English
Related papers

Related papers: On the Expressive Power of Transformers for Maxout…

200 papers

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…

Computation and Language · Computer Science 2025-04-08 Samuele Marro , Davide Evangelista , X. Angelo Huang , Emanuele La Malfa , Michele Lombardi , Michael Wooldridge

Planning is a crucial element of both human intelligence and contemporary large language models (LLMs). In this paper, we initiate a theoretical investigation into the emergence of planning capabilities in Transformer-based LLMs via their…

Machine Learning · Computer Science 2024-11-12 Siwei Wang , Yifei Shen , Shi Feng , Haoran Sun , Shang-Hua Teng , Wei Chen

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

Machine Learning · Computer Science 2018-11-09 Davide Bacciu , Antonio Carta , Alessandro Sperduti

Owing to success in the data-rich domain of natural images, Transformers have recently become popular in medical image segmentation. However, the pairing of Transformers with convolutional blocks in varying architectural permutations leaves…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Saikat Roy , Gregor Koehler , Michael Baumgartner , Constantin Ulrich , Jens Petersen , Fabian Isensee , Klaus Maier-Hein

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representations. In these…

Machine Learning · Computer Science 2021-02-24 Etai Littwin , Tomer Galanti , Lior Wolf , Greg Yang

Multiplication layers are a key component in various influential neural network modules, including self-attention and hypernetwork layers. In this paper, we investigate the approximation capabilities of deep neural networks with…

Machine Learning · Computer Science 2023-01-12 Ido Ben-Shaul , Tomer Galanti , Shai Dekel

This extended abstract describes a framework for analyzing the expressiveness, learning, and (structural) generalization of hypergraph neural networks (HyperGNNs). Specifically, we focus on how HyperGNNs can learn from finite datasets and…

Machine Learning · Computer Science 2023-03-10 Zhezheng Luo , Jiayuan Mao , Joshua B. Tenenbaum , Leslie Pack Kaelbling

The increasing number of protein sequences decoded from genomes is opening up new avenues of research on linking protein sequence to function with transformer neural networks. Recent research has shown that the number of known protein…

Machine Learning · Computer Science 2022-06-23 Anowarul Kabir , Amarda Shehu

We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated…

Machine Learning · Statistics 2017-06-20 Maithra Raghu , Ben Poole , Jon Kleinberg , Surya Ganguli , Jascha Sohl-Dickstein

Landmark universal function approximation results for neural networks with trained weights and biases provided the impetus for the ubiquitous use of neural networks as learning models in neuroscience and Artificial Intelligence (AI). Recent…

Neural and Evolutionary Computing · Computer Science 2025-03-25 Ezekiel Williams , Alexandre Payeur , Avery Hee-Woon Ryoo , Thomas Jiralerspong , Matthew G. Perich , Luca Mazzucato , Guillaume Lajoie

We study the expressive power of deep ReLU neural networks for approximating functions in dilated shift-invariant spaces, which are widely used in signal processing, image processing, communications and so on. Approximation error bounds are…

Machine Learning · Computer Science 2023-12-05 Yunfei Yang , Zhen Li , Yang Wang

Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole,…

Computation and Language · Computer Science 2024-05-03 Patrick Kahardipraja , Brielen Madureira , David Schlangen

As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target…

Machine Learning · Computer Science 2023-10-17 Yun Yi , Haokui Zhang , Rong Xiao , Nannan Wang , Xiaoyu Wang

Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map…

Optimization and Control · Mathematics 2026-02-16 Borjan Geshkovski , Philippe Rigollet , Domènec Ruiz-Balet

Empirical studies have identified a range of learnability biases and limitations of transformers, such as a persistent difficulty in learning to compute simple formal languages such as PARITY, and a bias towards low-degree functions.…

Machine Learning · Computer Science 2024-05-28 Michael Hahn , Mark Rofin

Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs…

Machine Learning · Computer Science 2019-01-31 Valentin Khrulkov , Oleksii Hrinchuk , Ivan Oseledets

Robustness verification that aims to formally certify the prediction behavior of neural networks has become an important tool for understanding model behavior and obtaining safety guarantees. However, previous methods can usually only…

Machine Learning · Computer Science 2020-12-24 Zhouxing Shi , Huan Zhang , Kai-Wei Chang , Minlie Huang , Cho-Jui Hsieh

The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability. However, while the theoretical capacity of deep architectures is high, the practical expressive power achieved through successful…

Machine Learning · Computer Science 2023-12-21 Zezhong Zhang , Feng Bao , Guannan Zhang

Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand,…

Machine Learning · Computer Science 2024-12-03 Bo Chen , Xiaoyu Li , Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song

It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, although the robust training error can be near zero via some…

Machine Learning · Computer Science 2022-10-17 Binghui Li , Jikai Jin , Han Zhong , John E. Hopcroft , Liwei Wang