On Finding the Best Learning Model for Assessing Confidence in Speech

Nair, Shruti; Mohan, Madhumita; Rajesh, Jemima; Chandran, Priya

doi:10.1145/3426826.3426838

Cited by 8 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI enhances its performance by optimizing a given objective function, which serves as a criterion for effective operation. This function acts as a performance metric, representing how well AI is functioning (Nair et al 2020). AI learns to maximize or minimize the objective function based on information acquired from learning data.…”

Section: Process Of Ai Goal Setting and Subgoal Derivationmentioning

confidence: 99%

Towards an international regulatory framework for AI safety: lessons from the IAEA’s nuclear safety regulations

Cha

2024

Humanit Soc Sci Commun

View full text Add to dashboard Cite

This study explores the necessity and direction of safety regulations for Artificial Intelligence (AI), drawing parallels from the regulatory practices of the International Atomic Energy Agency (IAEA) for nuclear safety. The rapid advancement and global proliferation of AI technologies necessitate the establishment of standardized safety norms to minimize discrepancies between national regulations and enhance the consistency and effectiveness of these rules. The study emphasizes the importance of international collaboration and the engagement of various stakeholders to strengthen the appropriateness of regulations and ensure their continuous updating in response to the evolving risks associated with technological advancements. The paper highlights the critical role of subgoal setting mechanisms in AI’s decision-making processes, underscoring their significance in ensuring the technology’s stability and social acceptability. Improperly tuned subgoal setting mechanisms may lead to outcomes that conflict with human intentions, posing risks to users and society at large. The study draws attention to the hidden risks often embedded within AI’s core decision-making mechanisms and advocates for regulatory approaches to guarantee safe and predictable AI operations. Furthermore, the study acknowledges the limitations of directly applying IAEA’s nuclear safety cases to AI due to the distinct characteristics and risks of the two fields. The paper calls for future research to delve deeper into the need for an independent regulatory framework tailored to AI’s unique features. Additionally, the study emphasizes the importance of accelerating international consensus, developing flexible regulatory models that reflect the situation in each country, exploring harmonization with existing regulations, and researching timely regulatory responses to the fast-paced development of AI technology.

show abstract

Section: Process Of Ai Goal Setting and Subgoal Derivationmentioning

confidence: 99%

Towards an international regulatory framework for AI safety: lessons from the IAEA’s nuclear safety regulations

Cha

2024

Humanit Soc Sci Commun

View full text Add to dashboard Cite

show abstract

“…In the computational reinforcement-learning literature, this reality has called into question longstanding approaches to model-based reinforcement learning (Littman, 2015 ; Sutton, 1991 ; Sutton & Barto, 1998 ) which use standard maximum-likelihood estimation techniques that endeavor to learn the exact model (𝒰, 𝒯) that governs the underlying MDP. The end result has been a flurry of recent work (Abachi et al, 2020 ; Asadi et al, 2018 ; Ayoub et al, 2020 ; Cui et al, 2020 ; D’Oro et al, 2020 ; Farahmand, 2018 ; Farahmand et al, 2017 ; Grimm et al, 2020 , 2021 , 2022 ; Nair et al, 2020 ; Nikishin et al, 2022 ; Oh et al, 2017 ; Schrittwieser et al, 2020 ; Silver et al, 2017 ; Voelcker et al, 2022 ) which eschews the traditional maximum-likelihood objective in favor of various surrogate objectives which restrict the focus of the agent’s modeling towards specific aspects of the environment. As the core goal of endowing a decision-making agent with its own internal model of the world is to facilitate model-based planning (Bertsekas, 1995 ), central among these recent approaches is the value-equivalence principle (Grimm et al, 2020 , 2021 , 2022 ) which provides mathematical clarity on how surrogate models can still enable lossless planning relative to the true model of the environment.…”

Section: Problem Formulationmentioning

confidence: 99%

Bayesian Reinforcement Learning With Limited Cognitive Load

Arumugam,

Ho,

Goodman

et al. 2024

Open Mind

View full text Add to dashboard Cite

All biological and artificial agents must act given limits on their ability to acquire and process information. As such, a general theory of adaptive behavior should be able to account for the complex interactions between an agent’s learning history, decisions, and capacity constraints. Recent work in computer science has begun to clarify the principles that shape these dynamics by bridging ideas from reinforcement learning, Bayesian decision-making, and rate-distortion theory. This body of work provides an account of capacity-limited Bayesian reinforcement learning, a unifying normative framework for modeling the effect of processing constraints on learning and action selection. Here, we provide an accessible review of recent algorithms and theoretical results in this setting, paying special attention to how these ideas can be applied to studying questions in the cognitive and behavioral sciences.

show abstract

“…Lynch et al [8] and Nair et al [9] tackle the challenge of achieving a manipulation task composed of several subtasks. Lynch et al [8] uses the pairs of current and goal images to estimate the entire sequence of actions to achieve the goal, by encoding the task in a latent space.…”

Section: A Related Workmentioning

confidence: 99%

“…Lynch et al [8] uses the pairs of current and goal images to estimate the entire sequence of actions to achieve the goal, by encoding the task in a latent space. Nair et al [9] also uses difference between a current image and a goal image to infer the latent space, but to select the following action. Florensa et al [10] used Reinforcement Learning to learn all feasible goal paths in the environment for locomotion.…”

Section: A Related Workmentioning

confidence: 99%

“…The module is trained 1000 epochs and thereafter, we add noise of brightness, parallel translation and rotation to the training image data and train additional 100 epochs. 2) SPM: We construct the SPM encoder, for outputting subgoal features using final goal and current image, whose idea refers [9]. For training the module, we use indicated ground truth subgoals mentioned in Section II-B.…”

Section: Deep Learning Modulesmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Designing Autonomous Robots that Know Their Limits

Gautam

Whiting

Cao

et al. 2022

2022 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

For assisting humans in their daily lives, robots need to perform long-horizon tasks, such as tidying up a room or preparing a meal. One effective strategy for handling a long-horizon task is to break it down into short-horizon subgoals, that the robot can execute sequentially. In this paper, we propose extending a predictive learning model using deep neural networks (DNN) with a Subgoal Proposal Module (SPM), with the goal of making such tasks realizable. We evaluate our proposed model in a case-study of a long-horizon task, consisting of cutting and arranging a pizza. This task requires the robot to consider: (1) the order of the subtasks, (2) multiple subtask selection, (3) coordination of dual-arm, and (4) variations within a subtask. The results confirm that the model is able to generalize motion generation to unseen tools and objects arrangement combinations. Furthermore, it significantly reduces the prediction error of the generated motions compared to without the proposed SPM. Finally, we validate the generated motions on the dual-arm robot Nextage Open.

show abstract

On Finding the Best Learning Model for Assessing Confidence in Speech

Cited by 8 publications

References 3 publications

Towards an international regulatory framework for AI safety: lessons from the IAEA’s nuclear safety regulations

Towards an international regulatory framework for AI safety: lessons from the IAEA’s nuclear safety regulations

Bayesian Reinforcement Learning With Limited Cognitive Load

A Method for Designing Autonomous Robots that Know Their Limits

Contact Info

Product

Resources

About