Search Results for author:
Found 38 papers, 8 papers with code
The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
In this paper, we leverage the implicit knowledge within foundation models to enhance the performance in NeSy tasks, whilst reducing the amount of data labelling and manual engineering.
A Unifying Framework for Learning Argumentation Semantics
In this paper we present a novel framework, which uses an Inductive Logic Programming approach to learn the acceptability semantics for several abstract and structured argumentation frameworks in an interpretable way.
NeuralFastLAS: Fast Logic-Based Learning from Raw Data
Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically.
Proceedings 39th International Conference on Logic Programming
This volume contains the Technical Communications presented at the 39th International Conference on Logic Programming (ICLP 2023), held at Imperial College London, UK from July 9 to July 15, 2023.
Reasoning over the Behaviour of Objects in Video-Clips for Adverb-Type Recognition
Specifically, we propose a novel pipeline that extracts human-interpretable object-behaviour-facts from raw video clips and propose novel symbolic and transformer based reasoning methods that operate over these extracted facts to identify adverb-types.
RECAP-KG: Mining Knowledge Graphs from Raw GP Notes for Remote COVID-19 Assessment in Primary Care
By relying on support phrases mined from the SNOMED ontology, as well as predefined supported facts from values used in the RECAP (REmote COVID-19 Assessment in Primary Care) patient risk prediction tool, our graph generative framework is able to extract structured knowledge graphs from the highly unstructured and inconsistent format that consultation notes are written in.
Towards preserving word order importance through Forced Invalidation
Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks.
Neuro-symbolic Rule Learning in Real-world Classification Tasks
Neuro-symbolic rule learning has attracted lots of attention as it offers better interpretability than pure neural models and scales better than symbolic rule learning.
Learning Reward Machines in Cooperative Multi-Agent Tasks
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks.
Sparse Relational Reasoning with Object-Centric Representations
We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints.
Automatic Concept Extraction for Concept Bottleneck-based Video Classification
CoDEx identifies a rich set of complex concept abstractions from natural language explanations of videos-obviating the need to predefine the amorphous set of concepts.
Hierarchies of Reward Machines
Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events.
Neuro-Symbolic Learning of Answer Set Programs from Raw Data
A promising direction for achieving this goal is Neuro-Symbolic AI, which aims to combine the interpretability of symbolic techniques with the ability of deep learning to learn from raw data.
Coherent and Consistent Relational Transfer Learning with Autoencoders
Human defined concepts are inherently transferable, but it is not clear under what conditions they can be modelled effectively by non-symbolic artificial learners.
Numerical reasoning in machine reading comprehension tasks: are we there yet?
The current standings of these models in the DROP leaderboard, over standard metrics, suggest that the models have achieved near-human performance.
FF-NSL: Feed-Forward Neural-Symbolic Learner
To address this limitation, we propose a neural-symbolic learning framework, called Feed-Forward Neural-Symbolic Learner (FFNSL), that integrates a logic-based machine learning system capable of learning from noisy examples, with neural networks, in order to learn interpretable knowledge from labelled unstructured data.
pix2rule: End-to-end Neuro-symbolic Rule Learning
Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules.
Discrete Reasoning Templates for Natural Language Understanding
Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models.
HySTER: A Hybrid Spatio-Temporal Event Reasoner
The task of Video Question Answering (VideoQA) consists in answering natural language questions about a video and serves as a proxy to evaluate the performance of a model in scene sequence understanding.
Learning a Non-Redundant Collection of Classifiers
Inspired by Quality-Diversity algorithms, in this work we train a collection of classifiers to learn distinct solutions to a classification problem, with the goal of learning to exploit a variety of predictive signals present in the training data.
NSL: Hybrid Interpretable Learning From Noisy Raw Data
Using the scoring function of FastLAS, NSL searches for short, interpretable rules that generalise over such noisy examples.
On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision
We propose a new model for relational VAE semi-supervision capable of balancing disentanglement and low complexity modelling of relations with different symbolic properties.
FLAP -- A Federated Learning Framework for Attribute-based Access Control Policies
The design of a policy transfer framework has challenges, including policy conflicts and privacy issues.
Cryptography and Security
Proceedings 36th International Conference on Logic Programming (Technical Communications)
Since the first conference held in Marseille in 1982, ICLP has been the premier international event for presenting research in logic programming.
Induction and Exploitation of Subgoal Automata for Reinforcement Learning
In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks.
Learning Diverse Representations for Fast Adaptation to Distribution Shift
assumption is a useful idealization that underpins many successful approaches to supervised machine learning.
The ILASP system for Inductive Learning of Answer Set Programs
The goal of Inductive Logic Programming (ILP) is to learn a program that explains a set of examples in the context of some pre-existing background knowledge.
A general framework for scientifically inspired explanations in AI
Explainability in AI is gaining attention in the computer science community in response to the increasing success of deep learning and the important need of justifying how such systems make predictions in life-critical applications.
Induction of Subgoal Automata for Reinforcement Learning
In this work we present ISA, a novel approach for learning and exploiting subgoals in reinforcement learning (RL).
Learning Neural Search Policies for Classical Planning
In this paper, we introduce a parametrized search algorithm template which combines various search techniques within a single routine.
Learning Invariants through Soft Unification
The core characteristic of our architecture is soft unification between examples that enables the network to generalise parts of the input into variables, thereby learning invariants.
Saliency Maps Generation for Automatic Text Summarization
Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications.
Learning Classical Planning Strategies with Policy Gradient
This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e. g. the IPC score.
Inductive Learning of Answer Set Programs from Noisy Examples
In recent years, non-monotonic Inductive Logic Programming has received growing interest.
DeepLogic: Towards End-to-End Differentiable Logical Reasoning
Combining machine learning with logic-based expert systems in order to get the best of both worlds are becoming increasingly popular.
Towards learning domain-independent planning heuristics
Automated planning remains one of the most general paradigms in Artificial Intelligence, providing means of solving problems coming from a wide variety of domains.
Iterative Learning of Answer Set Programs from Context Dependent Examples
In ILP, examples must all be explained by a hypothesis together with a given background knowledge.
Learning Weak Constraints in Answer Set Programming
This paper contributes to the area of inductive logic programming by presenting a new learning framework that allows the learning of weak constraints in Answer Set Programming (ASP).
