Tootfinder

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[2/2]:
- NoProp: Training Neural Networks without Full Back-propagation or Full Forward-propagation
Qinyu Li, Yee Whye Teh, Razvan Pascanu

Neural Architecture Search with Mixed Bio-inspired Learning Rules
Imane Hamzaoui, Riyadh Baghdadi
https://arxiv.org/abs/2507.13485 https://

Neural Architecture Search with Mixed Bio-inspired Learning Rules
Bio-inspired neural networks are attractive for their adversarial robustness, energy frugality, and closer alignment with cortical physiology, yet they often lag behind back-propagation (BP) based models in accuracy and ability to scale. We show that allowing the use of different bio-inspired learning rules in different layers, discovered automatically by a tailored neural-architecture-search (NAS) procedure, bridges this gap. Starting from standard NAS baselines, we enlarge the search space to…

This https://arxiv.org/abs/2412.07223 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm
This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility,Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.

Broadband Low-loss Unidirectional Reflection On-chip with Asymmetric Dielectric Metasurface
Heijun Jeong, Zeki Hayran, Yuan Liu, Yahui Xiao, Hwaseob Lee, Zi Wang, Jonathan Klamkin, Francesco Monticone, Tingyi Gu
https://arxiv.org/abs/2506.06872

Broadband Low-loss Unidirectional Reflection On-chip with Asymmetric Dielectric Metasurface
Metasurface has emerged as a powerful platform for controlling light at subwavelength thickness, enabling new functionalities for imaging, polarization manipulation, and angular momentum conversion within a flat surface. We explored an integrated asymmetric metasurface simultaneously achieving broadband, low loss forward power transmission, and significant back reflection sup-pression in multi-mode waveguides. The tapering along the direction of light propagation leads to low loss and space-eff…

Statistical Multiport-Network Modeling and Efficient Discrete Optimization of RIS
Cheima Hammami, Luc Le Magoarou, Philipp del Hougne
https://arxiv.org/abs/2508.01776 https://…

Statistical Multiport-Network Modeling and Efficient Discrete Optimization of RIS
This Letter fills the research gap on physics-consistent optimization for reconfigurable intelligent surfaces (RISs) with mutual coupling (MC) and 1-bit-tunable elements, a common hardware constraint in existing RIS prototypes. We compare a model-based method (temperature-annealed back-propagation) and model-agnostic methods (coordinate descent, genetic algorithm), and evaluate potential benefits of intelligently initializing these methods. To facilitate our evaluation, we introduce a technique…