English
Related papers

Related papers: Reducing numerical precision preserves classificat…

200 papers

Supervised learning algorithms generally assume the availability of enough memory to store their data model during the training and test phases. However, in the Internet of Things, this assumption is unrealistic when data comes in the form…

Machine Learning · Computer Science 2023-08-07 Martin Khannouz , Tristan Glatard

This paper presents the analysis of the impact of a floating-point number precision reduction on the quality of text classification. The precision reduction of the vectors representing the data (e.g. TF-IDF representation in our case)…

Computation and Language · Computer Science 2017-06-21 Krzysztof Wróbel , Maciej Wielgosz , Marcin Pietroń , Michał Karwatowski , Aleksander Smywiński-Pohl

Supervised learning algorithms generally assume the availability of enough memory to store data models during the training and test phases. However, this assumption is unrealistic when data comes in the form of infinite data streams, or…

Machine Learning · Computer Science 2022-10-13 Martin Khannouz , Tristan Glatard

In many machine learning applications, e.g., tree-based ensembles, floating point numbers are extensively utilized due to their expressiveness. Nowadays performing data analysis on embedded devices from dynamic data masses becomes…

Machine Learning · Computer Science 2022-09-12 Christian Hakert , Kuan-Hsun Chen , Jian-Jia Chen

Emerging continual learning applications necessitate next-generation neural processing unit (NPU) platforms to support both training and inference operations. The promising Microscaling (MX) standard enables narrow bit-widths for inference…

Hardware Architecture · Computer Science 2026-03-13 Stef Cuyckens , Xiaoling Yi , Robin Geens , Joren Dumoulin , Martin Wiesner , Chao Fang , Marian Verhelst

Introduced by Breiman, Random Forests are widely used classification and regression algorithms. While being initially designed as batch algorithms, several variants have been proposed to handle online learning. One particular instance of…

Machine Learning · Statistics 2019-04-10 Jaouad Mourtada , Stéphane Gaïffas , Erwan Scornet

This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. More specifically, this study considers networks where each layer may use different precision…

Convolutional neural networks (CNNs) achieve state-of-the-art performance at the cost of becoming deeper and larger. Although quantization (both fixed-point and floating-point) has proven effective for reducing storage and memory access,…

Signal Processing · Electrical Eng. & Systems 2020-03-06 Chen Wu , Mingyu Wang , Xiayu Li , Jicheng Lu , Kun Wang , Lei He

Traditional optimization methods rely on the use of single-precision floating point arithmetic, which can be costly in terms of memory size and computing power. However, mixed precision optimization techniques leverage the use of both…

Machine Learning · Computer Science 2023-09-25 Basile Lewandowski , Atli Kosson

Ensembles of randomized decision trees, usually referred to as random forests, are widely used for classification and regression tasks in machine learning and statistics. Random forests achieve competitive predictive performance and are…

Machine Learning · Statistics 2015-02-17 Balaji Lakshminarayanan , Daniel M. Roy , Yee Whye Teh

When training deep neural networks, keeping all tensors in high precision (e.g., 32-bit or even 16-bit floats) is often wasteful. However, keeping all tensors in low precision (e.g., 8-bit floats) can lead to unacceptable accuracy loss.…

Machine Learning · Computer Science 2023-06-26 Wonyeol Lee , Rahul Sharma , Alex Aiken

Machine learning has an emerging critical role in high-performance computing to modulate simulations, extract knowledge from massive data, and replace numerical models with efficient approximations. Decision forests are a critical tool…

Performance · Computer Science 2018-06-22 James Browne , Tyler M. Tomita , Disa Mhembere , Randal Burns , Joshua T. Vogelstein

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of…

Machine Learning · Computer Science 2018-04-17 Marc Ortiz , Adrián Cristal , Eduard Ayguadé , Marc Casas

This report is concerned with the Mondrian process and its applications in machine learning. The Mondrian process is a guillotine-partition-valued stochastic process that possesses an elegant self-consistency property. The first part of the…

Machine Learning · Statistics 2015-07-21 Matej Balog , Yee Whye Teh

In modern low-power embedded platforms, floating-point (FP) operations emerge as a major contributor to the energy consumption of compute-intensive applications with large dynamic range. Experimental evidence shows that 50% of the energy…

Hardware Architecture · Computer Science 2017-11-29 Giuseppe Tagliavini , Stefan Mach , Davide Rossi , Andrea Marongiu , Luca Benini

With the increasing complexity of machine learning models, managing computational resources like memory and processing power has become a critical concern. Mixed precision techniques, which leverage different numerical precisions during…

Machine Learning · Computer Science 2026-04-20 Juyoung Yun , Sol Choi , Francois Rameau , Byungkon Kang , Zhoulai Fu

The global optimization of classification trees has demonstrated considerable promise, notably in enhancing accuracy, optimizing size, and thereby improving human comprehensibility. While existing optimal classification trees substantially…

Machine Learning · Computer Science 2024-02-01 Jiancheng Tu , Wenqi Fan , Zhibin Wu

Besides serving as prediction models, classification trees are useful for finding important predictor variables and identifying interesting subgroups in the data. These functions can be compromised by weak split selection algorithms that…

Applications · Statistics 2010-11-03 Wei-Yin Loh

Database research can help machine learning performance in many ways. One way is to design better data structures. This paper combines the use of incremental computation and sequential and probabilistic filtering to enable "forgetful"…

Machine Learning · Computer Science 2022-12-16 Zhehu Yuan , Yinqi Sun , Dennis Shasha

The typical processors used for scientific computing have fixed-width data-paths. This implies that mathematical libraries were specifically developed to target each of these fixed precisions (binary16, binary32, binary64). However, to…

Mathematical Software · Computer Science 2020-05-07 David Defour , Pablo de Oliveira Castro , Matei Istoan , Eric Petit
‹ Prev 1 2 3 10 Next ›