New neural networks for non-commutative data.
problem No existing neural networks suitable for non-commutative data.
method Developed compact matrix quantum group equivariant neural networks.
result Characterized weight matrices for easy compact matrix quantum groups.
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the input image that causes the network to misclassify the sample. In this paper, w…
We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency. In the proposed method, we introduce a sparsity-inducing prior on the per u…
Compact DNNs increase memory footprint and reduce energy efficiency.
problem Designing compact deep neural networks (DNNs) for improved energy efficiency.
method Evaluation of recently proposed compact DNNs on a Tesla P100 GPU.
result Higher number of activations and memory footprint lead to reduced energy efficiency.
Study shows limits on deep and shallow neural networks for approximating compact sets.
problem Understanding the limitations of deep and shallow neural networks in approximating compact sets.
method Proved Carl's type inequalities for approximation error, using Lipschitz widths.
result Lower bounds on approximation error for neural network outputs.
The paper shows neural networks can approximate functions over non-compact domains with non-polynomial activation.
problem Approximating functions over non-compact domains using neural networks.
method Using single-hidden-layer feedforward neural networks with non-polynomial activation functions over non-compact subsets of Euclidean spaces.
result Neural networks can approximate functions in weighted Ck-spaces and weighted Sobolev spaces over unbounded domains. 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 …
This paper reviews methods to create compact neural networks for IoT applications.
problem Complex deep neural networks are costly and slow, hindering real-world deployment.
method Automatic synthesis of compact, accurate DNN/LSTM models.
result Compact neural networks reduce energy consumption, memory, and inference time.
Compact models for NOX formation during methane combustion are created using a new algorithm.
problem Creating accurate models for NOX formation during complex combustion processes.
method Adapted Machine Learning Optimization of Chemical Kinetics (MLOCK) algorithm with Latin Square method for virtual reaction network generation.
result Compact models with high fidelity (>75%) in reproducing industry-defined performance targets are generated.
Automates graph convolutional network design for semi-supervised node classification.
problem Designing optimal graph convolutional network architectures for semi-supervised node classification.
method An automatic process to define a problem-specific architecture based on graph structure.
result The proposed method outperforms existing methods in classification performance and network compactness.
In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon Channel-wise recurrent convolutional (CRC) layers, a novel type of convolutional …
Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several recent works attempt to mitigate these overheads by designing compact networks using pruning of connections. However, we observe that most …
Compact parameterization improves Bayesian neural network performance.
problem Improving performance of Bayesian neural networks using variational methods.
method Restricting variational distribution to a k-tied Normal distribution with low-rank factorization.
result Compact parameterization improves signal-to-noise ratio and convergence speed.
Improves deep learning robustness by enforcing local and global compactness.
problem Deep neural networks' vulnerability to adversarial attacks.
method Proposes Adversary Divergence Reduction Network (ADRN) that enforces local/global compactness and clustering assumption.
result Augmenting adversarial training with ADRN components improves robustness.
New bound on neural nets complexity for approximating functions.
problem Approximating continuous functions with shallow neural networks.
method Inspired by Stone-Weierstrass theorem, constructive proof.
result General upper bound on neuron count for accuracy.
Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to expensive computational cost and low learning efficiency. The problem can be alleviated …
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation functio…
Estimates neural network error approximating compact sets.
problem Approximating compact subsets from Banach spaces with neural networks.
method Estimates error rates for neural networks of varying width and depth.
result Depth is crucial for better approximation rates, width alone does not improve.
Paper develops data-driven compact models for diodes.
problem Manual and time-consuming compact model development.
method Machine Learning techniques for automation.
result Data-driven models accurately predict diode behavior.
NPAS trains neural networks with a fixed parameter budget, improving performance and compactness.
problem Training neural networks requires memory, and existing methods struggle with arbitrary parameter budgets.
method NPAS learns to share parameters automatically, covering low and high budgets.
result NPAS and SSNs improve network performance and compactness across various tasks.
Convolutional neural networks have been extremely successful in the image recognition domain because they ensure equivariance to translations. There have been many recent attempts to generalize this framework to other domains, including graphs and data lying on manifolds. In this paper we give a rigorous, theoretical t…
Paper presents a method to summarize HMC samples for neural networks, providing meaningful uncertainty estimates.
problem Lack of interpretable summary statistics for HMC samples in neural networks due to permutation symmetry.
method Introducing a transpositions metric to quantify permutations and using rebasin method to summarize HMC samples.
result Compact representation of HMC samples provides meaningful uncertainty estimates for each weight in a neural network.
Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow neural networks. Our framework is general and covers weight-sharing (convolutional ne…
Bayesian neural network predicts planetary instability.
problem Predicting planetary instability in compact systems.
method Novel Bayesian neural network trained on raw orbital elements.
result Model predicts planetary instability times with high accuracy and robust generalization.
Minimum width for ReLU networks on compact domain is exactly max{d_x, d_y, 2}
problem Characterizing the minimum width for ReLU networks to approximate functions on compact domains
method Analyzing the minimum width for Lp approximation of Lp functions from [0,1]d to Rdy using ReLU-like activation functions result The minimum width for Lp approximation on a compact domain is exactly max{d_x, d_y, 2} for ReLU-like activation functions Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
Improved sample efficiency with normalized RBF kernels in neural networks.
problem Learning more with less data in deep learning models.
method Two-phase method to train neural networks with normalized RBF kernels as output layer.
result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.
Dynamic Sparse Training finds efficient sparse networks from scratch.
problem Finding efficient sparse neural networks.
method Jointly optimizes network parameters and sparsity with trainable thresholds.
result Achieves state-of-the-art performance with minimal performance loss.
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled samples of a training batch to capture underlying structure in feature …
Deep neural network learns compact representations for driving tasks.
problem Improving autonomous driving through better neural network representations.
method Inspired by human brain's hierarchical structure and predictive nature, the paper proposes a deep learning framework that learns compact representations of driving concepts.
result The paper successfully learns compact representations using as few as 16 neural units for car and lane concepts.
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural n…
Compact neural network for ECG classification reduces resource needs.
problem Current reliance on deep learning for ECG analysis requires extensive resources and large datasets.
method Simple ANN architecture with advanced feature engineering.
result Achieved 97.36% accuracy in classifying 4 types of arrhythmias.
We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their unstructured or fully connected counterparts. As we show, even more compact topologi…
The paper develops mathematical models for neural networks using non-compact symmetric spaces.
problem Developing mathematical models for neural networks using non-compact symmetric spaces.
method Introducing layers modeled as non-compact symmetric spaces, each mapped onto the next by solvable group homomorphisms.
result Group theoretical construction of separators for all non-compact symmetric spaces and uniformization of specific surfaces.
Deep neural nets approximate random dynamical system trajectories uniformly in time.
problem Approximating trajectories of random dynamical systems over infinite time horizons.
method Recurrent neural networks with simple feedback structures.
result Certain random trajectories can be approximated uniformly in time to any desired accuracy.
This study uses neural networks to approximate Bayesian filtering problems.
problem Estimating latent time-series signal statistics from observation sequences.
method Formulated a generic recurrent neural network framework to learn recursive mappings directly.
result Approximation error bounds for filtering in non-compact domains and strong time-uniform bounds.
Machine learning finds a compact fixed point action for SU(3) gauge theory.
problem Finding accurate and compact parametrizations of fixed point actions for SU(3) gauge theory.
method Used machine learning, specifically a gauge equivariant convolutional neural network.
result Obtained a superior parametrization of a fixed point action for SU(3) gauge theory.
The paper clarifies thermodynamics on non-compact symmetric spaces using Kähler geometry.
problem Formulating thermodynamics on non-compact symmetric spaces U/H. method Introducing a distinction between thermodynamics of dynamical systems and Gibbs distributions, proving only Kähler spaces support Gibbs distributions, solving the temperature space problem.
result Only Kähler spaces support Gibbs distributions on non-compact symmetric spaces U/H. Tensor neural network improves human pose classification from 3D skeleton data.
problem Efficiently processing spatiotemporal data for human pose classification.
method Proposes a tensor-based neural network with three components: spatiotemporal feature construction, tensor fusion, and tensor-based neural network processing.
result Achieves state-of-the-art performance in human pose classification.
T-Basis represents neural network tensors with fewer parameters.
problem Efficiently representing neural network tensors with fewer parameters.
method T-Basis uses Tensor Rings to represent tensors in a neural network, parameterizing them with a small number of coefficients.
result T-Basis achieves high compression rates with minimal performance loss.
Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact can each layer be compressed, without losing performance? Most of the existing DN…
We show that compact fully connected (FC) deep learning networks trained to classify wireless protocols using a hierarchy of multiple denoising autoencoders (AEs) outperform reference FC networks trained in a typical way, i.e., with a stochastic gradient based optimization of a given FC architecture. Not only is the co…
Neural networks can approximate functions uniformly across various measures.
problem Universal approximation of functions across different probability measures.
method Proving neural networks are dense in Orlicz spaces, extending classical theorems.
result Neural networks uniformly approximate functions for weakly compact families of measures.
In this paper, a geometric framework for neural networks is proposed. This framework uses the inner product space structure underlying the parameter set to perform gradient descent not in a component-based form, but in a coordinate-free manner. Convolutional neural networks are described in this framework in a compact …
Study shows consistency of shallow GCNNs on sampled point clouds under manifold assumption.
problem Consistency of shallow GCNNs on sampled point clouds under manifold assumption.
method Functional analysis perspective, weakly compact product of unit balls, Sobolev regularity, frequency cutoff.
result Proves Γ-convergence of regularized empirical risk minimization functionals and convergence of their global minimizers. Residual networks with block width max(d_x, d_y) approximate all functions.
problem Achieving universal approximation with residual networks.
method Established bounds on block width for different activation functions.
result Minimum block width for universal approximation is max(d_x, d_y) with inner width 1.
New RBF networks can approximate any continuous function.
problem Approximating any continuous function on a compact subset.
method Replacing smoothing factors with shifts in RBF networks and proving approximation under certain conditions.
result RBF networks can approximate any continuous function on any compact subset.
In this paper, we propose to employ a bank of modality-dedicated Convolutional Neural Networks (CNNs), fuse, train, and optimize them together for person classification tasks. A modality-dedicated CNN is used for each modality to extract modality-specific features. We demonstrate that, rather than spatial fusion at the…