Related papers: Extracting Automata from Recurrent Neural Networks…

Recently, Deep Neural Network (DNN) algorithms have been explored for predicting trends in time series data. In many real world applications, time series data are captured from dynamic systems. DNN models must provide stable performance…

This literature review studies the field of automated process extraction, i.e., transforming textual descriptions into structured processes using Natural Language Processing (NLP). We found that Machine Learning (ML) / Deep Learning (DL)…

Large language model agents often fail to accumulate knowledge from experience, treating each task as an independent challenge. Recent methods extract experience as flattened textual knowledge, which cannot capture procedural logic of…

This paper presents a versatile system intended to acquire paraphrastic phrases from a representative corpus. In order to decrease the time spent on the elaboration of resources for NLP system (for example Information Extraction, IE…

Automata learning is a popular technique used to automatically construct an automaton model from queries. Much research went into devising ad hoc adaptations of algorithms for different types of automata. The CALF project seeks to unify…

Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and interpreted as a…

This paper considers finite-automata based algorithms for handling linear arithmetic with both real and integer variables. Previous work has shown that this theory can be dealt with by using finite automata on infinite words, but this…

Automatic definition extraction from texts is an important task that has numerous applications in several natural language processing fields such as summarization, analysis of scientific texts, automatic taxonomy generation, ontology…

We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such. Given oracle access to a neural network, we introduce a differential attack that can efficiently…

This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from…

Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorithms and…

Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural networks. In this paper, we propose a novel abstraction-based…

Advances in learning-based trajectory prediction are enabled by large-scale datasets. However, in-depth analysis of such datasets is limited. Moreover, the evaluation of prediction models is limited to metrics averaged over all samples in…

Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to…

The paper describes a system that uses large language model (LLM) technology to support the automatic learning of new entries in an intelligent agent's semantic lexicon. The process is bootstrapped by an existing non-toy lexicon and a…

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is…

We show that a well-known family of deterministic finite automata can be used to distinguish distinct binary strings of the same length from every start state. Further, we establish almost matching lower and upper bounds on the number of…

Automaton learning is a domain in which the target system is inferred by the automaton learning algorithm in the form of an automaton, by synthesizing a finite number of inputs and their corresponding outputs. Automaton learning makes use…

We present $L^{\#}$, a new and simple approach to active automata learning. Instead of focusing on equivalence of observations, like the $L^{\ast}$ algorithm and its descendants, $L^{\#}$ takes a different perspective: it tries to establish…

Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel…