Adam Cobb
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Adam Cobb has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Alexander M. Berenbeim
U.S. Military Academy
1 shared publication - Anirban Roy
Computer Science Laboratory, SRI International, Menlo Park, California, United States
1 shared publication - Brian Matejek
Harvard University
1 shared publication - Nathaniel D. Bastian
United States Military Academy
1 shared publication - Ramneet Kaur
SRI, Menlo Park, California, USA
1 shared publication - Susmit Jha
Computer Science Laboratory SRI International
1 shared publication
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 41 (4) , 16-26
Relevance Structures Are a Necessary Prerequisite for Artificial Metacognition
AI-enabled systems deployed in dynamic, open-world, safety- and mission-critical environments often lack mechanisms for reliable self-monitoring and self-regulation under shift and perturbation. Artificial Metacognition (AM) addresses this by enabling systems to assess and adapt their own inference and learning processes. We show that relevance structures, which are order-theoretic substrates for comparing generalization and specialization and for quantifying under-coverage versus overreach, are structurally unavoidable for computable self-regulation. In turn, relevance structures provide an operational control theory for metacognitive tasks. We introduce exploratory, parsimonious, and balanced relevance scores and embed them into version-space algebra to regulate hypothesis search and inductive strategy selection. The resulting framework yields competence-aware learning systems that can both correct and explain their behavior by explicitly balancing exploration and parsimony. We illustrate relevance structures and their application with a medical visual question answering study on the SLAKE dataset.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 41 (4) , 16-26
Relevance Structures Are a Necessary Prerequisite for Artificial Metacognition
AI-enabled systems deployed in dynamic, open-world, safety- and mission-critical environments often lack mechanisms for reliable self-monitoring and self-regulation under shift and perturbation. Artificial Metacognition (AM) addresses this by enabling systems to assess and adapt their own inference and learning processes. We show that relevance structures, which are order-theoretic substrates for comparing generalization and specialization and for quantifying under-coverage versus overreach, are structurally unavoidable for computable self-regulation. In turn, relevance structures provide an operational control theory for metacognitive tasks. We introduce exploratory, parsimonious, and balanced relevance scores and embed them into version-space algebra to regulate hypothesis search and inductive strategy selection. The resulting framework yields competence-aware learning systems that can both correct and explain their behavior by explicitly balancing exploration and parsimony. We illustrate relevance structures and their application with a medical visual question answering study on the SLAKE dataset.
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 114-115
hamiltorch: A PyTorch-based library for Hamiltonian Monte Carlo
This paper summarizes the recent developments of hamiltorch,1 which is a PyTorch-based library for Hamiltonian Monte Carlo (HMC). HMC is a gradient-based Markov chain Monte Carlo technique that has favorable scaling properties to high-dimensional parameter spaces, leading to it often becoming the sampling method of choice when derivatives are available. HMC is therefore especially suited to performing Bayesian inference over neural networks (NN). As a result hamiltorch has been specifically developed to sample from PyTorch NN models. The development of hamiltorch has also led to new sampling schemes that are part of the library. In this paper I will highlight such novelties as well as provide a brief introduction to the features of hamiltorch and highlight its use-cases in recently referenced work.
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 114-115
Open Accesshamiltorch: A PyTorch-based library for Hamiltonian Monte Carlo
This paper summarizes the recent developments of hamiltorch,1 which is a PyTorch-based library for Hamiltonian Monte Carlo (HMC). HMC is a gradient-based Markov chain Monte Carlo technique that has favorable scaling properties to high-dimensional parameter spaces, leading to it often becoming the sampling method of choice when derivatives are available. HMC is therefore especially suited to performing Bayesian inference over neural networks (NN). As a result hamiltorch has been specifically developed to sample from PyTorch NN models. The development of hamiltorch has also led to new sampling schemes that are part of the library. In this paper I will highlight such novelties as well as provide a brief introduction to the features of hamiltorch and highlight its use-cases in recently referenced work.