English
Related papers

Related papers: Measuring Arithmetic Extrapolation Performance

200 papers

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee

Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We…

The activation function is at the heart of a deep neural networks nonlinearity; the choice of the function has great impact on the success of training. Currently, many practitioners prefer the Rectified Linear Unit (ReLU) due to its…

Machine Learning · Computer Science 2021-08-24 Jordan Inturrisi , Sui Yang Khoo , Abbas Kouzani , Riccardo Pagliarella

For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients,…

Machine Learning · Computer Science 2021-06-10 George Philipp , Jaime G. Carbonell

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang

A well-calibrated neural model produces confidence (probability outputs) closely approximated by the expected accuracy. While prior studies have shown that mixup training as a data augmentation technique can improve model calibration on…

Computation and Language · Computer Science 2022-03-16 Seo Yeon Park , Cornelia Caragea

Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly,…

Artificial Intelligence · Computer Science 2026-01-27 Taiqiang Wu , Runming Yang , Tao Liu , Jiahao Wang , Ngai Wong

Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on…

Machine Learning · Computer Science 2019-08-27 Yang Liu , Jianpeng Zhang , Chao Gao , Jinghua Qu , Lixin Ji

Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in "dying ReLU units" with near-zero outputs. We first explore…

Machine Learning · Computer Science 2018-12-17 Scott C. Douglas , Jiutian Yu

Adversarial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. While being critical, we argue that solving this singular issue alone fails to provide a comprehensive…

Machine Learning · Computer Science 2021-03-02 Yu-Lin Tsai , Chia-Yi Hsu , Chia-Mu Yu , Pin-Yu Chen

Joint intent detection and slot filling, which is also termed as joint NLU (Natural Language Understanding) is invaluable for smart voice assistants. Recent advancements in this area have been heavily focusing on improving accuracy using…

Machine Learning · Computer Science 2023-09-27 Kalpa Gunaratna , Vijay Srinivasan , Hongxia Jin

Neural networks have been widely used to solve complex real-world problems. Due to the complicate, nonlinear, non-convex nature of neural networks, formal safety guarantees for the output behaviors of neural networks will be crucial for…

Machine Learning · Computer Science 2017-12-25 Weiming Xiang , Hoang-Dung Tran , Taylor T. Johnson

In the present paper, we consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks, so that the structure is determined by the number and types of neurons. The determination of the…

We prove several hardness results for training depth-2 neural networks with the ReLU activation function; these networks are simply weighted sums (that may include negative coefficients) of ReLUs. Our goal is to output a depth-2 neural…

Machine Learning · Computer Science 2020-11-30 Surbhi Goel , Adam Klivans , Pasin Manurangsi , Daniel Reichman

Assessing the complexity of functions computed by a neural network helps us understand how the network will learn and generalize. One natural measure of complexity is how the network distorts length - if the network takes a unit-length…

Machine Learning · Statistics 2021-06-24 Boris Hanin , Ryan Jeong , David Rolnick

We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models,…

Machine Learning · Computer Science 2024-11-28 Alan Oursland

Logs are extensively used during the development and maintenance of software systems. They collect runtime events and allow tracking of code execution, which enables a variety of critical tasks such as troubleshooting and fault detection.…

Machine Learning · Computer Science 2020-03-20 Sasho Nedelkoski , Jasmin Bogatinovski , Alexander Acker , Jorge Cardoso , Odej Kao

We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix. We measure this…

Machine Learning · Computer Science 2018-10-09 Edo Collins , Siavash Arjomand Bigdeli , Sabine Süsstrunk

This paper demonstrates that a single-layer neural network using Parametric Rectified Linear Unit (PReLU) activation can solve the XOR problem, a simple fact that has been overlooked so far. We compare this solution to the multi-layer…

Neural and Evolutionary Computing · Computer Science 2024-09-18 Rafael C. Pinto , Anderson R. Tavares

Despite the remarkable success of Transformer-based large language models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a significant challenge. In this paper, we conduct a rigorous…

Machine Learning · Computer Science 2025-06-24 Guhao Feng , Kai Yang , Yuntian Gu , Xinyue Ai , Shengjie Luo , Jiacheng Sun , Di He , Zhenguo Li , Liwei Wang