Search Results for author: Vaishak Belle

Found 41 papers, 3 papers with code

Deep Inductive Logic Programming meets Reinforcement Learning

no code implementations30 Aug 2023 Andreas Bueff, Vaishak Belle

One approach to explaining the hierarchical levels of understanding within a machine learning model is the symbolic method of inductive logic programming (ILP), which is data efficient and capable of learning first-order logic rules that can entail data behaviour.

Inductive logic programming reinforcement-learning

Learnability with PAC Semantics for Multi-agent Beliefs

no code implementations8 Jun 2023 Ionela G. Mocanu, Vaishak Belle, Brendan Juba

To circumvent the negative results in the literature on the difficulty of robust learning with the PAC semantics, we consider so-called implicit learning where we are able to incorporate observations to the background theory in service of deciding the entailment of an epistemic query.

PAC learning Philosophy

Toward A Logical Theory Of Fairness and Bias

no code implementations8 Jun 2023 Vaishak Belle

Fairness in machine learning is of considerable interest in recent years owing to the propensity of algorithms trained on historical data to amplify and perpetuate historical biases.

counterfactual Fairness

Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?

no code implementations8 Jun 2023 Vaishak Belle

In this paper, our aim is to briefly survey and articulate the logical and philosophical foundations of using (first-order) logic to represent (probabilistic) knowledge in a non-technical fashion.

Relational Reasoning

Synthesising Recursive Functions for First-Order Model Counting: Challenges, Progress, and Conjectures

1 code implementation7 Jun 2023 Paulius Dilkas, Vaishak Belle

First-order model counting (FOMC) is a computational problem that asks to count the models of a sentence in finite-domain first-order logic.

Why not both? Complementing explanations with uncertainty, and the role of self-confidence in Human-AI collaboration

no code implementations27 Apr 2023 Ioannis Papantonis, Vaishak Belle

AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice.


Using Abstraction for Interpretable Robot Programs in Stochastic Domains

no code implementations26 Jul 2022 Till Hofmann, Vaishak Belle

While this allows more precise robot models, the resulting programs are much harder to comprehend, because they need to deal with the noise, e. g., by looping until some desired state has been reached with certainty, and because the resulting action traces consist of a large number of actions cluttered with sensor noise.

Abstracting Noisy Robot Programs

no code implementations7 Apr 2022 Till Hofmann, Vaishak Belle

Abstraction is a commonly used process to represent some low-level system by a more coarse specification with the goal to omit unnecessary details while preserving important aspects.

Explainability in Machine Learning: a Pedagogical Perspective

no code implementations21 Feb 2022 Andreas Bueff, Ioannis Papantonis, Auste Simkute, Vaishak Belle

We provide a pedagogical perspective on how to structure the learning process to better impart knowledge to students and researchers in machine learning, when and how to implement various explainability techniques as well as how to interpret the results.

BIG-bench Machine Learning Decision Making

Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities

no code implementations27 Jan 2022 Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stuart Anderson, Subramanian Ramamoorthy

Robustness evaluations like our checklist will be crucial in future safety evaluations of visual perception modules, and be useful for a wide range of stakeholders including designers, deployers, and regulators involved in the certification of these systems.

Autonomous Driving

Principled Diverse Counterfactuals in Multilinear Models

no code implementations17 Jan 2022 Ioannis Papantonis, Vaishak Belle

Machine learning (ML) applications have automated numerous real-life tasks, improving both private and public life.


MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks

1 code implementation2 Nov 2021 Nicholas Hoernle, Rafael Michael Karampatsis, Vaishak Belle, Kobi Gal

In contrast, our approach, called MultiplexNet, represents domain knowledge as a logical formula in disjunctive normal form (DNF) which is easy to encode and to elicit from human experts.

Density Estimation

Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief

no code implementations6 Oct 2021 Christian Muise, Vaishak Belle, Paolo Felli, Sheila Mcilraith, Tim Miller, Adrian R. Pearce, Liz Sonenberg

Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own beliefs, as well as those of other agents.

Learning Implicitly with Noisy Data in Linear Arithmetic

1 code implementation23 Oct 2020 Alexander P. Rader, Ionela G. Mocanu, Vaishak Belle, Brendan Juba

In this work, we extend implicit learning in PAC-Semantics to handle noisy data in the form of intervals and threshold uncertainty in the language of linear arithmetic.

Principles and Practice of Explainable Machine Learning

no code implementations18 Sep 2020 Vaishak Belle, Ioannis Papantonis

In this report, we focus specifically on data-driven methods -- machine learning (ML) and pattern recognition models in particular -- so as to survey and distill the results and observations from the literature.

BIG-bench Machine Learning

Logic, Probability and Action: A Situation Calculus Perspective

no code implementations17 Jun 2020 Vaishak Belle

The unification of logic and probability is a long-standing concern in AI, and more generally, in the philosophy of science.


Symbolic Logic meets Machine Learning: A Brief Survey in Infinite Domains

no code implementations15 Jun 2020 Vaishak Belle

The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence (AI).

BIG-bench Machine Learning Philosophy +1

Generating Random Logic Programs Using Constraint Programming

no code implementations2 Jun 2020 Paulius Dilkas, Vaishak Belle

Existing methods to generate random logic programs are limited to propositional programs and often impose stringent syntactic restrictions.

On Constraint Definability in Tractable Probabilistic Models

no code implementations29 Jan 2020 Ioannis Papantonis, Vaishak Belle

Incorporating constraints is a major concern in probabilistic machine learning.


Interventions and Counterfactuals in Tractable Probabilistic Models: Limitations of Contemporary Transformations

no code implementations29 Jan 2020 Ioannis Papantonis, Vaishak Belle

We show that when transforming SPNs to a causal graph interventional reasoning reduces to computing marginal distributions; in other words, only trivial causal reasoning is possible.


no code implementations15 Jan 2020 Vaishak Belle

Inductive logic programming (ILP) has been a deeply influential paradigm in AI, enjoying decades of research on its theory and implementations.

Inductive logic programming

Logical Interpretations of Autoencoders

no code implementations26 Nov 2019 Anton Fuxjaeger, Vaishak Belle

The unification of low-level perception and high-level reasoning is a long-standing problem in artificial intelligence, which has the potential to not only bring the areas of logic and learning closer together but also demonstrate how abstract concepts might emerge from sensory data.

Dimensionality Reduction

The Quest for Interpretable and Responsible Artificial Intelligence

no code implementations10 Oct 2019 Vaishak Belle

Artificial Intelligence (AI) provides many opportunities to improve private and public life.

Experiential AI

no code implementations6 Aug 2019 Drew Hemment, Ruth Aylett, Vaishak Belle, Dave Murray-Rust, Ewa Luger, Jane Hillston, Michael Rovatsos, Frank Broz

Experiential AI is proposed as a new research agenda in which artists and scientists come together to dispel the mystery of algorithms and make their mechanisms vividly apparent.

Implicitly Learning to Reason in First-Order Logic

no code implementations NeurIPS 2019 Vaishak Belle, Brendan Juba

We consider the problem of answering queries about formulas of first-order logic based on background knowledge partially represented explicitly as other formulas, and partially represented as examples independently drawn from a fixed probability distribution.

Fairness in Machine Learning with Tractable Models

no code implementations16 May 2019 Michael Varley, Vaishak Belle

Tractable probabilistic models have emerged that guarantee that conditional marginal can be computed in time linear in the size of the model.

BIG-bench Machine Learning Fairness +1

A Correctness Result for Synthesizing Plans With Loops in Stochastic Domains

no code implementations16 May 2019 Laszlo Treszkai, Vaishak Belle

Finite-state controllers (FSCs), such as plans with loops, are powerful and compact representations of action selection widely used in robotics, video games and logistics.

Learning Credal Sum-Product Networks

no code implementations AKBC 2020 Amelie Levray, Vaishak Belle

Thus, learning probabilistic representations directly from data is a deep challenge, the main computational bottleneck being inference that is intractable.

Scaling up Probabilistic Inference in Linear and Non-Linear Hybrid Domains by Leveraging Knowledge Compilation

no code implementations29 Nov 2018 Anton Fuxjaeger, Vaishak Belle

Weighted model integration (WMI) extends weighted model counting (WMC) in providing a computational abstraction for probabilistic inference in mixed discrete-continuous domains.

Learning Tractable Probabilistic Models for Moral Responsibility and Blame

no code implementations8 Oct 2018 Lewis Hammond, Vaishak Belle

From the viewpoint of such systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data?

Decision Making Management +2

Abstracting Probabilistic Models: A Logical Perspective

no code implementations4 Oct 2018 Vaishak Belle

Abstraction is a powerful idea widely used in science, to model, reason and explain the behavior of systems in a more tractable search space, by omitting irrelevant details.

Reasoning about Discrete and Continuous Noisy Sensors and Effectors in Dynamical Systems

no code implementations14 Sep 2018 Vaishak Belle, Hector J. Levesque

Among the many approaches for reasoning about degrees of belief in the presence of noisy sensing and acting, the logical account proposed by Bacchus, Halpern, and Levesque is perhaps the most expressive.

On Plans With Loops and Noise

no code implementations14 Sep 2018 Vaishak Belle

In an influential paper, Levesque proposed a formal specification for analysing the correctness of program-like plans, such as conditional plans, iterative plans, and knowledge-based plans.

Learning Probabilistic Logic Programs in Continuous Domains

no code implementations15 Jul 2018 Stefanie Speichert, Vaishak Belle

The field of statistical relational learning aims at unifying logic and probability to reason and learn from data.

Inductive logic programming Relational Reasoning +1

Tractable Querying and Learning in Hybrid Domains via Sum-Product Networks

no code implementations14 Jul 2018 Andreas Bueff, Stefanie Speichert, Vaishak Belle

By leveraging local structure, representations such as sum-product networks (SPNs) can capture high tree-width models with many hidden layers, essentially a deep architecture, while still admitting a range of probabilistic queries to be computable in time polynomial in the network size.

Probabilistic Planning by Probabilistic Programming

no code implementations25 Jan 2018 Vaishak Belle

Automated planning is a major topic of research in artificial intelligence, and enjoys a long and distinguished history.

Probabilistic Programming

Semiring Programming: A Declarative Framework for Generalized Sum Product Problems

no code implementations21 Sep 2016 Vaishak Belle, Luc De Raedt

To solve hard problems, AI relies on a variety of disciplines such as logic, probabilistic reasoning, machine learning and mathematical programming.

Bayesian Inference BIG-bench Machine Learning

The Symbolic Interior Point Method

no code implementations26 May 2016 Martin Mladenov, Vaishak Belle, Kristian Kersting

A recent trend in probabilistic inference emphasizes the codification of models in a formal syntax, with suitable high-level features such as individuals, relations, and connectives, enabling descriptive clarity, succinctness and circumventing the need for the modeler to engineer a custom solver.

Decision Making Descriptive

Robot Location Estimation in the Situation Calculus

no code implementations28 Feb 2014 Vaishak Belle, Hector Levesque

Location estimation is a fundamental sensing task in robotic applications, where the world is uncertain, and sensors and effectors are noisy.

Reasoning about Probabilities in Dynamic Systems using Goal Regression

no code implementations26 Sep 2013 Vaishak Belle, Hector Levesque

Reasoning about degrees of belief in uncertain dynamic worlds is fundamental to many applications, such as robotics and planning, where actions modify state properties and sensors provide measurements, both of which are prone to noise.

Gaussian Processes regression

Cannot find the paper you are looking for? You can Submit a new open access paper.