English
Related papers

Related papers: Looped ReLU MLPs May Be All You Need as Practical …

200 papers

We present the Input-Connected Multilayer Perceptron (IC-MLP), a feedforward neural network architecture in which each hidden neuron receives, in addition to the outputs of the preceding layer, a direct affine connection from the raw input.…

Machine Learning · Computer Science 2026-03-25 Vugar Ismailov

In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-12 Pedro Carrinho , Hamid Moghadaspour , Oscar Ferraz , João Dinis Ferreira , Yann Falevoz , Vitor Silva , Gabriel Falcao

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training. Neural Arithmetic Units aim to overcome this difficulty, but current arithmetic…

Machine Learning · Computer Science 2020-12-18 Niklas Heim , Tomáš Pevný , Václav Šmídl

A mechanistic understanding of how MLPs do computation in deep neural networks remains elusive. Current interpretability work can extract features from hidden activations over an input dataset but generally cannot explain how MLP weights…

Machine Learning · Computer Science 2025-06-26 Michael T. Pearce , Thomas Dooms , Alice Rigg , Jose M. Oramas , Lee Sharkey

Feed-forward, fully-connected Artificial Neural Networks (ANNs) or the so-called Multi-Layer Perceptrons (MLPs) are well-known universal approximators. However, their learning performance varies significantly depending on the function or…

Computer Vision and Pattern Recognition · Computer Science 2019-10-21 Serkan Kiranyaz , Turker Ince , Alexandros Iosifidis , Moncef Gabbouj

This work studies the expressivity of ReLU neural networks with a focus on their depth. A sequence of previous works showed that $\lceil \log_2(n+1) \rceil$ hidden layers are sufficient to compute all continuous piecewise linear (CPWL)…

Machine Learning · Computer Science 2026-02-23 Egor Bakaev , Florestan Brunck , Christoph Hertrich , Jack Stade , Amir Yehudayoff

Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Ruize He , Dongchen Han , Gao Huang

Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning. ReLU activation has been shown to mitigate the vanishing gradient issue, to encourage sparsity in the…

Machine Learning · Statistics 2021-10-14 Nicola Picchiotti , Marco Gori

Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as…

Hardware Architecture · Computer Science 2024-02-19 Christodoulos Peltekis , Kosmas Alexandridis , Giorgos Dimitrakopoulos

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…

Hardware Architecture · Computer Science 2024-07-12 Mohammed Elbtity , Peyton Chandarana , Ramtin Zand

Neural networks have shown state-of-the-art performances in various classification and regression tasks. Rectified linear units (ReLU) are often used as activation functions for the hidden layers in a neural network model. In this article,…

Machine Learning · Computer Science 2026-01-12 Shufei Ge , Shijia Wang , Lloyd Elliott

The expressive power of neural networks is important for understanding deep learning. Most existing works consider this problem from the view of the depth of a network. In this paper, we study how width affects the expressiveness of neural…

Machine Learning · Computer Science 2017-11-02 Zhou Lu , Hongming Pu , Feicheng Wang , Zhiqiang Hu , Liwei Wang

Neural networks (NN) can be divided into two broad categories, recurrent and non-recurrent. Both types of neural networks are popular and extensively studied, but they are often treated as distinct families of machine learning algorithms.…

Machine Learning · Computer Science 2024-04-02 Quincy Hershey , Randy Paffenroth , Harsh Pathak , Simon Tavener

Successive linear transforms followed by nonlinear "activation" functions can approximate nonlinear functions to arbitrary precision given sufficient layers. The number of necessary layers is dependent on, in part, by the nature of the…

Neural and Evolutionary Computing · Computer Science 2018-09-26 Andrei Nicolae

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one…

Machine Learning · Statistics 2019-10-22 Boris Hanin , David Rolnick

Pooling operations, which can be calculated at low cost and serve as a linear or nonlinear transfer function for data reduction, are found in almost every modern neural network. Countless modern approaches have already tackled replacing the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Wolfgang Fuhl , Enkelejda Kasneci

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

Computation and Language · Computer Science 2026-01-16 Guanxu Chen , Dongrui Liu , Jing Shao

With the rapid development of geometric deep learning techniques, many mesh-based convolutional operators have been proposed to bridge irregular mesh structures and popular backbone networks. In this paper, we show that while convolutions…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Qiujie Dong , Xiaoran Gong , Rui Xu , Zixiong Wang , Shuangmin Chen , Shiqing Xin , Changhe Tu , Wenping Wang

While Transformer-based pre-trained language models and their variants exhibit strong semantic representation capabilities, the question of comprehending the information gain derived from the additional components of PLMs remains an open…

Computation and Language · Computer Science 2024-01-04 Li Zhou , Wenyu Chen , Yong Cao , Dingyi Zeng , Wanlong Liu , Hong Qu