English
Related papers

Related papers: Weight-based Decomposition: A Case for Bilinear ML…

200 papers

Recently proposed Gated Linear Networks present a tractable nonlinear network architecture, and exhibit interesting capabilities such as learning with local error signals and reduced forgetting in sequential learning. In this work, we…

Machine Learning · Computer Science 2022-12-13 Qianyi Li , Haim Sompolinsky

Binary Neural Networks (BNNs) use 1-bit weights and activations to efficiently execute deep convolutional neural networks on edge devices. Nevertheless, the binarization of the first layer is conventionally excluded, as it leads to a large…

Machine Learning · Computer Science 2023-05-05 Lorenzo Vorabbi , Davide Maltoni , Stefano Santi

Today, it is more important than ever before for users to have trust in the models they use. As Machine Learning models fall under increased regulatory scrutiny and begin to see more applications in high-stakes situations, it becomes…

Machine Learning · Computer Science 2020-12-03 William Knauth

This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction. Our study suggests that different from convolutional neural networks (including the discriminator) where…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Jinglan Liu , Jiaxin Zhang , Yukun Ding , Xiaowei Xu , Meng Jiang , Yiyu Shi

Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models. Several prior works simplified these operations with look-up tables or integer computations, but such…

Machine Learning · Computer Science 2021-12-07 Joonsang Yu , Junki Park , Seongmin Park , Minsoo Kim , Sihwa Lee , Dong Hyun Lee , Jungwook Choi

In this paper, we introduce a deep learning-based decoder designed for concatenated coding schemes over a deletion/substitution channel. Specifically, we focus on serially concatenated codes, where the outer code is either a convolutional…

Information Theory · Computer Science 2024-10-15 E. Uras Kargı , Tolga M. Duman

Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs/LMMs into a reduced-dimension…

Machine Learning · Computer Science 2025-05-27 Toshiaki Koike-Akino , Xiangyu Chen , Jing Liu , Ye Wang , Pu , Wang , Matthew Brand

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…

Computation and Language · Computer Science 2026-02-10 Abir Harrasse , Florent Draye , Punya Syon Pandey , Zhijing Jin , Bernhard Schölkopf

Large language models (LLMs) are dominated by dense linear transformations, whose storage, memory and computational overheads hinder efficient adaptation and deployment while masking the functional impacts of structural simplification. Here…

Computation and Language · Computer Science 2026-05-26 Ying Lu , Peng-Fei Zhou , Qi-Xuan Fang , Pan Zhang , Shi-Ju Ran , Gang Su

Convolutional Neural Networks (CNNs) are models that are utilized extensively for the hierarchical extraction of features. Vision transformers (ViTs), through the use of a self-attention mechanism, have recently achieved superior modeling…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Ali Jamali , Swalpa Kumar Roy , Danfeng Hong , Peter M Atkinson , Pedram Ghamisi

Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretability literature focuses on providing semantic meaning to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Brenda Praggastis , Davis Brown , Carlos Ortiz Marrero , Emilie Purvine , Madelyn Shapiro , Bei Wang

Scaling laws can be understood from ground-up numerical analysis, where traditional function approximation theory can explain shifts in model architecture choices. GLU variants now dominate frontier LLMs and similar outer-product…

Machine Learning · Computer Science 2026-02-25 Alejandro Francisco Queiruga

This paper presents a novel unifying framework of bilinear LSTMs that can represent and utilize the nonlinear interaction of the input features present in sequence datasets for achieving superior performance over a linear LSTM and yet not…

Machine Learning · Computer Science 2023-09-12 Mohit Rajpal , Bryan Kian Hsiang Low

Digital twins of complex physical systems are expected to infer unobserved states from sparse measurements and predict their evolution in time, yet these two functions are typically treated as separate tasks. Here we present GLU, a…

Machine Learning · Computer Science 2026-03-30 Linzheng Wang , Jason Chen , Nicolas Tricard , Zituo Chen , Sili Deng

In recent times, the research on Large Language Models (LLMs) has grown exponentially, predominantly focusing on models underpinned by the transformer architecture, as established by [1], and further developed through the decoder-only…

Machine Learning · Computer Science 2024-10-10 Sathya Krishnan Suresh , Shunmugapriya P

In the machine learning fields, Recurrent Neural Network (RNN) has become a popular architecture for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and…

Machine Learning · Computer Science 2018-05-09 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

We propose a ``half'' layer of hidden units that has some of its weights randomly set and some of them trained. A half unit is composed of two stages: First, it takes a weighted sum of its inputs with fixed random weights, and second, the…

Machine Learning · Computer Science 2025-06-06 Ethem Alpaydin

The logarithmic running of the gauge couplings alpha_1, alpha_2 and alpha_3, indicates that they may unify at some scale M_GUT ~ 10^16. This is often taken to imply that the standard model gauge group is embedded into some larger simple…

High Energy Physics - Phenomenology · Physics 2007-05-23 Neal Weiner

This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the curse of dimensionality and allow for a compact…

Machine Learning · Computer Science 2022-02-21 Adam Celarek , Pedro Hermosilla , Bernhard Kerbl , Timo Ropinski , Michael Wimmer

Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods learn interpretable approximations via neuron-level sparsity,…

Machine Learning · Computer Science 2026-01-15 James Oldfield , Shawn Im , Sharon Li , Mihalis A. Nicolaou , Ioannis Patras , Grigorios G Chrysos