English
Related papers

Related papers: What's Hidden in a One-layer Randomly Weighted Tra…

200 papers

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Learning deeper models is usually a simple and effective approach to improve model performance, but deeper models have larger model parameters and are more difficult to train. To get a deeper model, simply stacking more layers of the model…

Computation and Language · Computer Science 2021-08-27 GuoLiang Li , Yiyang Li

Human intelligence relies in part on our brains' ability to create abstract mental models that succinctly capture the hidden blueprint of our reality. Such abstract world models notably allow us to rapidly navigate novel situations by…

Artificial Intelligence · Computer Science 2023-12-12 Quentin RV. Ferry , Joshua Ching , Takashi Kawai

Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements.…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Reinhard Heckel , Paul Hand

The topology of many real complex networks has been conjectured to be embedded in hidden metric spaces, where distances between nodes encode their likelihood of being connected. Besides of providing a natural geometrical interpretation of…

Physics and Society · Physics 2017-01-23 Antoine Allard , M. Ángeles Serrano , Guillermo García-Pérez , Marián Boguñá

We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of the hidden layers. We show that a set of optimal hidden layer weights for a norm regularized DNN training problem…

Machine Learning · Computer Science 2021-06-14 Tolga Ergen , Mert Pilanci

Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2016-08-29 Xing Wang , Jie Liang

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as…

Machine Learning · Computer Science 2017-09-25 Liang Zhao , Siyu Liao , Yanzhi Wang , Zhe Li , Jian Tang , Victor Pan , Bo Yuan

Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition accuracy (arXiv:2003.07705 [eess.AS],…

Computation and Language · Computer Science 2021-09-17 Rami Botros , Tara N. Sainath , Robert David , Emmanuel Guzman , Wei Li , Yanzhang He

In contrast to traditional weight optimization in a continuous space, we demonstrate the existence of effective random networks whose weights are never updated. By selecting a weight among a fixed set of random values for each individual…

Machine Learning · Computer Science 2021-06-09 Maxwell Mbabilla Aladago , Lorenzo Torresani

According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the…

Neural and Evolutionary Computing · Computer Science 2024-11-08 Philipp Altmann , Julian Schönberger , Maximilian Zorn , Thomas Gabor

There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network $\textit{one layer at a time}$ with only a "single forward pass"…

Machine Learning · Statistics 2022-02-10 Chieh Wu , Aria Masoomi , Arthur Gretton , Jennifer Dy

This paper introduces a new learning paradigm termed Neural Metamorphosis (NeuMeta), which aims to build self-morphable neural networks. Contrary to crafting separate models for different architectures or sizes, NeuMeta directly learns the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Xingyi Yang , Xinchao Wang

Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both…

Computation and Language · Computer Science 2023-11-30 Xiaohui Chen , Yinkai Wang , Yuanqi Du , Soha Hassoun , Li-Ping Liu

Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation. While the Transformer model has achieved significant improvements for many language pairs and has…

Computation and Language · Computer Science 2020-11-05 Ali Araabi , Christof Monz

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…

Machine Learning · Computer Science 2023-05-19 Fuzhao Xue , Jianghai Chen , Aixin Sun , Xiaozhe Ren , Zangwei Zheng , Xiaoxin He , Yongming Chen , Xin Jiang , Yang You

Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression…

Machine Learning · Computer Science 2025-05-27 Safa Hamreras , Sukhbinder Singh , Román Orús

We introduce an algorithm where the individual bits representing the weights of a neural network are learned. This method allows training weights with integer values on arbitrary bit-depths and naturally uncovers sparse networks, without…

Machine Learning · Computer Science 2022-02-22 Cristian Ivan

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu