English
Related papers

Related papers: Theano: new features and speed improvements

200 papers

Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide…

Hardware Architecture · Computer Science 2024-06-13 Nandeeka Nayak , Toluwanimi O. Odemuyiwa , Shubham Ugare , Christopher W. Fletcher , Michael Pellauer , Joel S. Emer

Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to compress these models, the lack of a unified,…

Machine Learning · Computer Science 2026-01-23 Fahd Seddik , Abdulrahman Elbedewy , Gaser Sami , Mohamed Abdelmoniem , Yahia Zakaria

Neural networks are increasingly deployed in scientific, safety critical, and mission critical pipelines, yet verification and analysis are often performed outside the programming environment that defines and runs the model. This creates a…

Mathematical Software · Computer Science 2026-05-26 Robert Joseph George , Jennifer Cruden , Will Adkisson , Xiangru Zhong , Huan Zhang , Anima Anandkumar

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet…

Machine Learning · Computer Science 2018-09-05 Eunji Jeong , Joo Seong Jeong , Soojeong Kim , Gyeong-In Yu , Byung-Gon Chun

In this paper, we tackle the problem of automatically generating algorithms for linear algebra operations by taking advantage of problem-specific knowledge. In most situations, users possess much more information about the problem at hand…

Mathematical Software · Computer Science 2012-11-27 Diego Fabregat-Traver , Paolo Bientinesi

Convolutional Neural Networks (CNNs) are used for a wide range of image-related tasks such as image classification and object detection. However, a large pre-trained CNN model contains a lot of redundancy considering the task-specific edge…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-09 Zhuwei Qin , Fuxun Yu , Xiang Chen

In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, ``classical'' federated learning…

Machine Learning · Computer Science 2023-11-27 Louis Leconte , Van Minh Nguyen , Eric Moulines

This paper considers the development of an AI-based provably-correct mathematical proof tutor. While Large Language Models (LLMs) allow seamless communication in natural language, they are error prone. Theorem provers such as Lean allow for…

Machine Learning · Computer Science 2026-03-05 Manooshree Patel , Rayna Bhattacharyya , Thomas Lu , Arnav Mehta , Niels Voss , Narges Norouzi , Gireeja Ranade

This paper considers the development of an AI-based provably-correct mathematical proof tutor. While Large Language Models (LLMs) allow seamless communication in natural language, they are error prone. Theorem provers such as Lean allow for…

Artificial Intelligence · Computer Science 2026-03-05 Manooshree Patel , Rayna Bhattacharyya , Thomas Lu , Arnav Mehta , Niels Voss , Narges Norouzi , Gireeja Ranade

Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. This is in contrast with Deep Neural Networks (DNNs), which use multiply-accumulate operations. State-of-the-art WNN…

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile…

Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of…

Computation and Language · Computer Science 2024-11-26 Jiayi Chen , Chen Wu , Shaoqun Zhang , Nan Li , Liangjie Zhang , Qi Zhang

Modern transformer-based deep neural networks present unique technical challenges for effective acceleration in real-world applications. Apart from the vast amount of linear operations needed due to their sizes, modern transformer models…

Hardware Architecture · Computer Science 2024-11-07 Jiajun Wu , Mo Song , Jingmin Zhao , Yizhao Gao , Jia Li , Hayden Kwok-Hay So

Recently, data-driven approaches motivated by modern deep learning have been applied to optical communications in place of traditional model-based counterparts. The application of deep neural networks (DNN) allows flexible statistical…

Signal Processing · Electrical Eng. & Systems 2019-11-25 Toshiaki Koike-Akino , Ye Wang , David S. Millar , Keisuke Kojima , Kieran Parsons

Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in…

Machine Learning · Computer Science 2025-08-14 Alessandro Pierro , Steven Abreu , Jonathan Timcheck , Philipp Stratmann , Andreas Wild , Sumit Bam Shrestha

Transformer neural networks (TNN) excel in natural language processing (NLP), machine translation, and computer vision (CV) without relying on recurrent or convolutional layers. However, they have high computational and memory demands,…

Hardware Architecture · Computer Science 2025-12-30 Ehsan Kabir , Jason D. Bakos , David Andrews , Miaoqing Huang

Presolving has become an essential component of modern MIP solvers both in terms of computational performance and numerical robustness. In this paper, we present PaPILO, a new C++ header-only library that provides a large set of presolving…

Optimization and Control · Mathematics 2024-03-21 Ambros Gleixner , Leona Gottwald , Alexander Hoen

With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands.…

Hardware Architecture · Computer Science 2025-10-22 Ye Qiao , Zhiheng Chen , Yifan Zhang , Yian Wang , Sitao Huang

In this report, we describe a Theano-based AlexNet (Krizhevsky et al., 2012) implementation and its naive data parallelism on multiple GPUs. Our performance on 2 GPUs is comparable with the state-of-art Caffe library (Jia et al., 2014) run…

Machine Learning · Computer Science 2015-04-08 Weiguang Ding , Ruoyan Wang , Fei Mao , Graham Taylor

This paper introduces HyperNOs, a PyTorch library designed to streamline and automate the process of exploring neural operators, with a special focus on hyperparameter optimization for comprehensive and exhaustive exploration. Indeed,…

Machine Learning · Computer Science 2026-02-09 Massimiliano Ghiotto
‹ Prev 1 3 4 5 6 7 10 Next ›