English
Related papers

Related papers: Transformers are Bayesian Networks

200 papers

Transformer models bring propelling advances in various NLP tasks, thus inducing lots of interpretability research on the learned representations of the models. However, we raise a fundamental question regarding the reliability of the…

Computation and Language · Computer Science 2023-05-25 Yuxin Ren , Qipeng Guo , Zhijing Jin , Shauli Ravfogel , Mrinmaya Sachan , Bernhard Schölkopf , Ryan Cotterell

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

Machine Learning · Computer Science 2022-04-28 Anwesh Bhattacharya , Marios Mattheakis , Pavlos Protopapas

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural language understanding…

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Computation and Language · Computer Science 2023-02-23 Mohammad Akbar-Tajari , Sara Rajaee , Mohammad Taher Pilehvar

Belief networks represent a powerful approach to problems involving probabilistic inference, but much of the work in this area is software based utilizing standard deterministic hardware based on the transistor which provides the gain and…

Mesoscale and Nanoscale Physics · Physics 2016-07-26 Behtash Behin-Aein , Vinh Diep , Supriyo Datta

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…

Machine Learning · Computer Science 2026-02-25 Wei Wang , Xiao-Yong Wei , Qing Li

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Machine Learning · Computer Science 2025-06-03 Yifan Hao , Chenlu Ye , Chi Han , Tong Zhang

With Artificial Intelligence (AI) increasingly permeating various aspects of society, including healthcare, the adoption of the Transformers neural network architecture is rapidly changing many applications. Transformer is a type of deep…

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

The recent success of Vision Transformers is shaking the long dominance of Convolutional Neural Networks (CNNs) in image recognition for a decade. Specifically, in terms of robustness on out-of-distribution samples, recent research finds…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Zeyu Wang , Yutong Bai , Yuyin Zhou , Cihang Xie

Bayesian network is a complete model for the variables and their relationships, it can be used to answer probabilistic queries about them. A Bayesian network can thus be considered a mechanism for automatically applying Bayes' theorem to…

Artificial Intelligence · Computer Science 2010-11-08 Jianguo Ding

Robotic manipulation can be formulated as inducing a sequence of spatial displacements: where the space being moved can encompass an object, part of an object, or end effector. In this work, we propose the Transporter Network, a simple…

Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only partially understood. Contemporary research has largely…

Machine Learning · Computer Science 2025-06-02 Sagar Ghosh , Kushal Bose , Swagatam Das

Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions. In this note, we revisit their coupling and autoregressive transformation layers as probabilistic graphical…

Machine Learning · Computer Science 2020-06-05 Antoine Wehenkel , Gilles Louppe

The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these capabilities, Sanford et al. proposed the sparse token…

Machine Learning · Statistics 2024-06-12 Zixuan Wang , Stanley Wei , Daniel Hsu , Jason D. Lee

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes…

Computation and Language · Computer Science 2023-11-30 Tong Xiao , Jingbo Zhu

Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our understanding of how the new architecture works is still…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Juyeop Kim , Junha Park , Songkuk Kim , Jong-Seok Lee

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Dharma KC , Venkata Ravi Kiran Dayana , Meng-Lin Wu , Venkateswara Rao Cherukuri , Hau Hwang

Faithfulness is a common assumption in causal inference, often motivated by the fact that the faithful parameters of linear Gaussian and discrete Bayesian networks are typical, and the folklore belief that this should also hold for other…

Statistics Theory · Mathematics 2026-03-13 Philip Boeken , Patrick Forré , Joris M. Mooij
‹ Prev 1 4 5 6 7 8 10 Next ›