving neural network performance on a main task using auxiliary tasks.
method Implicit differentiation to learn a network that combines auxiliary tasks into a single coherent objective function.
result AuxiLearn consistently outperforms competing methods in various tasks and domains.
We propose two neural network based mixture models in this article. The proposed mixture models are explicit in nature. The explicit models have analytical forms with the advantages of computing likelihood and efficiency of generating samples. Computation of likelihood is an important aspect of our models. Expectation-…
TNDE quantifies dynamic gene drivers from single-cell snapshots.
problem Reconstructing time-resolved regulatory effects in biological processes.
method Time-varying Network Driver Estimation (TNDE) using shared graph attention encoder and partial optimal transport.
result TNDE identifies stage-specific driver genes in mouse erythropoiesis.
Ensemble of GANs improves performance on disconnected data.
problem Disconnected datasets in computer vision cannot be represented by continuous GANs.
method Construct an optimization problem to relate single GAN, ensemble of GANs, conditional GANs, and Gaussian Mixture GANs.
result Ensemble of GANs outperforms single GANs with fewer parameters.
The instance segmentation problem intends to precisely detect and delineate objects in images. Most of the current solutions rely on deep convolutional neural networks but despite this fact proposed solutions are very diverse. Some solutions approach the problem as a network problem, where they use several networks or …
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
SNGP improves single-model deep uncertainty by enhancing distance-awareness.
problem Improving uncertainty estimation in deep learning models, especially for real-time applications.
method SNGP improves distance-awareness of DNNs through spectral normalization and Gaussian process layers.
result SNGP outperforms other single-model approaches in prediction, calibration, and out-of-domain detection.
Lookahead pruning extends single-layer optimization to multi-layer, outperforming magnitude-based pruning.
problem Pruning neural networks to reduce computational cost and memory usage.
method Developed a multi-layer optimization approach extending the single-layer optimization of magnitude-based pruning.
result Consistently outperforms magnitude-based pruning on various networks, especially in high sparsity.
A new method infers graph structure and parameters using a single generative flow network.
problem Bayesian Network structure and parameter inference from data.
method Single GFlowNet with two-phase sampling: DAG generation followed by parameter assignment.
result Accurate approximation of joint posterior distribution over graph structure and parameters.
Neural networks can achieve optimal sample complexity for learning single-index models.
problem Achieving optimal computational-statistical tradeoff in learning Gaussian single-index models.
method Unified gradient-based algorithm for training a two-layer neural network, adaptable to various loss and activation functions.
result Sample complexity of ds⋆/2∨d matches the SQ lower bound up to a polylogarithmic factor. Study combines speaker verification and voice trigger detection in a single network.
problem Separate training for speaker verification and voice trigger detection.
method Multi-task learning with a single network trained on both tasks.
result Single network achieves comparable accuracy to independent models for each task.
Single neural network learns multiple tasks from combined data.
problem Can a single neural network learn multiple unrelated tasks?
method Investigates how task representations affect joint learning; uses various task encoding methods.
result Single neural network can learn multiple tasks from combined data, even when tasks are unrelated and different.
Paper proposes CNN-LSTM for WiFi indoor localization.
problem Classical WiFi localization methods using only spatial data.
method Combines CNN and LSTM for CSI feature extraction.
result Achieves 2.5~m average localization error with 80% under 4~m.
Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture and is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may con…
Neural networks have recently had a lot of success for many tasks. However, neural network architectures that perform well are still typically designed manually by experts in a cumbersome trial-and-error process. We propose a new method to automatically search for well-performing CNN architectures based on a simple hil…
Finding the best neural network architecture requires significant time, resources, and human expertise. These challenges are partially addressed by neural architecture search (NAS) which is able to find the best convolutional layer or cell that is then used as a building block for the network. However, once a good buil…
Single neural network predicts ImageNet model parameters for faster training.
problem Training diverse ImageNet models requires significant resources and time.
method Trained a neural network to predict ImageNet model parameters and used them for initialization.
result Models initialized with predicted parameters converge faster and achieve competitive performance.
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive uncertainty of networks and variance of the prediction scores obtained by …