English
Related papers

Related papers: giMLPs: Gate with Inhibition Mechanism in MLPs

200 papers

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

Recent studies have demonstrated the effectiveness of Gated Linear Units (GLU) in enhancing transformer models, particularly in Large Language Models (LLMs). Additionally, utilizing a parallel configuration within each Transformer block…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Mahesh Ramesh , Aswinkumar Ramkumar

The attention mechanism has become a go-to technique for natural language processing and computer vision tasks. Recently, the MLP-Mixer and other MLP-based architectures, based simply on multi-layer perceptrons (MLPs), are also powerful…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Tian Lv , Chongyang Bai , Chaojie Wang

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there…

Image and Video Processing · Electrical Eng. & Systems 2022-04-05 Zhengzhong Tu , Hossein Talebi , Han Zhang , Feng Yang , Peyman Milanfar , Alan Bovik , Yinxiao Li

To the best of our knowledge, this is the first paper to introduce Convolutions to Gated MultiLayer Perceptron and contributes an implementation of this novel Deep Learning architecture. Google Brain introduced the gMLP in May 2021.…

Computer Vision and Pattern Recognition · Computer Science 2021-11-09 A. Rajagopal , V. Nirmala

Conventional neural networks strictly separate learning and inference because if parameters are updated during inference, outputs become unstable and even the inference function itself is not well defined [1, 2, 3]. This paper shows that…

Machine Learning · Computer Science 2026-04-16 Yongil Choi

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL tasks, including…

Machine Learning · Computer Science 2025-05-22 Ivan Smirnov , Shangding Gu

Gated Linear Units (GLUs) have become a common building block in modern foundation models. Bilinear layers drop the non-linearity in the "gate" but still have comparable performance to other GLUs. An attractive quality of bilinear layers is…

Machine Learning · Computer Science 2024-06-10 Michael T. Pearce , Thomas Dooms , Alice Rigg

We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the Information Bottleneck Language Modeling (IBLM) objective,…

Machine Learning · Computer Science 2025-10-23 Fangyuan Yu

This work explores optimizing transformer-based language models by integrating model compression techniques with inhibitor attention, a novel alternative attention mechanism. Inhibitor attention employs Manhattan distances and ReLU…

Computation and Language · Computer Science 2025-03-21 Tony Zhang , Rickard Brännvall

This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions. As compared to modern MLP architectures, e.g., MLP-Mixer, ResMLP, and gMLP, whose architectures are…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Shoufa Chen , Enze Xie , Chongjian Ge , Runjian Chen , Ding Liang , Ping Luo

In this work we revisit the most fundamental building block in deep learning, the multi-layer perceptron (MLP), and study the limits of its performance on vision tasks. Empirical insights into MLPs are important for multiple reasons. (1)…

Machine Learning · Computer Science 2023-10-04 Gregor Bachmann , Sotiris Anagnostidis , Thomas Hofmann

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

Dropout is a representative regularization technique that stochastically deactivates hidden units during training to mitigate overfitting. In contrast, standard inference executes the full network with dense computation, so its goal and…

Machine Learning · Computer Science 2026-03-18 Yong Il Choi

Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has explored two distinct…

Computation and Language · Computer Science 2025-03-07 Songlin Yang , Jan Kautz , Ali Hatamizadeh

Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance…

Machine Learning · Computer Science 2024-10-15 Sean Wu , Jordan Hong , Keyu Bai , Gregor Bachmann

A multilayer perceptron (MLP) is typically made of multiple fully connected layers with nonlinear activation functions. There have been several approaches to make them better (e.g. faster convergence, better convergence limit, etc.). But…

Machine Learning · Computer Science 2021-08-24 Taewoon Kim

There is an increasing interest in the application of deep learning architectures to tabular data. One of the state-of-the-art solutions is TabTransformer which incorporates an attention mechanism to better track relationships between…

Machine Learning · Computer Science 2022-01-04 Radostin Cholakov , Todor Kolev

In recent years, NLP practitioners have converged on the following practice: (i) import an off-the-shelf pretrained (masked) language model; (ii) append a multilayer perceptron atop the CLS token's hidden representation (with randomly…

Computation and Language · Computer Science 2023-12-07 Mrigank Raman , Pratyush Maini , J. Zico Kolter , Zachary C. Lipton , Danish Pruthi

Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT)…

Computation and Language · Computer Science 2025-10-28 Yan-Shuo Liang , Jia-Rui Chen , Wu-Jun Li
‹ Prev 1 2 3 10 Next ›