Loss function
A loss function is a mathematical function used in optimization and machine learning to measure the difference between predicted values and actual values. It guides algorithms in minimizing errors during model training.
machine learning
Libratus
Libratus is an artificial intelligence program developed to play and excel at no-limit Texas hold ’em poker. It demonstrated significant advances in AI by defeating top human professional players in 2017, showcasing new techniques in game theory and decision-making under uncertainty.
Transformers for reinforcement learning (Decision Transformer)
The Decision Transformer is a model that applies transformer architectures to reinforcement learning, merging sequence modeling with decision-making tasks.
ChatGPT
ChatGPT is an AI language model developed by OpenAI that generates human-like text based on input prompts. It is used for various applications including conversation, content creation, and assistance in diverse fields.
Artificial intelligence in China
Artificial intelligence in China refers to the development, application, and strategic prioritization of AI technologies within the country. China has rapidly expanded its AI capabilities through government initiatives, industry investments, and academic research, aiming to become a global leader in the field.
Progressive neural networks
Progressive neural networks are an advanced machine learning architecture that enables efficient transfer learning by leveraging previously learned tasks.
Latent world models (LWM)
Latent world models (LWM) are a framework in artificial intelligence that capture complex environments and dynamics for decision-making tasks.
AI safety
AI safety refers to the field of study focused on ensuring that artificial intelligence systems operate reliably and without causing unintended harm. It encompasses technical, ethical, and policy challenges related to the development and deployment of AI technologies.
Counterfactual explanations
Counterfactual explanations provide insights into the decisions made by algorithms by illustrating what could have happened under different circumstances.
VoxCeleb
VoxCeleb is a large-scale speaker recognition dataset designed for research in speaker verification and recognition tasks.