Fashion-MNIST
PulseAugur coverage of Fashion-MNIST — every cluster mentioning Fashion-MNIST across labs, papers, and developer communities, ranked by signal.
- instance of federated learning 90%
- used by The Street View House Numbers Dataset 70%
- instance of residual neural network 70%
- used by multilayer perceptron 70%
- used by federated learning 70%
- used by residual neural network 70%
- competes with AdamW 70%
- used by ResNet-18 70%
- instance of CIFAR-100 60%
- used by DagsHub 60%
- used by AdamW 50%
12 day(s) with sentiment data
-
New methods improve Forward-Forward algorithm's resilience to simulated sleep deprivation
Researchers have developed methods to mitigate the negative effects of simulated sleep deprivation on the Forward-Forward algorithm. By introducing alternative activations, optimizing loss functions, and adjusting thres…
-
New FLIWBO method enhances Bayesian optimization with adaptive input warping
Researchers have developed Finite-Library Input-Warped Bayesian Optimization (FLIWBO), a novel method designed to improve the efficiency of Gaussian-process Bayesian optimization (GP-BO) for black-box functions. Traditi…
-
Autoencoder parameters can represent data, study finds · 2 sources tracked
Researchers have proposed that the parameters of autoencoder models can serve as a dense vector representation of the data they are trained on. This hypothesis was tested through theoretical analysis and experiments, wh…
-
RecKAN introduces learnable recursive polynomial basis for enhanced neural networks
Researchers have introduced RecKAN, a novel approach to Kolmogorov-Arnold Networks (KANs) that enhances their ability to learn complex functions. Unlike previous KAN variants that use fixed bases for their learnable fun…
-
New optimizers enhance tree tensor networks for machine learning tasks
Researchers have developed new stochastic Riemannian optimizers for tree tensor networks (TTNs), a type of model originating from quantum physics that shows promise for machine learning applications. These optimizers ar…
-
New QCBO framework enables provable, scalable training for quantized neural networks
Researchers have developed a new framework for training quantized neural networks, addressing challenges posed by non-convex loss landscapes and discrete parameter spaces. Their approach utilizes an exact Quadratic Cons…
-
ES-HyperNEAT hyperparameter optimization using TPE shows promise
A new study explores optimizing hyperparameters for ES-HyperNEAT, a neuroevolutionary algorithm, using the Tree-structured Parzen Estimator (TPE) approach. The research investigated over 3 billion hyperparameter combina…
-
New method reconstructs fractal patterns from density maps
Researchers have developed a novel method for reconstructing Iterated Function Systems (IFS) from density maps, which are used to generate fractal patterns. This new approach, termed amortized set prediction, replaces t…
-
GradAttn enhances CNNs with attention-modulated gradient flow
Researchers have introduced GradAttn, a novel approach to enhance deep convolutional neural networks (CNNs) by replacing fixed residual connections with attention-controlled pathways. This method dynamically weights fea…
-
New method calibrates generative model training paths for improved performance
Researchers have introduced Difficulty-Calibrated Flow Matching, a novel approach to training generative models. This method dynamically adjusts the noise-to-data interpolation path based on the model's learning difficu…
-
Deep Artificial Immune Networks achieve replay-free visual memory
Researchers have developed a novel approach to unsupervised visual class-incremental learning using deep artificial immune networks (AINs). This method employs structured, gradient-free immune affinity, formalizing visu…
-
New framework Bridge Graphical Models improves generative AI design
Researchers have introduced Bridge Graphical Models (BGMs) as a new framework to analyze and improve continuous-time generative models. BGMs decouple design choices such as endpoint coupling, bridge law, and Markovian p…
-
New method adapts optimizer selection during deep learning training
Researchers have developed a new method called Repeated Optimizer Resampling (ROR) to improve the selection of optimizers for deep neural network training. Instead of choosing a single optimizer upfront, ROR allows the …
-
New study questions PGD's ability to measure AI model robustness
A new study published on arXiv investigates the effectiveness of Projected Gradient Descent (PGD) in evaluating adversarial robustness for convolutional neural networks. Researchers found that while PGD is commonly used…
-
Classical SU(2) models outperform quantum circuits on vision tasks
A new research paper compares classical SU(2) models with variational quantum circuits (VQCs) on various vision benchmarks. The study found that quaternion-valued neural networks, a type of classical SU(2) model, perfor…
-
Biologically-inspired D-SNN architecture enhances efficiency and transparency
Researchers have developed a Decomposable Spiking Neural Network (D-SNN) that mimics biological neural systems by isolating classification pathways into independent experts, thus avoiding global entanglement. This modul…
-
New federated learning strategies tackle data heterogeneity and security threats · 5 sources tracked
Researchers are developing new federated learning (FL) strategies to address challenges like data heterogeneity and security threats. FedImp and FedTVD aim to improve convergence speed and model accuracy by weighting cl…
-
Quaternion Networks Outperform Quantum Circuits on Vision Tasks
Researchers have compared the performance of quaternion-valued neural networks against shallow variational quantum circuits (VQCs) on classical supervised learning tasks. The study found that quaternion networks general…
-
New research explores advanced federated learning techniques · 10 sources tracked
Multiple research papers published on arXiv in August 2026 introduce novel approaches to enhance federated learning (FL) and decentralized FL. These methods address challenges such as modality missingness in multimodal …
-
Deep Belief Networks spontaneously organize representations of unlabeled data
Researchers have demonstrated that Deep Belief Networks (DBNs), when trained on unlabeled data, can spontaneously organize their internal representations to reflect the underlying class structures of that data. By analy…