English
Related papers

Related papers: Negative Pre-activations Differentiate Syntax

200 papers

The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models. There are several commonly used simple nonlinear functions, including Rectified Linear Unit (ReLU) and Leaky-ReLU…

Machine Learning · Computer Science 2020-10-16 Nalinda Kulathunga , Nishath Rajiv Ranasinghe , Daniel Vrinceanu , Zackary Kinsman , Lei Huang , Yunjiao Wang

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Computation and Language · Computer Science 2021-07-02 Dong Wang , Ning Ding , Piji Li , Hai-Tao Zheng

Empirical works show that for ReLU neural networks (NNs) with small initialization, input weights of hidden neurons (the input weight of a hidden neuron consists of the weight from its input layer to the hidden neuron and its bias term)…

Machine Learning · Computer Science 2022-10-20 Hanxu Zhou , Qixuan Zhou , Tao Luo , Yaoyu Zhang , Zhi-Qin John Xu

Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process incoming signals for them. They are essential for learning…

Machine Learning · Computer Science 2023-08-31 Jianfei Li , Han Feng , Ding-Xuan Zhou

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Fabio Cermelli , Massimiliano Mancini , Samuel Rota Buló , Elisa Ricci , Barbara Caputo

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear…

Machine Learning · Computer Science 2015-11-30 Bing Xu , Naiyan Wang , Tianqi Chen , Mu Li

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid towards individual neurons.We carry outa neuron-level analysis…

Computation and Language · Computer Science 2020-10-07 Nadir Durrani , Hassan Sajjad , Fahim Dalvi , Yonatan Belinkov

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

Computation and Language · Computer Science 2024-01-17 Nadir Durrani , Fahim Dalvi , Hassan Sajjad

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU),…

Machine Learning · Computer Science 2021-04-07 Anh Nguyen , Khoa Pham , Dat Ngo , Thanh Ngo , Lam Pham

An activation function has a significant impact on the efficiency and robustness of the neural networks. As an alternative, we evolved a cutting-edge non-monotonic activation function, Negative Stimulated Hybrid Activation Function (Nish).…

Machine Learning · Computer Science 2022-12-20 Yildiray Anagun , Sahin Isik

Leveraging sparsity is crucial for optimizing large language model inference. however, modern LLMs employing SiLU as their activation function exhibit minimal activation sparsity. Recent research has proposed replacing SiLU with ReLU to…

Performance · Computer Science 2025-01-27 Jiho Shin , Hoeseok Yang , Youngmin Yi

We present GLUScope, an open-source tool for analyzing neurons in Transformer-based language models, intended for interpretability researchers. We focus on more recent models than previous tools do; specifically we consider gated activation…

Computation and Language · Computer Science 2026-03-02 Sebastian Gerstner , Hinrich Schütze

Large pre-trained language models (PLMs) have shown remarkable performance across various natural language understanding (NLU) tasks, particularly in low-resource settings. Nevertheless, their potential in Automatic Speech Recognition (ASR)…

Computation and Language · Computer Science 2023-06-13 Aravind Krishnan , Jesujoba Alabi , Dietrich Klakow

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than modern piecewise-linear and smooth activations such as ELU, LeakyReLU, LogSigmoid, PReLU,…

Machine Learning · Computer Science 2026-02-16 Maosen Tang , Alex Townsend

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Computation and Language · Computer Science 2019-08-29 Zi-Yi Dou , Keyi Yu , Antonios Anastasopoulos

Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progress w.r.t. the mean Intersection-over Union (mIoU) with the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Xiaofeng Liu , Yimeng Zhang , Xiongchang Liu , Song Bai , Site Li , Jane You

Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS are determined by…

Machine Learning · Statistics 2020-02-25 D. Kafka , Daniel. N. Wilke

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

Machine Learning · Computer Science 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio