Search Results for author:
Found 42 papers, 3 papers with code
KEViN: A Knowledge Enhanced Validity and Novelty Classifier for Arguments
The ArgMining 2022 Shared Task is concerned with predicting the validity and novelty of an inference for a given premise and conclusion pair.
Ranked #2 on
ValNov
on ValNov Subtask A
ToM-LM: Delegating Theory Of Mind Reasoning to External Symbolic Executors in Large Language Models
Theory of Mind (ToM) refers to the ability of individuals to attribute mental states to others.
Deep Inductive Logic Programming meets Reinforcement Learning
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.
Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?
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.
Toward A Logical Theory Of Fairness and Bias
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.
Learnability with PAC Semantics for Multi-agent Beliefs
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.
Synthesising Recursive Functions for First-Order Model Counting: Challenges, Progress, and Conjectures
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
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
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
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
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.
Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities
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.
Principled Diverse Counterfactuals in Multilinear Models
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
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.
Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief
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
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
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.
Logic, Probability and Action: A Situation Calculus Perspective
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
The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence (AI).
Generating Random Logic Programs Using Constraint Programming
Existing methods to generate random logic programs are limited to propositional programs and often impose stringent syntactic restrictions.
Interventions and Counterfactuals in Tractable Probabilistic Models: Limitations of Contemporary Transformations
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.
On Constraint Definability in Tractable Probabilistic Models
Incorporating constraints is a major concern in probabilistic machine learning.
SMT + ILP
Inductive logic programming (ILP) has been a deeply influential paradigm in AI, enjoying decades of research on its theory and implementations.
Logical Interpretations of Autoencoders
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.
The Quest for Interpretable and Responsible Artificial Intelligence
Artificial Intelligence (AI) provides many opportunities to improve private and public life.
Experiential AI
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
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
Tractable probabilistic models have emerged that guarantee that conditional marginal can be computed in time linear in the size of the model.
A Correctness Result for Synthesizing Plans With Loops in Stochastic Domains
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
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
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
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?
Abstracting Probabilistic Models: A Logical Perspective
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.
On Plans With Loops and Noise
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.
Reasoning about Discrete and Continuous Noisy Sensors and Effectors in Dynamical Systems
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.
Learning Probabilistic Logic Programs in Continuous Domains
The field of statistical relational learning aims at unifying logic and probability to reason and learn from data.
Tractable Querying and Learning in Hybrid Domains via Sum-Product Networks
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
Automated planning is a major topic of research in artificial intelligence, and enjoys a long and distinguished history.
Semiring Programming: A Declarative Framework for Generalized Sum Product Problems
To solve hard problems, AI relies on a variety of disciplines such as logic, probabilistic reasoning, machine learning and mathematical programming.
The Symbolic Interior Point Method
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.
Robot Location Estimation in the Situation Calculus
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
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.
