Generalization in neural networks: A broad survey

C Rohlfs - Neurocomputing, 2025 - Elsevier
This paper reviews concepts, modeling approaches, and recent findings along a spectrum of
different levels of abstraction of neural network models including generalization across (1) …

Many-objective coevolutionary learning algorithm with extreme learning machine auto-encoder for ensemble classifier of feedforward neural networks

H Li, L Bai, W Gao, J **e, L Huang - Expert Systems with Applications, 2024 - Elsevier
In artificial neural network (ANN) learning, empirical risk can be expressed by training error,
while structural risk can be expressed by network complexity. Learning from data is often …

Neural networks regularization with graph-based local resampling

AD Assis, LCB Torres, LRG Araújo, VM Hanriot… - IEEE …, 2021 - ieeexplore.ieee.org
This paper presents the concept of Graph-based Local Resampling of perceptron-like neural
networks with random projections (RN-ELM) which aims at regularization of the yielded …

Multi-objective neural network model selection with a graph-based large margin approach

LCB Torres, CL Castro, HP Rocha, GM Almeida… - Information …, 2022 - Elsevier
This work presents a new decision-making strategy for multi-objective learning problem of
artificial neural networks (ANN). The proposed decision-maker searches for the solution that …

Biobjective optimization problems in simple neural networks as binary associative memories

T Saito, T Togawa - … on Systems, Man, and Cybernetics (SMC), 2021 - ieeexplore.ieee.org
This paper studies biobjective optimization problems in synthesis of binary associative
memories characterized by ternary cross-connection parameters and the signum activation …

A Trade-Off between Memory Stability and Connection Sparsity in Simple Binary Associative Memories

K Saka, T Saito - IEICE Transactions on Fundamentals of …, 2022 - search.ieice.org
This letter studies a biobjective optimization problem in binary associative memories
characterized by ternary connection parameters. First, we introduce a condition of …