paper-with-me

Papers

Deriving Activation Functions Using Integration

2024-11-20 · Allen Hao Huang, Imanol Schlag

Our work proposes a novel approach to designing activation functions by focusing on their gradients and deriving the corresponding activation functions using integration. We introduce the Expanded Integral of the Exponential Linear Unit (xIELU), a trainable piecewise activation function derived by integrating trainable affine transformations applied to the Exponential Linear Unit (ELU). xIELU combines two key properties for the gradient: (1) a trainable and linearly increasing gradient for positive inputs, similar to Squared ReLU (ReLU$^2$), and (2) a trainable gradient that can take negative values for negative inputs, inspired by Expanded SiLU (xSiLU). Conceptually, xIELU can be viewed as an extension of ReLU$^2$ to handle negative inputs. The trainable parameters in xIELU allow it to adaptively reduce its nonlinearity for higher-level representations deeper in the network. In experiments with 1.1B and 3B parameter Llama models trained on 125B tokens of FineWeb Edu, xIELU achieves lower perplexity compared to popular activation functions like ReLU$^2$ and SwiGLU when matched for the same compute cost and parameter count. A reference implementation is available at https://github.com/Anonymous5823/xielu.

📄 PDF Abstract BibTeX arXiv:2411.13010

Code (1)

anonymous5823/xielu 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
SiLU Sigmoid Linear Units, or SiLUs, are activation functions for neural networks. The activation of the SiLU is computed by the sigmoid function multiplied by its input, or…
Squared ReLU Squared ReLU is an activation function used in the Primer architecture in the feedforward block of the…
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…
ELU 설명 없음
SwiGLU SwiGLU is an activation function which is a variant of GLU. The definition is as follows: $$ \text{SwiGLU}\left(x, W, V, b, c,…

Similar Papers 제목 키워드 기반

Formalising the Use of the Activation Function in Neural Inference

2021-02-02 · Dalton A R Sakthivadivel

We investigate how the activation function can be used to describe neural firing in an abstract way, and in turn, why it works well in artificial neural networks. We discuss how a spike in a biological neurone belongs to…

Efficient Quantum Circuits for Machine Learning Activation Functions including Constant T-depth ReLU

2024-04-09 · Wei Zi, Siyi Wang, Hyunji Kim, Xiaoming Sun 외

In recent years, Quantum Machine Learning (QML) has increasingly captured the interest of researchers. Among the components in this domain, activation functions hold a fundamental and indispensable role. Our research foc…

Quantum Machine Learning

VI^3NR: Variance Informed Initialization for Implicit Neural Representations

2025-01-01 · CVPR 2025 1 · Chamin Hewa Koneputugodage, Yizhak Ben-Shabat, Sameera Ramasinghe, Stephen Gould

Implicit Neural Representations (INRs) are a versatile and powerful tool for encoding various forms of data, including images, videos, sound, and 3D shapes. A critical factor in the success of INRs is the initializat…

Surface Reconstruction

Evolution of Novel Activation Functions in Neural Network Training with Applications to Classification of Exoplanets

2019-06-01 · Snehanshu Saha, Nithin Nagaraj, Archana Mathur, Rahul Yedida

We present analytical exploration of novel activation functions as consequence of integration of several ideas leading to implementation and subsequent use in habitability classification of exoplanets. Neural networks, a…

General Classification

A Use of Even Activation Functions in Neural Networks

2020-11-23 · Fuchang Gao, Boyu Zhang

Despite broad interest in applying deep learning techniques to scientific discovery, learning interpretable formulas that accurately describe scientific data is very challenging because of the vast landscape of possible …

scientific discovery