ROCKET speeds up time series classification without sacrificing accuracy.
problem High computational complexity and intractability of existing time series classification methods.
method Simple linear classifiers using random convolutional kernels.
result Achieves state-of-the-art accuracy with significantly reduced computational expense.
Paper proposes a method to speed up DNNs by quantizing Winograd/Toom-Cook convolutions.
problem Speeding up convolution computations in DNNs with reduced time consumption and improved accuracy.
method Application of base change technique for quantized Winograd-aware training model.
result 8-bit quantized network achieves nearly the same accuracy as direct quantized convolution with minimal additional operations.
UGConvs improve CNN accuracy with unitary transforms.
problem Improving CNN accuracy with richer representations.
method UGConvs combine group convolutions with unitary transforms.
result HadaNets achieve similar accuracy to circulant networks with lower complexity.
CNNs adapted for graphs match image CNNs without prior knowledge.
problem Matching CNN performance on graph-structured data without prior knowledge.
method Strided convolutions and data augmentation on graphs.
result Significant accuracy improvement on fMRI data.
Winograd convolution improves DNN accuracy in fp16 and bf16 formats.
problem Improving DNN accuracy in floating point formats.
method Investigated a wider range of Winograd algorithms for DNNs.
result Significant improvement in FP accuracy in fp16 and bf16 formats.
Improved CNN with general image processing kernels reduces training time and achieves high accuracy.
problem Training time and accuracy of CNNs.
method Used 41 general-purpose kernels for the first layer of CNNs.
result GFNN reduces training time by 30% and achieves 99.56% accuracy.
Deep convolutional Gaussian processes boost image classification accuracy.
problem Image classification with hierarchical feature combinations.
method Deep Gaussian process architecture with convolutional structure.
result Significantly improved image classification performance on MNIST and CIFAR-10 datasets.
Structured linear substitutions improve both efficiency and accuracy in neural networks.
problem Improving neural network efficiency and accuracy tradeoff.
method Replacing linear components in pointwise convolutions with structured linear decompositions.
result Structured layers provide Pareto-optimal benefits in efficiency/accuracy.
Channel pruning and weight binarization improve keyword spotting accuracy.
problem Improving accuracy of keyword spotting in neural networks.
method Group-wise splitting method using group Lasso penalty for channel sparsity, combined with 1-bit weight precision.
result Achieved over 50% channel sparsity with minimal accuracy loss.
Winograd convolutions are used to improve quantized neural networks.
problem Improving quantized neural networks using Winograd convolutions.
method Proposed a Winograd-aware formulation of convolution layers to expose numerical inaccuracies to learning.
result Up to 10% higher classification accuracy on CIFAR-10 with Winograd-aware layers.
Efficiently implements large-scale CNNs using memristors.
problem Implementing high-dimensional convolution in deep neural networks efficiently.
method Developed a method to convert CNN kernels to memristor-based circuits, optimized for accuracy and minimized error.
result 8-bit ADC/DAC is necessary to preserve software level classification accuracy in memristor-based CNNs.
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…
LeanConvNets reduces CNN costs without sacrificing accuracy.
problem High computational cost in fully-coupled CNNs.
method Sparsifying fully-coupled operators in CNNs.
result LeanConvNets achieve similar accuracy to state-of-the-art networks but with lower computational cost.
A hybrid model reduces graph complexity for improved classification accuracy.
problem High computational complexity and large number of parameters in higher-order graph convolutional networks.
method Weight sharing mechanism and novel fusion pooling layer to reduce parameters and complexity.
result The proposed model achieves highest classification accuracy with fewer trainable parameters.
Band-limited training reduces resource usage without sacrificing accuracy.
problem Resource constraints in training Convolutional Neural Networks (CNNs).
method Artificially constraining the frequency spectra of convolutional filters during training.
result CNNs can leverage lower-frequency components effectively, reducing resource usage.
Graph Convolutional Networks improved with topological features for better accuracy.
problem Improving Graph Convolutional Networks for node classification.
method Using topological features of nodes and adjacency matrices with distant nodes of similar topology.
result Adding topological features to GCN significantly improves accuracy over state-of-the-art methods.
Paper analyzes Winograd convolution errors and proposes methods to reduce them.
problem Reduction of floating point error in Winograd convolution for deep neural networks.
method Analysis of worst case FP error, estimation of norm and conditioning, proposed evaluation orderings, sampling points selection, mixed-precision convolution, pairwise summation.
result Proposed methods significantly reduce FP error for a given block size, allowing larger block sizes and reduced computation.
A modified VDCNN model reduces size and latency for mobile platforms.
problem Memory and processing constraints on mobile platforms.
method Temporal Depthwise Separable Convolutions and Global Average Pooling.
result The squeezed model (SVDCNN) is 10x-20x smaller with minimal accuracy loss.
Bayesian deep convolutional GPs improve image classification accuracy.
problem Inaccurate uncertainty estimates in traditional GPs for image classification.
method Translation-insensitive convolutional kernel, multi-output GPs, Bayesian approach.
result Improved performance in single-layer and deep models.
DeepPainter classifies painters using autoencoders without manual feature extraction.
problem Painter classification problem.
method Deep convolutional autoencoder neural networks trained on raw pixel data.
result Significant improvement in classification accuracy (63% reduction in error rate).
Deep neural networks improve modulation recognition accuracy.
problem Improving modulation recognition accuracy in wireless signals.
method Developed and tested deep neural network architectures, including CNN, ResNet, DenseNet, and CLDNN.
result Achieved high accuracy (up to 88.5%) in recognizing wireless signal modulations.
Reduces CNN parameters by 2x with minimal loss in accuracy.
problem Parameter efficiency in distributed machine learning and edge devices.
method Introduces a Convolutional Slice Generator (CSG) to reduce CNN parameters.
result Reduces CNN parameters by approximately 2x with minimal accuracy loss.
Improved singular value approximation for convolutional layers.
problem Improving accuracy of singular value approximation for linear convolutional layers.
method Developed a new spectral density matrix method for singular value approximation with improved accuracy and reduced computational complexity.
result Obtained moderate improvement in singular value distribution compared to circular approximation.
New method relaxes spatial invariance in locally connected layers, improving accuracy.
problem Improving classification accuracy with locally connected layers.
method Designing a low-rank locally connected layer with varying spatially varying combining weights.
result Relaxing spatial invariance improves classification accuracy over convolution and locally connected layers.
Self distillation boosts CNN accuracy without increasing model size.
problem Improving CNN accuracy in resource-limited domains.
method Divide and compress knowledge within the network structure.
result Average accuracy improvement of 2.65% across various networks.
Automated tool reduces FPGA inference latency to 5 μs for deep neural networks.
problem Deploying ultra low-latency, low-power deep neural networks on FPGAs.
method Extending hls4ml library, using model compression techniques like pruning and quantization-aware training.
result Achieved inference latency of 5 μs with 97% resource reduction.
IEA improves CNN models by averaging multiple convolutional layers.
problem Improving CNN model accuracy through ensemble learning.
method Replacing single convolutional layers with Inner Average Ensembles (IEA) of multiple convolutional layers.
result CNN models using IEA outperform those with regular convolutional layers.
Low-bit training framework reduces energy consumption in CNNs.
problem Reducing energy consumption in convolutional neural networks.
method Low-bit training framework using MLS tensor format with dynamic quantization.
result Achieves superior trade-off between accuracy and bit-width.
SPP prunes CNN weights probabilistically for faster inference.
problem Efficiently accelerate Convolutional Neural Networks (CNNs) without significant accuracy loss.
method Structured Probabilistic Pruning (SPP) with adjustable pruning probabilities.
result 4x speedup with minimal accuracy loss (0.3% for AlexNet, 0.8% for VGG-16).
Improved VGG networks enhance image classification accuracy.
problem Enhancing image classification accuracy using modified VGG architectures.
method Two improved VGG architectures were created by freezing the first two blocks and applying different dilation rates in the last three blocks.
result Significant out-performance on image classification tasks on CIFAR-10 and CIFAR-100 datasets.
This paper proposes reusing CNN layers to speed up hyperparameters tuning.
problem Time-consuming hyperparameters tuning in CNNs.
method Reuse trained convolutional layers among different trainings.
result Reduces training time and increases accuracy of neural networks.
New graph CNN layers improve accuracy on graph datasets.
problem Graph data relations are better represented as graphs, not grids.
method Proposed new graph CNN layers for vertex and edge features.
result Improved classification accuracy on graph datasets.
Proposes a new method to improve CNNs' shift invariance and accuracy.
problem Improving CNNs' shift invariance and prediction accuracy.
method Replaces RMax with CMod, a Gabor-like structure, to increase shift invariance and accuracy.
result Achieves superior accuracy on ImageNet and CIFAR-10 classification tasks.
The paper improves DFA for CNN and RNN training to match BP accuracy.
problem Low accuracy in CNN and RNN training using DFA.
method Divide network into modules, apply DFA within, use sparse backward weight, and incorporate dilated convolution and sparse matrix multiplication.
result Achieves BP-level accuracy in CNN and RNN training.
CNNs improve positioning accuracy in massive MIMO systems.
problem Improving positioning accuracy in massive MIMO systems.
method Applying CNNs to learn sparse massive MIMO channel fingerprints.
result Moderately deep CNNs achieve fractional-wavelength positioning accuracy.
CTM uses conjunctive clauses for image recognition, achieving high accuracy.
problem High computational complexity and lack of interpretability in CNNs.
method Introduces Convolutional Tsetlin Machine (CTM) using conjunctive clauses in propositional logic.
result CTM achieves competitive accuracy on various benchmarks, including MNIST and Fashion-MNIST.
Convolutional network predicts DNA chromatin structure from sequence images.
problem Predicting chromatin structure from DNA sequences.
method Developed a convolutional neural network using image-representation of DNA sequences.
result The method outperforms existing methods in prediction accuracy and training time.
Improved activation function NLReLU boosts neural network performance.
problem Performance issues with ReLU activation function.
method NLReLU uses parametric natural logarithmic transform to improve ReLU.
result NLReLU provides higher accuracy than ReLU in various neural networks.
Enhanced Graph Convolutional Network predicts diseases faster and more accurately.
problem Improving disease prediction accuracy using structural data from Electronic Health Records.
method Developed a Multi Layered-Parallel Graph Convolutional Network (ML-PGCN) with novel weighting layers.
result Significant improvement in accuracy and AUC compared to state-of-the-art methods.
Convolutional neural networks improve image classification accuracy.
problem Improving accuracy in image classification.
method Analyzing the convergence rate of misclassification risk for image classifiers.
result A rate of convergence independent of image dimension proves the effectiveness of CNNs.
Symmetry in neural networks reduces parameter count without sacrificing accuracy.
problem Improving parameter usage and efficiency in deep neural networks.
method Imposing symmetry constraints on neural network parameters, especially in convolutional and recurrent networks.
result Symmetry can have little or no negative effect on network accuracy, even in deep overparameterized networks.
Finet uses FBN for efficient, lightweight neural networks.
problem Building efficient neural networks with limited computational resources.
method Introduces Fine-grained Batch Normalization (FBN) and a novel light-weight network (Finet) that combines FBN with standard convolution.
result Finet achieves state-of-the-art performance on ImageNet classification with reduced computational complexity.
CNNs improve signal-background classification in particle physics experiments.
problem Improving accuracy in classifying signal from background in particle physics experiments.
method Extensive convolutional neural architecture search for 2D and 3D image data.
result Achieved high accuracy for signal/background discrimination with CNNs, less parameters than ResNet.
Model predicts odor pleasantness using CNN, outperforming manual methods.
problem Predicting odor pleasantness for industry applications.
method Used a convolutional neural network to replace manual feature extraction.
result Shows 90% correlation with human ratings and 99.9% accuracy in categorizing odors.
Convolutional neural network localizes OD and fovea in UWFoV-SLO images.
problem Localizing optic disc and fovea centers in ultra-widefield retinal images.
method Convolutional neural network trained on reflectance and autofluorescence images.
result 99.4% OD localisation accuracy and 99.1% fovea localisation accuracy.
Convolutional Gaussian Processes improve image classification accuracy.
problem Improving Gaussian Processes for high-dimensional inputs like images.
method Introducing convolutional structure into Gaussian processes with an inter-domain inducing point approximation.
result Convolutional Gaussian Processes achieve better generalization and faster inference on image datasets.
Enhanced GQ-CNN boosts robot grasp accuracy.
problem Improving grasp success rates for unknown objects.
method Proposed a new GQ-CNN architecture with practical improvements.
result Validation accuracy increased from 92.2% to 95.8% and from 85.9% to 88.0%.
Convolutional neural networks outperform other architectures in streaming time series classification.
problem Efficient deep learning models for real-time data streams.
method Asynchronous dual-pipeline deep learning framework for real-time predictions.
result Convolutional architectures achieve higher accuracy and efficiency in streaming time series classification.