MNIST

Dataset Card for MNIST Dataset Summary The MNIST dataset consists of 70,000 28x28 black-and-white images of handwritten digits extracted from two NIST databases. There are 60,000 images in the training dataset and 10,000 images in the validation dataset, one class per digit so a total of 10 classes, with 7,000 images (

Papers using MNIST (14)

A Unified Generative-Predictive Framework for Deterministic Inverse Design2025 · 2 citesPhotonic convolutional neural network with pre-trained in-situ training2026Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification2026No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computation2026Holographic generative flows with AdS/CFT2026MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks2025Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines2025Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion2025Cauchy activation function and XNet2024How important are activation functions in regression and classification? A survey, performance comparison, and future directions2022 · 13 citesQuantum-limited stochastic optical neural networks operating at a few quanta per activation2023 · 6 citesTensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks2023 · 6 citesPhysics-aware Roughness Optimization for Diffractive Optical Neural Networks2023 · 1 citesNoise-robust chemical reaction networks training artificial neural networks2024