MNIST database
PulseAugur coverage of MNIST database — every cluster mentioning MNIST database across labs, papers, and developer communities, ranked by signal.
- instance of Fashion-MNIST 90%
- used by variational auto-encoder 90%
- used by CIFAR-100 70%
- used by ResNet-18 70%
- used by Variational Autoencoders 70%
- instance of CIFAR-10 60%
- used by federated learning 60%
- instance of federated learning 60%
- instance of CIFAR-100 60%
- instance of Celeba 60%
- instance of The Street View House Numbers Dataset 60%
- instance of Sulawesi 60%
16 day(s) with sentiment data
-
New method trains energy-based neural networks using Ising Machines
Researchers have developed a new method for training energy-based neural networks by hybridizing Equilibrium Propagation with Ising Machines. This approach aims to overcome the energy demands of traditional GPU-based tr…
-
New training method boosts visible-light diffractive neural networks
Researchers have developed a new training method for diffractive deep neural networks (D2NNs) that addresses limitations in visible-light applications. The existing thin-layer approximation fails for visible-range D2NNs…
-
Quantum algorithm Q-FLAIR slashes resource needs for ML
Researchers have developed a new algorithm called Q-FLAIR to reduce the computational resources needed for quantum machine learning feature maps. This method shifts significant workloads to classical computers, enabling…
-
New framework measures representational ambiguity in neural networks
Researchers have developed a new information-theoretic framework to measure representational ambiguity in neural networks. Their experiments on MNIST classifiers showed that relational structures in network connectivity…
-
New training strategy allows neural networks to learn per-neuron activation functions
Researchers have developed SmartMixed, a new two-phase training strategy that enables neural networks to learn optimal activation functions for individual neurons. The first phase uses a differentiable mixture mechanism…
-
New framework enhances federated learning with evolutionary client selection
Researchers have developed a new framework called EvoCSFL to improve federated learning efficiency and robustness. This method uses an evolutionary algorithm guided by a surrogate model to select clients, optimizing for…
-
Synthetic image models tested for data scarcity and privacy
A new study published on arXiv examines the effectiveness of synthetic image generation models like VAE, GAN, and DDPM when faced with limited data and privacy concerns. Researchers developed a framework to evaluate fid…
-
Optimized optics boost AI classification under detector limits
Researchers have developed a theoretical framework to understand when optimizing optical front-ends with neural network back-ends improves imaging classification performance. The study found that these gains are most si…
-
New quantum gradient method trains circuits orders of magnitude faster
Researchers have developed a new framework for estimating gradients in parameterized quantum circuits (PQCs) that significantly reduces the measurement cost associated with training. This approach, based on the forward …
-
New Aumann-SHAP framework explains ML decisions via counterfactual geometry
Researchers have developed Aumann-SHAP, a new framework for explaining machine learning model decisions by analyzing counterfactual interactions. This method decomposes changes by focusing on a local hypercube between b…
-
New method predicts neural network generalization using Fourier fractal dimension
Researchers have developed a new method to predict how well deep neural networks will generalize without needing separate validation data. This approach uses the Fourier fractal dimension of the network's weight variati…
-
Karpathy revisits 1989 neural net, cuts errors with modern AI techniques
Andrej Karpathy recreated a 1989 neural network, achieving a 60% error reduction by applying modern deep learning techniques. He demonstrated that innovations like using cross-entropy loss instead of mean squared error,…
-
New framework detects noisy labels in AI training data
Researchers have developed a new adaptive framework for detecting noisy labels in datasets used for training deep neural networks. This method integrates local, global, and learning dynamics cues to robustly identify co…
-
New VAE framework improves data representation with topology-matched priors
Researchers have developed a new mathematical framework to improve Variational Autoencoders (VAEs) when dealing with data that has non-Euclidean topology. The proposed method addresses the topological mismatch caused by…
-
Neural collapse dynamics linked to feature norm threshold
Researchers have identified a critical feature norm threshold, fn*, that largely dictates when neural collapse occurs in deep learning models. This threshold is specific to each model-dataset pair and is largely unaffec…
-
HalfNet paper explores learned geometry in random neural network weights
Researchers have introduced HalfNet, a novel approach to neural networks that utilizes random weights drawn from a distribution with learned subspace geometry. This method, detailed in a recent arXiv paper, aims to matc…
-
New BayesWarp framework enhances neural network testing for safety-critical domains
Researchers have developed BayesWarp, a new framework for testing neural networks that aims to improve reliability in safety-critical applications. This method uses interpretable saliency techniques to identify critical…
-
Transformer study finds QKV projection sharing slashes memory use
Researchers have investigated the necessity of three distinct projections (query, key, and value) in Transformer models. Their study found that sharing projections, particularly the Q-K=V variant, can significantly redu…
-
New coherence method enhances neural network interpretability
Researchers have developed a new method called coherence to improve the interpretability of deep neural networks. This geometric property, inspired by neural coding in the brain, ensures that neurons respond to contiguo…
-
New algorithm enhances privacy guarantees in selective release machine learning
Researchers have identified a flaw in the privacy accounting of the Differentially Private Selective Update and Release (DPSUR) algorithm. The existing method overlooks variations in sampling probability introduced by i…