English
Related papers

Related papers: Simulating Weighted Automata over Sequences and Tr…

200 papers

The remarkable capability of over-parameterised neural networks to generalise effectively has been explained by invoking a ``simplicity bias'': neural networks prevent overfitting by initially learning simple classifiers before progressing…

Computation and Language · Computer Science 2025-10-02 Riccardo Rende , Federica Gerace , Alessandro Laio , Sebastian Goldt

Tree automata based algorithms are essential in many fields in computer science such as verification, specification, program analysis. They become also essential for databases with the development of standards such as XML. In this paper, we…

Computational Complexity · Computer Science 2007-05-23 J. Carme , R. Gilleron , A. Lemay , A. Terlutte , M. Tommasi

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…

Machine Learning · Computer Science 2021-07-28 Danielle Rothermel , Margaret Li , Tim Rocktäschel , Jakob Foerster

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a…

Machine Learning · Computer Science 2018-09-13 Cheng-Hao Cai , Yanyan Xu , Dengfeng Ke , Kaile Su , Jing Sun

Self-adaptive large language models (LLMs) aim to solve the challenges posed by traditional fine-tuning methods, which are often computationally intensive and static in their ability to handle diverse tasks. We introduce…

Machine Learning · Computer Science 2025-01-27 Qi Sun , Edoardo Cetin , Yujin Tang

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

Machine Learning · Computer Science 2024-05-08 Dongseong Hwang , Weiran Wang , Zhuoyuan Huo , Khe Chai Sim , Pedro Moreno Mengibar

Deep neural networks (DNNs) can be useful within the marine robotics field, but their utility value is restricted by their black-box nature. Explainable artificial intelligence methods attempt to understand how such black-boxes make their…

Robotics · Computer Science 2022-03-02 Vilde B. Gjærum , Inga Strümke , Ole Andreas Alsos , Anastasios M. Lekkas

Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining representations within hidden states. This…

Computation and Language · Computer Science 2026-03-12 Markus Frey , Behzad Shomali , Ali Hamza Bashir , David Berghaus , Joachim Koehler , Mehdi Ali

Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA), from demonstrations. Unfortunately,…

Machine Learning · Computer Science 2025-06-24 Marcell Vazquez-Chanlatte , Karim Elmaaroufi , Stefan J. Witwicki , Matei Zaharia , Sanjit A. Seshia

Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks?…

Machine Learning · Computer Science 2025-04-30 Vincent Herrmann , Francesco Faccio , Jürgen Schmidhuber

Finite-turn pushdown automata (PDA) are investigated concerning their descriptional complexity. It is known that they accept exactly the class of ultralinear context-free languages. Furthermore, the increase in size when converting…

Formal Languages and Automata Theory · Computer Science 2009-05-08 Andreas Malcher , Giovanni Pighizzini

Existing work has analyzed the representational capacity of the transformer architecture by means of formal models of computation. However, the focus so far has been on analyzing the architecture in terms of language \emph{acceptance}. We…

Computation and Language · Computer Science 2024-06-21 Anej Svete , Ryan Cotterell

Cellular automata are a discrete dynamical system which models massively parallel computation. Much attention is devoted to computations with small time complexity for which the parallelism may provide further possibilities. In this paper,…

Formal Languages and Automata Theory · Computer Science 2012-08-15 Anaël Grandjean , Gaétan Richard , Véronique Terrier

We advance the recently proposed neuro-symbolic Differentiable Tree Machine, which learns tree operations using a combination of transformers and Tensor Product Representations. We investigate the architecture and propose two key…

Deterministic finite automata (DFAs) are constructed for various purposes in computational biology. Little attention, however, has been given to the efficient construction of minimal DFAs. In this article, we define simple non-deterministic…

Formal Languages and Automata Theory · Computer Science 2010-12-10 Tobias Marschall

Insects, such as fruit flies and honey bees, can solve simple associative learning tasks and learn abstract concepts such as "sameness" and "difference", which is viewed as a higher-order cognitive function and typically thought to depend…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Jinyung Hong , Theodore P. Pavlic

Complexity classes such as $\#\mathbf{P}$, $\oplus\mathbf{P}$, $\mathbf{GapP}$, $\mathbf{OptP}$, $\mathbf{NPMV}$, or the class of fuzzy languages realised by polynomial-time fuzzy nondeterministic Turing machines, can all be described in…

Formal Languages and Automata Theory · Computer Science 2024-08-20 Peter Kostolányi

Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform. Consequently, they can often be compressed using techniques such…

Machine Learning · Computer Science 2020-12-03 Vinu Joseph , Saurav Muralidharan , Animesh Garg , Michael Garland , Ganesh Gopalakrishnan

In this paper we propose that a restricted version of logical inference can be implemented with self-attention networks. We are aiming at showing that LLMs (Large Language Models) constructed with transformer networks can make logical…

Artificial Intelligence · Computer Science 2024-10-16 Phan Thi Thanh Thuy , Akihiro Yamamoto

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning. We generalize the…

Neural and Evolutionary Computing · Computer Science 2020-12-11 Nico Potyka
‹ Prev 1 8 9 10 Next ›