note

過学習（Overfitting）： AI システムの開発における本質的な問題

以前、集合学習や、交差検証に関する記事、また機械学習のECへの応用に関する記事等で、繰り返し、AIシステムにおけるモデルのロバストネスを高め、「過学習（Overfitting）」をいかに防いでいくかが大事であると述べました。 今回は、そもそもその「過 ...
GitHub

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a ...
IEEE

Overfitting Problem of ANN- and VSTF-Based Nonlinear Equalizers Trained on Repeated Random ...

Abstract: In this paper, we investigated the overfitting characteristics of nonlinear equalizers based on an artificial neural network (ANN) and the Volterra series transfer function (VSTF), which ...
Tech Xplore on MSN

Overparameterized neural networks: Feature learning precedes overfitting, research finds

Modern neural networks, with billions of parameters, are so overparameterized that they can "overfit" even random, structureless data. Yet when trained on datasets with structure, they learn the ...