Fine-Grained Cognitive Evaluation Framework
A structured approach to assess cognitive processes and reasoning behaviors in models and humans.
Tag: Technique
Reinforcement Learning
A type of machine learning where an agent learns to make decisions by receiving rewards or penalties based on its actions in an environment.
Sum-of-Squares Framework
A method in optimization and algorithm design that uses polynomial equations to derive stronger relaxations for combinatorial problems.
Linear Gradient Matching
Linear Gradient Matching is a method that optimizes synthetic images to induce gradients in a linear classifier similar to those produced by real data when processed through a pre-trained feature extractor.
Supervised Fine-Tuning
A process of further training a pre-trained model on a labeled dataset to improve performance on specific tasks.
Fitness Performance Analysis
An evaluation method used to assess how well a solution or operator performs in achieving the objectives of an optimization problem.
Dataset Distillation
Dataset distillation is the process of creating a smaller synthetic dataset that retains the performance characteristics of a larger real dataset when used for training models.
Warm Starting
Warm Starting refers to the practice of using the solution of a previous problem as the starting point for solving a new, related problem, which can improve convergence speed.