Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Learning non-differentiable weights of neural networks using evolutionary strategies

Learning non-differentiable weights of neural networks using evolutionary strategies

US Patent 11676035 · Granted Jun 13, 2023

Estimated economic value: $78,657,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Generation of agentic trajectories for training artificial intelligence agents t2025
Predicting protein structures using geometry neural networks that estimate simil2025
Runtime architecture for interfacing with agents to automate multimodal interfac2025
Multimodal agent for efficient image-text interface automation2025
Determining protein distance maps by combining distance maps crops2025
Distributed training using actor-critic reinforcement learning with off-policy c2025
Generating audio data using unaligned text inputs with an adversarial network2025
Generating audio data using unaligned text inputs with an adversarial network2025
Generative adversarial networks with temporal and spatial discriminators for eff2025
Training machine learning models by determining update rules using neural networ2025
Generating images using neural networks2025
Speech synthesis utilizing audio waveform difference signal(s)2025