English
Related papers

Related papers: Encoding large information structures in linear al…

200 papers

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of…

Machine Learning · Statistics 2023-10-11 Nick Polson , Vadim Sokolov

Large scale dynamical systems (e.g. many nonlinear coupled differential equations) can often be summarized in terms of only a few state variables (a few equations), a trait that reduces complexity and facilitates exploration of behavioral…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

Computer Vision and Pattern Recognition · Computer Science 2016-05-10 Hailin Shi , Xiangyu Zhu , Zhen Lei , Shengcai Liao , Stan Z. Li

In this work we show that the classification performance of high-dimensional structural MRI data with only a small set of training examples is improved by the usage of dimension reduction methods. We assessed two different dimension…

Machine Learning · Computer Science 2015-05-27 Andreas Grünauer , Markus Vincze

A new statistical technique for constructing linear latent structure (LLS) models from available data, supported by well established theoretical results and an efficient algorithm, is presented. The method reduces the problem of estimating…

Statistics Theory · Mathematics 2007-06-13 I. Akushevich , M. Kovtun , A. I. Yashin , K. G. Manton

Traditionally it had been a problem that researchers did not have access to enough spatial data to answer pressing research questions or build compelling visualizations. Today, however, the problem is often that we have too much data.…

Machine Learning · Computer Science 2018-03-23 Geoff Boeing

Dimensionality reduction techniques play an essential role in data analytics, signal processing and machine learning. Dimensionality reduction is usually performed in a preprocessing stage that is separate from subsequent data analysis,…

Machine Learning · Computer Science 2016-12-21 Bo Yang , Xiao Fu , Nicholas D. Sidiropoulos

Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG,…

Computation and Language · Computer Science 2024-02-23 Younghun Lee , Sungchul Kim , Tong Yu , Ryan A. Rossi , Xiang Chen

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep…

Machine Learning · Computer Science 2016-07-06 Vishwajeet Singh , Killamsetti Ravi Kumar , K Eswaran

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

Computation and Language · Computer Science 2025-01-31 Mohamed Elfeki , Rui Liu , Chad Voegele

State-of-the-art approaches for clustering high-dimensional data utilize deep auto-encoder architectures. Many of these networks require a large number of parameters and suffer from a lack of interpretability, due to the black-box nature of…

Machine Learning · Computer Science 2022-02-28 Alexander Lin , Andrew H. Song , Demba Ba

Approaches to signal representation and coding theory have traditionally focused on how to best represent signals using parsimonious representations that incur the lowest possible distortion. Classical examples include linear and non-linear…

Information Theory · Computer Science 2015-12-25 Petros T Boufounos , Shantanu Rane , Hassan Mansour

Data compression has been widely applied in many data processing areas. Compression methods use variable-size codes with the shorter codes assigned to symbols or groups of symbols that appear in the data frequently. Fibonacci coding, as a…

Performance · Computer Science 2007-12-19 R. Baca , V. Snasel , J. Platos , M. Kratky , E. El-Qawasmeh

Network embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension -- small enough to be efficient and large enough to be…

Physics and Society · Physics 2021-06-22 Weiwei Gu , Aditya Tandon , Yong-Yeol Ahn , Filippo Radicchi

Linear computation coding is concerned with the compression of multidimensional linear functions, i.e. with reducing the computational effort of multiplying an arbitrary vector to an arbitrary, but known, constant matrix. This paper…

Information Theory · Computer Science 2025-07-02 Hans Rosenberger , Johanna S. Fröhlich , Ali Bereyhi , Ralf R. Müller

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

The encoding of solutions in black-box optimization is a delicate, handcrafted balance between expressiveness and domain knowledge -- between exploring a wide variety of solutions, and ensuring that those solutions are useful. Our main…

Neural and Evolutionary Computing · Computer Science 2020-07-07 Adam Gaier , Alexander Asteroth , Jean-Baptiste Mouret

The success of machine learning has resulted from its structured representation of data. Similar data have close internal representations as compressed codes for classification or emerged labels for clustering. We observe that the frequency…

Machine Learning · Computer Science 2022-04-13 Sungyeop Lee , Junghyo Jo

Our research demonstrates the significant benefits of using fine-tuning with explanations to enhance the performance of language models. Unlike prompting, which maintains the model's parameters, fine-tuning allows the model to learn and…

Computation and Language · Computer Science 2024-02-13 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kuehnberger

Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two…

Machine Learning · Statistics 2019-05-21 Ilya Feige