Home Knowledge Base MNIST

MNIST

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Binary Amplitude Modulation Suppresses Noise Up-Conversion in Coherent Diffractive Optical Networks

arXiv:2605.30820v1 Announce Type: new Abstract: We establish a fundamental principle in coherent wave-optical computing: restricting the modulation manifold from continuous complex-valued to binary amplitude suppresses stochastic-noise up-conversion while preserving classification fidelity, yielding a counter-intuitive less-is-more robustness law. Seven-layer binary-amplitude-mask D2NN (BM-D2NN) achieve 90.9% (MNIST) and 81.9% (Fashion-MNIST) test accuracy, within 2~4 pp of...

arXiv Physics 9d ago

HalfNet: Randomized Neural Networks with Learned Subspace Geometry

arXiv:2606.04583v1 Announce Type: new Abstract: Many researchers investigated neural networks with some of their weights fixed to values randomly drawn from a given distribution, e.g., $N(0, I)$. Our proposed HalfNet draws random weights from $N(0, \Sigma)$, where $\Sigma$, which defines the geometry of the distribution, has a low-rank factorization that we learn from data. Experiments on MNIST and CIFAR-10 demonstrate that HalfNet can match the performance of fully trained multilayer...

arXiv CS 6d ago

BRo-JEPA: Learning Modular Arithmetic in Latent Space

arXiv:2606.01372v1 Announce Type: new Abstract: Can neural networks learn abstract algebraic rules, or do they merely memorize training patterns? We investigate this using MNIST digits as states and modular arithmetic operations as actions in a JEPA-style latent world model.

arXiv CS 8d ago

Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks

arXiv:2606.07896v1 Announce Type: cross Abstract: Diffractive deep neural networks (D2NNs) promise miniaturized, power-efficient, light-speed optical front-ends for machine vision, yet the most mature demonstrations remain in the terahertz regime, built from readily fabricated millimeter-scale neurons. Translating D2NNs to the visible range, where nearly all vision pipelines operate, was long blamed on the difficulty of fabricating nanoscale neurons; but even after recent advances removed...

arXiv CS 1d ago

S$^3$LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization

arXiv:2605.31311v1 Announce Type: cross Abstract: Networked AI systems increasingly rely on multiple agents that collaboratively learn and adapt models over communication networks. In such systems, bilevel formulations naturally arise in hyperparameter optimization, data cleaning, and meta-learning, but the repeated evaluation of gradients, Jacobians, and Hessians can impose a substantial computational burden on individual agents. To address this challenge, we propose Snapshot-SLDBO...

arXiv CS 9d ago

Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks

arXiv:2606.07896v1 Announce Type: new Abstract: Diffractive deep neural networks (D2NNs) promise miniaturized, power-efficient, light-speed optical front-ends for machine vision, yet the most mature demonstrations remain in the terahertz regime, built from readily fabricated millimeter-scale neurons. Translating D2NNs to the visible range, where nearly all vision pipelines operate, was long blamed on the difficulty of fabricating nanoscale neurons; but even after recent advances removed that...

arXiv Physics 1d ago

Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

arXiv:2605.20341v2 Announce Type: replace Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. We present HF-KCU, a method that removes a client's contribution by approximating the influence function through conjugate gradient iterations in Krylov subspaces, reducing complexity from O(d^3) to O(kd) where k<<d. A causal weighting mechanism ensures that only...

arXiv CS 1d ago

Robust class-gated single-pixel diffractive optical neural network with random-aberration-aware training

Announce Type: new Abstract: Optical computing offers the theoretical potential for high-speed, energy-efficient inference, yet its practical deployment remains constrained by fundamental input-output bottlenecks, particularly the reliance on electronic sensors with limited frame rates and stringent alignment requirements between optical components. Here, we demonstrate an image-class-gated single-pixel DONN that overcomes these limitations by converting spatial complexity into a temporal...

arXiv Physics 9d ago

Quantum feature-map learning with reduced resource overhead

Announce Type: replace-cross Abstract: Current quantum computers require algorithms that use limited resources economically. In quantum machine learning, success hinges on quantum feature-maps, which embed classical data into the state space of qubits. We introduce Quantum Feature-Map Learning via Analytic Iterative Reconstructions (Q-FLAIR), an algorithm that reduces quantum resource overhead in iterative feature-map circuit construction.

arXiv CS 1d ago

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks

Announce Type: replace Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons. We introduce SmartMixed, a novel two-phase training strategy that allows networks to learn optimal per-neuron activation functions while preserving computational efficiency at inference. In the first phase, neurons adaptively select from a pool of candidate activation functions (ReLU, Sigmoid,...

arXiv CS 1d ago