English
Related papers

Related papers: Investigating the Role of Feed-Forward Networks in…

200 papers

Decoder-only transformer networks have become incredibly popular for language modeling tasks. State-of-the-art models can have over a hundred transformer blocks, containing billions of trainable parameters, and are trained on trillions of…

Computation and Language · Computer Science 2025-05-13 Isaac Gerber

The Transformer architecture has two main non-embedding components: Attention and the Feed Forward Network (FFN). Attention captures interdependencies between words regardless of their position, while the FFN non-linearly transforms each…

Computation and Language · Computer Science 2023-10-24 Telmo Pessoa Pires , António V. Lopes , Yannick Assogba , Hendra Setiawan

Transformers are ubiquitous in wide tasks. Interpreting their internals is a pivotal goal. Nevertheless, their particular components, feed-forward (FF) blocks, have typically been less analyzed despite their substantial parameter amounts.…

Computation and Language · Computer Science 2024-04-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

Transformers have achieved remarkable success across diverse domains, but their monolithic architecture presents challenges in interpretability, adaptability, and scalability. This paper introduces a novel modular Transformer architecture…

Machine Learning · Computer Science 2025-01-07 Zhenyu Guo , Wenguang Chen

This study investigates the layerwise importance of feed-forward networks (FFNs) in Transformer-based language models during pretraining. We introduce an experimental approach that, while maintaining the total parameter count, increases the…

Computation and Language · Computer Science 2025-08-26 Wataru Ikeda , Kazuki Yano , Ryosuke Takahashi , Jaesung Lee , Keigo Shibata , Jun Suzuki

Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Cong Wang , Jinshan Pan , Yeying Jin , Liyan Wang , Wei Wang , Gang Fu , Wenqi Ren , Xiaochun Cao

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and…

Transformer, composed of self-attention and Feed-Forward Network, has revolutionized the landscape of network design across various vision tasks. While self-attention is extensively explored as a key factor in performance, FFN has received…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Seokju Yun , Dongheon Lee , Youngmin Ro

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where…

Computation and Language · Computer Science 2021-09-07 Mor Geva , Roei Schuster , Jonathan Berant , Omer Levy

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…

Machine Learning · Computer Science 2025-12-09 Minshen Zhang , Xiang Hu , Jianguo Li , Wei Wu , Kewei Tu

Transformer is an attention-based neural network, which consists of two sublayers, namely, Self-Attention Network (SAN) and Feed-Forward Network (FFN). Existing research explores to enhance the two sublayers separately to improve the…

Computation and Language · Computer Science 2021-03-26 Zhihao Fan , Yeyun Gong , Dayiheng Liu , Zhongyu Wei , Siyuan Wang , Jian Jiao , Nan Duan , Ruofei Zhang , Xuanjing Huang

Transformers are widely used in state-of-the-art machine translation, but the key to their success is still unknown. To gain insight into this, we consider three groups of parameters: embeddings, attention, and feed forward neural network…

Computation and Language · Computer Science 2021-09-22 Nikolay Bogoychev

Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance…

Machine Learning · Statistics 2026-05-27 Gyeonghun Kang , Changwoo J. Lee , Xiang Cheng

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-29 Shucong Zhang , Erfan Loweimi , Peter Bell , Steve Renals

The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge. In this work, we conduct an empirical ablation study on updating keys (the 1st layer in the…

Computation and Language · Computer Science 2024-02-20 Zihan Qiu , Zeyu Huang , Youcheng Huang , Jie Fu

Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in…

Machine Learning · Computer Science 2025-11-13 Freya Behrens , Luca Biggio , Lenka Zdeborová

In this work we provide new insights into the transformer architecture, and in particular, its best-known variant, BERT. First, we propose a method to measure the degree of non-linearity of different elements of transformers. Next, we focus…

Computation and Language · Computer Science 2021-05-10 Sumu Zhao , Damian Pascual , Gino Brunner , Roger Wattenhofer
‹ Prev 1 2 3 10 Next ›