English
Related papers

Related papers: When You Must Forget: beyond strong persistence wh…

200 papers

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove…

Machine Learning · Computer Science 2024-11-01 Kairan Zhao , Meghdad Kurmanji , George-Octavian Bărbulescu , Eleni Triantafillou , Peter Triantafillou

Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this…

Computation and Language · Computer Science 2026-04-08 Alexandros Christoforos

Many inference scenarios rely on extracting relevant information from known data in order to make future predictions. When the underlying stochastic process satisfies certain assumptions, there is a direct mapping between its exact…

Quantum Physics · Physics 2024-05-10 Leonardo Banchi

This paper presents a novel approach based on variable forgetting, which is a useful tool in resolving contradictory by filtering some given variables, to merging multiple knowledge bases. This paper first builds a relationship between…

Artificial Intelligence · Computer Science 2013-01-11 Dai Xu , Xiaowang Zhang , Zuoquan Lin

It is well-know that deciding consistency for normal answer set programs (ASP) is NP-complete, thus, as hard as the satisfaction problem for classical propositional logic (SAT). The best algorithms to solve these problems take exponential…

Logic in Computer Science · Computer Science 2020-07-10 Markus Hecher , Jorge Fandinno

Many applications require complexly structured data objects. Developing new or adapting existing algorithmic solutions for creating such objects can be a non-trivial and costly task if the considered objects are subject to different…

Programming Languages · Computer Science 2015-03-19 Johannes Oetsch , Jörg Pührer , Hans Tompits

The decoupling between the representation of a certain problem, i.e., its knowledge model, and the reasoning side is one of main strong points of model-based Artificial Intelligence (AI). This allows, e.g. to focus on improving the…

Artificial Intelligence · Computer Science 2022-03-03 Carmine Dodaro , Marco Maratea , Mauro Vallati

Reinforcement learning (RL) agents can forget tasks they have previously been trained on. There is a rich body of work on such forgetting effects in humans. Therefore we look for commonalities in the forgetting behavior of humans and RL…

Machine Learning · Computer Science 2025-03-05 Marc Speckmann , Theresa Eimer

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Machine Learning · Computer Science 2024-09-05 Eric Zhang , Leshem Chosen , Jacob Andreas

The advance of Internet and Sensor technology has brought about new challenges evoked by the emergence of continuous data streams. Beyond rapid data processing, application areas like ambient assisted living, robotics, or dynamic scheduling…

Artificial Intelligence · Computer Science 2013-01-09 Martin Gebser , Torsten Grote , Roland Kaminski , Philipp Obermeier , Orkunt Sabuncu , Torsten Schaub

Consistent query answering over a database that violates primary key constraints is a classical hard problem in database research that has been traditionally dealt with logic programming. However, the applicability of existing logic-based…

Artificial Intelligence · Computer Science 2015-07-23 Marco Manna , Francesco Ricca , Giorgio Terracina

Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or…

Machine Learning · Computer Science 2023-12-04 Nuri Korhan , Ceren Öner

Selecting relevant features is an important and necessary step for intelligent machines to maximize their chances of success. However, intelligent machines generally have no enough computing resources when faced with huge volume of data.…

Machine Learning · Computer Science 2025-07-04 Hexiang Bai , Deyu Li , Jiye Liang , Yanhui Zhai

This research started with an algebra for reasoning about rely/guarantee concurrency for a shared memory model. The approach taken led to a more abstract algebra of atomic steps, in which atomic steps synchronise (rather than interleave)…

Logic in Computer Science · Computer Science 2017-10-11 Ian J. Hayes , Larissa A. Meinicke , Kirsten Winter , Robert J. Colvin

Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of…

Artificial Intelligence · Computer Science 2018-06-20 Christos Kaplanis , Murray Shanahan , Claudia Clopath

Answer set programming (ASP) is a logic programming paradigm that can be used to solve complex combinatorial search problems. Aggregates are an ASP construct that plays an important role in many applications. Defining a satisfactory…

Artificial Intelligence · Computer Science 2008-12-09 Paolo Ferraris

Answer Set Programming (ASP) is a well-established paradigm of declarative programming that has been developed in the field of logic programming and nonmonotonic reasoning. Advances in ASP solving technology are customarily assessed in…

Artificial Intelligence · Computer Science 2014-06-04 Francesco Calimeri , Martin Gebser , Marco Maratea , Francesco Ricca

We introduce an implementation of an extension of Answer Set Programming (ASP) with language constructs from dynamic (and temporal) logic that provides an expressive computational framework for modeling dynamic applications. Starting from…

Artificial Intelligence · Computer Science 2020-02-20 Pedro Cabalar , Martín Diéguez , Torsten Schaub , François Laferrière

We introduce a model of online algorithms subject to strict constraints on data retention. An online learning algorithm encounters a stream of data points, one per round, generated by some stationary process. Crucially, each data point can…

Machine Learning · Computer Science 2024-04-18 Nicole Immorlica , Brendan Lucier , Markus Mobius , James Siderius

Our research concerns generating imperative programs from Answer Set Programming Specifications. ASP is highly declarative and is ideal for writing specifications. Further with negation-as-failure it is easy to succinctly represent…

Symbolic Computation · Computer Science 2019-09-20 Sarat Chandra Varanasi