Results 1 to 10 of about 1,046,535 (320)
The arithmetic of arithmetic Coxeter groups [PDF]
Proceedings of the National Academy of Sciences, 2018 In the 1990s, J.H. Conway published a combinatorial-geometric method for analyzing integer-valued binary quadratic forms (BQFs). Using a visualization he named the "topograph," Conway revisited the reduction of BQFs and the solution of quadratic ...
Milea, Suzana +2 more
core +5 more sources
The Arithmetic Optimization Algorithm
Computer Methods in Applied Mechanics and Engineering, 2021 This work proposes a new meta-heuristic method called Arithmetic Optimization Algorithm (AOA) that utilizes the distribution behavior of the main arithmetic operators in mathematics including (Multiplication ( M ), Division ( D ), Subtraction ( S ), and ...
Ali H Diabat +2 more
exaly +2 more sources
Solving General Arithmetic Word Problems [PDF]
Conference on Empirical Methods in Natural Language Processing, 2015 This paper presents a novel approach to automatically solving arithmetic word problems. This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or ...
Roth, Dan, Roy, Subhro
core +3 more sources
, 2002 This survey paper is aimed to describe a relatively new branch of symbolic dynamics which we call Arithmetic Dynamics. It deals with explicit arithmetic expansions of reals and vectors that have a "dynamical" sense. This means precisely that they (semi-)
Sidorov, Nikita
core +4 more sources
Editing Models with Task Arithmetic [PDF]
International Conference on Learning Representations, 2022 Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems.
Gabriel Ilharco +6 more
semanticscholar +1 more source
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models [PDF]
Neural Information Processing Systems, 2023 Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks, while ...
Guillermo Ortiz-Jiménez +2 more
semanticscholar +1 more source
Composing Parameter-Efficient Modules with Arithmetic Operations [PDF]
Neural Information Processing Systems, 2023 As an efficient alternative to conventional full finetuning, parameter-efficient finetuning (PEFT) is becoming the prevailing method to adapt pretrained language models.
Jinghan Zhang +3 more
semanticscholar +1 more source
How well do Large Language Models perform in Arithmetic tasks? [PDF]
arXiv.org, 2023 Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic ...
Zheng Yuan +4 more
semanticscholar +1 more source
Teaching Arithmetic to Small Transformers [PDF]
arXiv.org, 2023 Large language models like GPT-4 exhibit emergent capabilities across general-purpose tasks, such as basic arithmetic, when trained on extensive text data, even though these tasks are not explicitly encoded by the unsupervised, next-token prediction ...
Nayoung Lee +4 more
semanticscholar +1 more source
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes.
Benoit Jacob +7 more
semanticscholar +1 more source