Fashion-MNIST
PulseAugur coverage of Fashion-MNIST — every cluster mentioning Fashion-MNIST across labs, papers, and developer communities, ranked by signal.
- used by The Street View House Numbers Dataset 70%
- instance of federated learning 70%
- used by federated learning 70%
- used by residual neural network 70%
- instance of residual neural network 70%
- used by backpropagation 70%
- competes with AdamW 70%
- used by ResNet-18 70%
- used by ResNet18 70%
- instance of CIFAR-100 60%
- used by multilayer perceptron 60%
- instance of The Street View House Numbers Dataset 60%
9 day(s) with sentiment data
-
LightSplit enhances privacy in split learning with orthogonal projections
Researchers have developed LightSplit, a novel approach to privacy-preserving split learning that uses orthogonal projections to reduce communication overhead and protect against reconstruction attacks. This method part…
-
LiBRA method enhances Byzantine-robust client selection in federated learning
Researchers have developed LiBRA, a novel method for Byzantine-robust client selection in federated learning. Unlike existing approaches that compare client parameter vectors, LiBRA analyzes the computed output (logit f…
-
New SCIB method boosts Spiking Neural Network robustness and efficiency
Researchers have developed a new learning objective called SCIB (Conditional Information Bottleneck) to improve the robustness of Spiking Neural Networks (SNNs). This method addresses the vulnerability of SNNs to noise …
-
TRIP-Shapley framework improves P2P federated learning attribution
Researchers have developed TRIP-Shapley, a new framework for attributing contributions in peer-to-peer federated learning (P2PFL). This method addresses communication overhead and misreporting attack vulnerabilities inh…
-
New criterion optimizes weight initialization for deep neural networks
Researchers have developed a new mathematical criterion for selecting the optimal variance of weight initialization in deep neural networks (DNNs). By analyzing stochastic gradient descent (SGD) through a continuous-tim…
-
Quantum and classical AI representations fused for enhanced prediction
A new research paper explores the benefits of integrating quantum machine learning representations with classical ones for improved predictive performance. The study proposes a framework that combines both classical and…
-
Forward-Only Deep Learning Algorithms Show Mixed Energy Efficiency
A new study published on arXiv benchmarks forward-only deep learning algorithms against traditional backpropagation. The research found that while some forward-only methods like Forward-Forward and Cascaded Forward are …
-
New power side-channel attack infers ML training data from embedded device power traces
Researchers have developed a novel power side-channel membership inference attack (PSCMIA) that can infer whether a specific data sample was used to train an embedded machine learning model. Unlike previous attacks that…
-
MetaLearnNCA: Decentralized Few-Shot Meta-Learning with Neural Cellular Automata
Researchers have introduced MetaLearnNCA, a novel framework for few-shot meta-learning that utilizes interacting Neural Cellular Automata (NCAs). This decentralized approach adapts to new tasks without requiring analyti…
-
New research explores neurosymbolic AI integration and interpretability
Two new research papers explore the integration of symbolic reasoning with neural networks for AI. The first paper, "Rule-Based Languages for Neurosymbolic AI," surveys existing rule-based languages like Datalog and pro…
-
Quantum machine learning frameworks show promise for classification tasks
Researchers have developed new frameworks for quantum machine learning, focusing on improving classification tasks. One approach introduces a versatile variational quantum kernel framework that demonstrates competitive …
-
Automated framework EXAQC evolves quantum circuits for image classification
Researchers have developed an evolutionary framework called EXAQC to automatically discover optimal quantum circuit architectures for image classification tasks. This framework integrates parameterized quantum circuits …
-
Kolmogorov-Arnold Networks show promise in scaling, PDEs, and interpretability · 3 sources tracked
Researchers are exploring the capabilities and theoretical underpinnings of Kolmogorov-Arnold Networks (KANs), an alternative to traditional Multi-Layer Perceptrons (MLPs). One study investigates KANs' neural scaling la…
-
New T-ARC clustering method corrects k-means geometric bias using topology
Researchers have introduced T-ARC, a novel topology-aware randomized clustering method designed to overcome the geometric biases inherent in traditional k-means clustering. This new approach integrates topological infor…
-
New Spiking Neural Network Architecture Enhances Image and Event Stream Processing · 3 sources tracked
Researchers have developed a novel spiking neural network (SNN) architecture called Multi-Depth Temporal Fusion (MDTF) designed for processing static images and event streams using time-to-first-spike latencies. This ne…
-
New scale-invariant networks improve image scale generalization
Researchers have developed new scale-invariant Gaussian derivative residual networks (GaussDerResNets) designed to improve how deep learning models handle images at different scales. These networks incorporate residual …
-
New research advances diffusion language models with efficiency and performance gains · 10 sources tracked
Researchers are developing new methods to improve diffusion language models (DLMs), focusing on efficiency and performance. "Clock Diffusion" introduces semi-autoregressive continuous DLMs with position-dependent noise …
-
New framework certifies safety in federated Bayesian learning models
Researchers have developed a new framework for certifying the safety of Bayesian neural networks in federated learning scenarios. This method, called Posterior Event Transport, addresses the challenge that local safety …
-
New DDLGN framework boosts TFHE encrypted inference speed
Researchers have developed EI-DDLGN, a novel framework for efficient encrypted inference using Deep Differentiable Logic Gate Networks (DDLGNs) with Torus Fully Homomorphic Encryption (TFHE). This approach leverages DDL…
-
QSTAR framework enhances quantum transfer learning by selectively routing uncertain predictions
Researchers have developed QSTAR, a novel framework for quantum transfer learning that selectively routes uncertain predictions to a quantum branch. This approach aims to clarify the utility of quantum components in mac…