Even in recent neural network architectures such as Transformers and Extended LSTM (xLSTM), and traditional ones like Convolutional Neural Networks, Activation Functions are an integral part of nearly all neural networks. They enable more effective training and capture nonlinear data patterns. More than 400 functions have been proposed over the last 30 years, including fixed or trainable parameters, but only a few are widely used. ReLU is one of the most frequently used, with GELU and Swish variants increasingly appearing. However, ReLU presents non-differentiable points and exploding gradient issues, while testing different parameters of GELU and Swish variants produces varying results, needing more parameters to adapt to datasets and architectures. This article introduces a novel set of activation functions called Zorro, a continuously differentiable and flexible family comprising five main functions fusing ReLU and Sigmoid. Zorro functions are smooth and adaptable, and serve as information gates, aligning with ReLU in the 0-1 range, offering an alternative to ReLU without the need for normalization, neuron death, or gradient explosions. Zorro also approximates functions like Swish, GELU, and DGELU, providing parameters to adjust to different datasets and architectures. We tested it on fully connected, convolutional, and transformer architectures to demonstrate its effectiveness.
Institute of Robotics and Cognitive Systems, University of Lübeck(吕贝克大学机器人与认知系统研究所);Mercedes-Benz AG(梅赛德斯-奔驰公司);Software Competence Center Hagenberg (SCCH)(哈根贝格软件能力中心);Institute of Signal Processing, Johannes Kepler University of Linz (JKU)(林茨约瑟夫·凯斯勒大学信号处理研究所);Institute of Neuro- and Bioinformatics, University of Lübeck(吕贝克大学神经与生物信息学研究所)
Department of Computer Science Rensselaer Polytechnic Institute(计算机科学系伦塞拉尔理工大学);Department of Biomedical Engineering Rensselaer Polytechnic Institute(生物医学工程系伦塞拉尔理工大学)
National University of Singapore(新加坡国立大学);Center for AI Research, VinUniversity(Vin大学人工智能研究中心);Independent Researcher(独立研究者);Hanoi University of Science and Technology(河内科学技术大学)
An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network
Ho Chi Minh City University of Technology, Vietnam National University - Ho Chi Minh(胡志明市理工大学,越南国立大学胡志明市分校);University of Technology and Education HCMC(胡志明市技术教育大学);Da Nang University of Science and Technology(岘港科技大学);Austrian Institute of Technology(奥地利理工学院)
Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
Bellini College of AI, Cybersecurity and Computing(人工智能、网络安全与计算学院);University of South Florida(佛罗里达州立大学);College of Computing and Informatics(计算与信息学院);Drexel University(德雷塞尔大学);Departments of Physics(物理系)
Microwave Remote Sensing Lab Center of Studies in Resources Engineering(微波遥感实验室 资源工程研究中心);Centre of Machine Intelligence and Data Science(智能与数据科学中心);Department of Electrical Engineering(电气工程系);School of Mathematics and Statistics(数学与统计学学院);Center of Studies in Resources Engineering(资源工程研究中心)
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
School of Statistics and Data Science, Nankai University(南开大学统计与数据科学学院);School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院);Department of Automation, Tsinghua University(清华大学自动化系);Central Research Institute, United Imaging Healthcare, Co., Ltd.(联影医疗股份有限公司中央研究院)
Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
Department of Artificial Intelligence, Korea University(人工智能系,韩国大学);Department of Mathematics and Statistics, Sejong University(数学与统计学系,世宗大学);Department of Mathematical Sciences, Gwangju Institute of Science and Technology(数学科学系,光州科学技术院)
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
School of Mathematical Sciences, Peking University(北京大学数学科学学院);Seed-Foundation-Model, ByteDance(字节跳动种子大模型部);Capital University of Economics and Business(首都经济贸易大学)
Department of Physics, Cornell University(康奈尔大学物理系);Institute of Natural Sciences, Shanghai Jiao Tong University(上海交通大学自然科学研究院);School of Mathematical Sciences, Shanghai Jiao Tong University(上海交通大学数学科学学院);Ministry of Education Key Laboratory in Scientific and Engineering Computing, Shanghai Jiao Tong University(上海交通大学教育部科学与工程计算重点实验室);Global College, Shanghai Jiao Tong University(上海交通大学全球学院);School of Electrical and Computer Engineering, Cornell University(康奈尔大学电气与计算机工程学院)
Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
Department of Mathematics and Statistics, Sejong University(数学与统计学系,世宗大学);Department of Mathematical Sciences, GIST(数学科学系,韩国科学技术院);Department of Computer Science, POSTECH(计算机科学系,POSTECH);Department of Artificial Intelligence, Korea University(人工智能系,韩国大学)
COTN: A Chaotic Oscillatory Transformer Network for Complex Volatile Systems under Extreme Conditions
Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Guangdong Provincial Key Laboratory of IRADS(广东省IRADS重点实验室);Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science(广东省珠海交叉学科与数据科学应用重点实验室);Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学)
Neural Network Verification with Branch-and-Bound for General Nonlinearities
University of California, Los Angeles(加州大学洛杉矶分校);University of Michigan(密歇根大学);Carnegie Mellon University(卡内基梅隆大学);Columbia University(哥伦比亚大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Directional Linear Separability of Neural Representations: Geometry and Transformations
State Key Laboratory of Novel Software Technology, School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院软件新技术国家重点实验室);AI for Good (AIGO), Istituto Italiano di Tecnologia(意大利技术研究院AI for Good (AIGO));DITEN, University of Genoa(热那亚大学DITEN);State Key Laboratory of Novel Software Technology, School of Artificial Intelligence, Nanjing University(南京大学人工智能学院软件新技术国家重点实验室)
Demystifying Oversmoothing in Attention-Based Graph Neural Networks
Institute for Data, Systems and Society (IDSS), MIT(麻省理工学院数据、系统与社会研究所);Laboratory for Information and Decision Systems (LIDS), MIT(麻省理工学院信息与决策系统实验室);Department of Computing and Mathematical Sciences (CMS), Caltech(加州理工学院计算与数学科学学院)