Probabilistic Foundations for Metacognition via Hybrid-AI

2025-02-08 · Paulo Shakarian, Gerardo I. Simari, Nathaniel D. Bastian

Metacognition is the concept of reasoning about an agent's own internal processes, and it has recently received renewed attention with respect to artificial intelligence (AI) and, more specifically, machine learning systems. This paper reviews a hybrid-AI approach known as "error detecting and correcting rules" (EDCR) that allows for the learning of rules to correct perceptual (e.g., neural) models. Additionally, we introduce a probabilistic framework that adds rigor to prior empirical studies, and we use this framework to prove results on necessary and sufficient conditions for metacognitive improvement, as well as limits to the approach. A set of future

📄 PDF Abstract BibTeX arXiv:2502.05398

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Metacognition in LLMs: Foundations, Progress, and Opportunities

2026-07-13 · Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu, Jordan Thomas 외 hf

Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone…

Theoretical Foundations of GPU-Native Compilation for Rapid Code Iteration

2025-12-12 · Adilet Metinov, Gulida M. Kudakeeva, Gulnara D. Kabaeva arxiv

Current AI code generation systems suffer from significant latency bottlenecks due to CPU-GPU data transfers during compilation, execution, and testing phases. We establish theoretical foundations for three complementary…

Code Generation

Hybrid Bayesian Neural Networks with Functional Probabilistic Layers

2021-07-14 · Daniel T. Chang

Bayesian neural networks provide a direct and natural way to extend standard deep neural networks to support probabilistic deep learning through the use of probabilistic layers that, traditionally, encode weight (and bia…

Bayesian Inference Gaussian Processes Probabilistic Deep Learning Variational Inference

Learning a metacognition for object perception

2020-11-30 · NeurIPS Workshop SVRHM 2020 12 · Marlene Berke, Mario Belledonne, Julian Jara-Ettinger

Beyond representing the external world, humans also represent their own cognitive processes. In the context of perception, this metacognition helps us identify unreliable percepts, such as when we recognize that we are s…

Object

Computational Metacognition

2022-01-30 · Michael Cox, Zahiduddin Mohammad, Sravya Kondrakunta, Ventaksamapth Raja Gogineni 외

Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in a…