Tensor methods improve image classification performance.
problem Improving image classification accuracy using tensor-based machine learning.
method Two novel tensor-based approaches: MANDy kernel reformulation and alternating ridge regression in tensor-train format.
result Tensor-based methods are competitive with state-of-the-art neural networks.
MNIST-NET10 fusion improves MNIST classification to 0.1% error rate.
problem Improving MNIST classification accuracy.
method Complex heterogeneous fusion architecture using degree of certainty aggregation.
result MNIST-NET10 achieves 0.1% error rate with 10 misclassifications.
q-CNN learns data features through entangled states.
problem Classifying MNIST and Fashion MNIST datasets.
method Introduces q-CNN model, a tensor network description, and studies entanglement structure.
result q-CNN learns entanglement structure to perform classification tasks accurately.
A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data cover configuration space. Here we show that this coverage can be substantially increased u…
Quantum computing at room temperature achieves high accuracy in image classification.
problem Classifying images with single photons at room temperature.
method Optical transformation of quantum state to exploit interference and entanglement.
result Theoretical accuracy of 41.27% for MNIST and 36.14% for Fashion-MNIST.
Study finds resolution impacts human classification performance in MNIST data.
problem Understanding factors affecting human classification performance in machine learning.
method Empirical study of MNIST data at various resolutions.
result Derived a quantitative relationship between resolution and human classification performance.
Delta method vs Bootstrap for deep learning classification shows strong linear relationship and faster computation.
problem Validating the Delta method for deep learning classification.
method Comparison of Delta method and Bootstrap on LeNet-based neural networks using MNIST and CIFAR-10 datasets.
result The Delta method provides a five times faster computation with strong linear predictive uncertainty relationship.
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Defense against small image patches using occlusions.
problem Vulnerability of deep learning to small adversarial patches.
method Partially occlude image around each patch location.
result Certified security against patch attacks of a certain size.
Bidirectional VAE reduces parameters and improves image tasks.
problem Improving image reconstruction, classification, interpolation, and generation.
method Uses a single neural network for both encoding and decoding in both forward and backward directions.
result Bidirectional VAEs reduce parameters by almost 50% and slightly outperform unidirectional VAEs.
A new loss function α-loss bridges log-loss and 0-1 loss for binary classification.
problem Improving binary classification performance using a tunable loss function.
method Introducing α-loss, proving its margin-based form and classification-calibration, and providing an upper bound on empirical risk. result Empirical and expected risk difference upper bound for logistic regression-based classification.
New protocol benchmarks deep learning methods' data efficiency.
problem Measuring data efficiency of deep learning methods.
method Proposed experimental protocol to benchmark CNNs and HiGSFA.
result HiGSFA outperforms CNNs on smaller datasets.
New method certifies robustness to sparse adversarial attacks.
problem Ensuring robustness of classifiers to sparse adversarial attacks.
method Randomized ablation of input features to provide robustness guarantees.
result Certifies robustness to sparse adversarial attacks with up to 31 pixels of distortion.
DCTN uses tensor networks for image classification, achieving state-of-the-art results.
problem Improving image classification accuracy with deep neural networks.
method Developed a novel deep convolutional tensor network (DCTN) based on Entangled plaquette states (EPS).
result DCTN achieves state-of-the-art results on MNIST and FashionMNIST but overfits on CIFAR10.
Mobile agents classify images via reinforcement learning and consensus.
problem Image classification using multiple mobile agents.
method Proposed network architecture for local belief formation and feature extraction. Decentralized consensus protocol using reinforcement learning.
result Effectiveness of the proposed framework demonstrated on MNIST dataset.
AWDO trains neural networks for digit classification.
problem Training feedforward neural networks.
method Adaptive Wind Driven Optimization (AWDO).
result AWDO outperforms steepest descent method in digit classification.
New insights suggest larger early layers improve CNN performance.
problem Common assumption of monotonously increasing feature counts in CNNs is challenged.
method Used a skew normal distribution to investigate feature amounts in CNN layers.
result Architectures favoring larger early layers yield better accuracy.
TensorNetwork boosts image classification accuracy.
problem Improving image classification accuracy.
method Encoding images into matrix product states and using tensor network contraction.
result 98% and 88% accuracy on MNIST and Fashion-MNIST datasets respectively.
We proposed the expected energy-based restricted Boltzmann machine (EE-RBM) as a discriminative RBM method for classification. Two characteristics of the EE-RBM are that the output is unbounded and that the target value of correct classification is set to a value much greater than one. In this study, by adopting featur…
Faster Tsetlin Machines use clause indexing to speed inference and learning.
problem Overfitting and slow inference in Tsetlin Machines.
method Introduced a look-up table that indexes clauses based on feature falsification, enabling faster evaluation of clauses.
result Up to 15 times faster classification and three times faster learning on MNIST and Fashion-MNIST.
We provide an overview of several non-linear activation functions in a neural network architecture that have proven successful in many machine learning applications. We conduct an empirical analysis on the effectiveness of using these function on the MNIST classification task, with the aim of clarifying which functions…
Study on error probabilities of machine learning classification techniques using large deviations theory.
problem Performance analysis of machine learning binary classification techniques.
method Large deviations theory applied to Data-Driven Decision Function (D3F) for error probability analysis.
result Classification error probabilities vanish exponentially, with an asymptotic formula providing precise error rate estimates.
Study shows MSE with sigmoid can match SCE in classification tasks, especially with noisy data.
problem Inconsistent errors in neural network classification tasks.
method Introduced Output Reset algorithm to use MSE with sigmoid activation.
result MSE with sigmoid activation achieves comparable accuracy and convergence rates to Softmax Cross-Entropy, especially in noisy data scenarios.
New optimization algorithms for neural networks using operator splitting.
problem Training efficiency and convergence in neural networks.
method Sequential operator splitting technique applied to neural network training.
result Empirical rate of convergence towards local minimum of loss function validated.
A method for classifying points with minimal queries using Hermite polynomials.
problem Classifying points from an unknown probability measure with minimal label queries.
method Convex combination of conditional probabilities, Hermite polynomial kernel for hierarchical support estimation.
result The method achieves high F-score for classification in hyper-spectral images and MNIST. Study shows dataset properties impact adversarial machine learning robustness.
problem Vulnerability of DNNs to adversarial attacks.
method Examined five datasets, analyzed input size and contrast effects.
result Input size and contrast significantly influence adversarial success.
TDA classifies MNIST digits with reduced feature set.
problem Classifying MNIST digits using machine learning.
method Persistent homology for feature generation and classification.
result 5x reduction in feature set size with similar accuracy.
PixelHop uses SSL for image classification, outperforming CNN.
problem Image classification accuracy improvement.
method PixelHop combines SSL with supervised and unsupervised dimension reduction.
result PixelHop outperforms CNN on MNIST, Fashion MNIST, and CIFAR-10 datasets.
Invertible neural networks with masked convolutions improve classification and generative models.
problem Building robust invertible neural networks for better model interpretability and generative tasks.
method Combining masked convolutions and iterative inversion methods to create invertible architectures.
result Invertible neural networks achieve competitive performance in classification and generative tasks.
Proposes SGELU for neural networks to improve performance and convergence.
problem Improving neural network performance and convergence.
method Integrates Gaussian Error Linear Unit (GELU) with symmetrical characteristics to create SGELU.
result SGELU outperforms GELU and LiSHT in MNIST classification and auto-encoder tasks.
New algorithm defends against adversarial examples in image classification.
problem Defending against adversarial examples in image classification.
method Approximates Discrete Fourier transform of sparse signals corrupted by L0 noise. result Successfully defends against L0 adversaries in image classification. Adds a precortical module to CNNs for improved robustness to light variations.
problem Robustness of CNNs to global light intensity and contrast variations.
method Developed a mathematical model of the mammalian visual pathway, inspired by CNNs, and added a preliminary convolutional module.
result Significantly more robust CNNs achieved with added module on MNIST, FashionMNIST, and SVHN databases.
Spiking neural networks perform similarly to deep networks on occluded images.
problem Robust object recognition in partially occluded images.
method Developed a two-layer spiking neural network trained on natural scenes with a biologically plausible learning rule, compared to deep convolutional networks.
result Spiking neural networks achieve good accuracy and robustness on stepwise pixel erasement tasks.
A new method detects and corrects adversarial attacks on classifiers.
problem Detecting and correcting adversarial attacks on machine learning models.
method Unsupervised autoencoder trained with KL divergence loss to match predictions.
result Almost completely neutralizes powerful attacks on MNIST and Fashion-MNIST.
Deep neural networks reveal a low-dimensional manifold structure in data.
problem Understanding the structure of data for better model performance.
method Model-centric analysis of the data manifold using the local data matrix and Fisher information matrix.
result The dataset lies on a data leaf with a dimension bounded by the number of labels.
EXoN creates an explainable latent space for semi-supervised learning.
problem Creating an explainable latent space for semi-supervised learning.
method EXoN combines VAE with SCI (Soft-label Consistency Interpolation) to create an explainable latent space.
result EXoN reduces the cost of investigating representation patterns on the latent space.
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification. We demonstrate greatly improved image classification performance compared …
New model uses PEPS for image classification, outperforming tree-like networks.
problem Efficiently modeling and classifying 2D data like images.
method Feature map followed by PEPS contraction with trainable parameters.
result Significantly superior to tree-like networks on MNIST and Fashion-MNIST.
PixelHop++ improves image classification with a smaller model size.
problem Improving image classification models with smaller sizes.
method Decomposing input tensor, channel-wise Saab transform, successive subspace learning, feature ranking.
result PixelHop++ offers a flexible tradeoff between model size and performance.
Probabilistic decoupling separates labels from classes for improved classification.
problem Improving classification accuracy with noisy or partially labeled data.
method Probabilistic decoupling of labels from underlying classes.
result Method enhances performance on various classification tasks, including noisy and partially labeled data.
New artificial neuron doubles weight for improved deep learning accuracy.
problem Improving deep learning models' accuracy.
method Introducing a double-weight neuron, tested on MNIST and CIFAR-10 datasets.
result Significant improvement in classification accuracy for MNIST and CIFAR-10 datasets.
This work enhances deep neural networks with robust features to improve their robustness against adversarial attacks.
problem Vulnerability of deep neural networks to adversarial images.
method Augmenting classification pipelines with robust features like binarization and group extraction.
result Improved robustness and training speed on adversarial inputs, with significant improvements over state-of-the-art methods.
Bucketed PCA-NN outperforms DNNs by 96% on MNIST.
problem Benchmarking deep neural networks for supervised classification.
method Applies PCA to individual buckets constructed in two phases, retains neural network architecture, and uses neurons that mirror input signals.
result Bucketed PCA-NN achieves 96% accuracy on MNIST, similar to DNNs.
Hybrid model avoids forgetting across tasks and classes.
problem Challenges of continual learning in modern deep learning.
method Hybrid generative-discriminative approach using normalizing flows.
result Strong performance on various continual learning benchmarks.
We introduce a semiparametric approach to neighbor-based classification. We build off the recently proposed Boundary Trees algorithm by Mathy et al.(2015) which enables fast neighbor-based classification, regression and retrieval in large datasets. While boundary trees use an Euclidean measure of similarity, the Differ…
GANchors generates realistic image perturbations for better classifier explanations.
problem Improving the trustworthiness of image classification explanations.
method Using GANs to optimize a lower-dimensional latent space for realistic perturbation distributions.
result Generated images are more likely to be from the original training set, leading to more precise explanations.
Paper proposes BQNs for efficient Bayesian quantized neural networks.
problem Learning with well-calibrated uncertainty in neural networks.
method Bayesian quantized networks (BQNs) with efficient algorithms for learning and prediction without sampling.
result BQNs achieve lower predictive errors and better-calibrated uncertainties than E-QNN with less than 20% negative log-likelihood.
DVT transfers knowledge across domains using semi-supervised deep generative models.
problem Reduces labeling effort in domains with abundant labeled examples.
method Deep Variational Transfer (DVT) using a shared latent Gaussian mixture model.
result Achieves state-of-the-art classification performances across different datasets.