New AI framework autonomously optimizes training data, architectures and algorithms — outperforming human baselines

EVOLVE, an agentic framework that autonomously optimizes AI training data, model architectures, and learning algorithms — ...
IEEE

Inverse Reinforcement Learning via a Modified Kleinman Iteration Approach

Abstract: The Kleinman iteration is a policy iteration method for solving Riccati equations and forms the basis of many reinforcement learning (RL) algorithms. However, its direct application to ...
IEEE

Research on Innovative Application of Genetic Algorithm in Improving BP Neural Network Model

Abstract: In the complex nonlinear prediction problem BP neural network exists overfitting, prediction accuracy is not high and easy to fall into the local optimal defects, so the optimization of BP ...