English
Related papers

Related papers: Connecting Weighted Automata and Recurrent Neural …

200 papers

Transformers with linearised attention (''linear Transformers'') have demonstrated the practical scalability and effectiveness of outer product-based Fast Weight Programmers (FWPs) from the '90s. However, the original FWP formulation is…

Machine Learning · Computer Science 2021-10-28 Kazuki Irie , Imanol Schlag , Róbert Csordás , Jürgen Schmidhuber

We introduce WARP (Weight-space Adaptive Recurrent Prediction), a simple yet powerful model that unifies weight-space learning with linear recurrence to redefine sequence modeling. Unlike conventional recurrent neural networks (RNNs) which…

Despite their great success, neural networks still remain as black-boxes due to the lack of interpretability. Here we propose a new analyzing method, namely the weight pathway analysis (WPA), to make them transparent. We consider weights in…

Machine Learning · Computer Science 2022-08-09 Sihan Feng , Yong Zhang , Fuming Wang , Hong Zhao

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Computation and Language · Computer Science 2023-04-07 Jeremy Wilkerson

Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two…

Computation and Language · Computer Science 2018-05-17 Roy Schwartz , Sam Thomson , Noah A. Smith

Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links…

Machine Learning · Statistics 2019-10-18 Dexiong Chen , Laurent Jacob , Julien Mairal

In recent years, there has been increasing demand for automatic architecture search in deep learning. Numerous approaches have been proposed and led to state-of-the-art results in various applications, including image classification and…

Neural and Evolutionary Computing · Computer Science 2019-04-09 Zhiheng Huang , Bing Xiang

We show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early '90s, where a ``slow" neural net learns by gradient descent to program the ``fast weights" of another net through sequences of…

Machine Learning · Computer Science 2021-06-10 Imanol Schlag , Kazuki Irie , Jürgen Schmidhuber

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

In this paper, we study the approximate minimization problem of weighted finite automata (WFAs): to compute the best possible approximation of a WFA given a bound on the number of states. By reformulating the problem in terms of Hankel…

Formal Languages and Automata Theory · Computer Science 2025-02-12 Clara Lacroce , Borja Balle , Prakash Panangaden , Guillaume Rabusseau

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some…

Computation and Language · Computer Science 2017-03-24 Youssef Oualil , Clayton Greenberg , Mittul Singh , Dietrich Klakow

We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear…

Computation and Language · Computer Science 2018-08-29 Yi Yang

We propose a query learning algorithm for residual symbolic finite automata (RSFAs). Symbolic finite automata (SFAs) are finite automata whose transitions are labeled by predicates over a Boolean algebra, in which a big collection of…

Formal Languages and Automata Theory · Computer Science 2019-09-18 Kaizaburo Chubachi , Diptarama Hendrian , Ryo Yoshinaka , Ayumi Shinohara

Recurrent neural networks are a powerful means to cope with time series. We show how autoregressive linear, i.e., linearly activated recurrent neural networks (LRNNs) can approximate any time-dependent function f(t). The approximation can…

Machine Learning · Computer Science 2025-10-01 Frieder Stolzenburg , Sandra Litz , Olivia Michael , Oliver Obst

Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state…

Machine Learning · Computer Science 2021-03-16 T. Konstantin Rusch , Siddhartha Mishra

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold. Our such-generated neural networks, called Flattening…

Machine Learning · Computer Science 2023-09-11 Michael Psenka , Druv Pai , Vishal Raman , Shankar Sastry , Yi Ma

Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal…

Machine Learning · Computer Science 2021-04-14 Lorenzo Giambagli , Lorenzo Buffoni , Timoteo Carletti , Walter Nocentini , Duccio Fanelli

Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is…

Neural and Evolutionary Computing · Computer Science 2018-04-19 T. Anderson Keller , Sharath Nittur Sridhar , Xin Wang

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Neural and Evolutionary Computing · Computer Science 2017-02-28 Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , Yoshua Bengio