Activation function is a key component in deep learning that performs non-linear mappings between the inputs and outputs. Rectified Linear Unit (ReLU) has been the most popular activation function across the deep learning community. However, ReLU contains several shortcomings that can result in inefficient training of the deep neural networks, these are: 1) the negative cancellation property of ReLU tends to treat negative inputs as unimportant information for the learning, resulting in a performance degradation; 2) the inherent predefined nature of ReLU is unlikely to promote additional flexibility, expressivity, and robustness to the networks; 3) the mean activation of ReLU is highly positive and leads to bias shift effect in network layers; and 4) the multilinear structure of ReLU restricts the non-linear approximation power of the networks. To tackle these shortcomings, this paper introduced Parametric Flatten-T Swish (PFTS) as an alternative to ReLU. By taking ReLU as a baseline method, the experiments showed that PFTS improved classification accuracy on SVHN dataset by 0.31%, 0.98%, 2.16%, 17.72%, 1.35%, 0.97%, 39.99%, and 71.83% on DNN-3A, DNN-3B, DNN-4, DNN- 5A, DNN-5B, DNN-5C, DNN-6, and DNN-7, respectively. Besides, PFTS also achieved the highest mean rank among the comparison methods. The proposed PFTS manifested higher non-linear approximation power during training and thereby improved the predictive performance of the networks.
Universiti Tun Hussein Onn Malaysia（马来西亚敦胡先翁大学）；Institute of Engineering and Management（工程与管理学院）
Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function across the deep learning community since 2012. Although ReLU has been popular, however, the hard zero property of the ReLU has heavily hindered the negative values from propagating through the network. Consequently, the deep neural network has not been benefited from the negative representations. In this work, an activation function called Flatten-T Swish (FTS) that leverage the…
Activation functions have a notorious impact on neural networks on both training and testing the models against the desired problem. Currently, the most used activation function is the Rectified Linear Unit (ReLU). This paper introduces a new and novel activation function, closely related with the new activation $Swish = x * sigmoid(x)$ (Ramachandran et al., 2017) which generalizes it. We call the new activation $E-swish = βx * sigmoid(x)$. We show that E-swish outperforms many other well-known activations including both ReLU and Swish. For example, using E-swish provided 1.5% and 4.6% accurac…
SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance
Jiangsu University（江苏大学）；Abdus Salam School of Mathematical Sciences, Govt College University（政府学院大学阿卜杜斯·萨拉姆数学科学学院）；Metaverse Research Institute, School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院元宇宙研究院）
Ubiquitous Knowledge Processing Lab (UKP-TUDA)（普适知识处理实验室（UKP-TUDA））；Department of Computer Science（计算机科学系）；Technische Universität Darmstadt（达姆施塔特工业大学）
Activation functions play a crucial role in neural networks because they are the nonlinearities which have been attributed to the success story of deep learning. One of the currently most popular activation functions is ReLU, but several competitors have recently been proposed or 'discovered', including LReLU functions and swish. While most works compare newly proposed activation functions on few tasks (usually from image classification) and against few competitors (usually ReLU), we perform the first large-scale comparison of 21 activation functions across eight different NLP tasks. We find t…
Activation functions play a significant role in the performance of deep learning algorithms. In particular, the Swish activation function tends to outperform ReLU on deeper models, including deep reinforcement learning models, across challenging tasks. Despite this progress, ReLU is the preferred function partly because it is more efficient than Swish. Furthermore, in contrast to the fields of computer vision and natural language processing, the deep reinforcement learning and robotics domains have seen less inclination to adopt new activation functions, such as Swish, and instead continue to …
The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance. Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU). Although various hand-designed alternatives to ReLU have been proposed, none have managed to replace it due to inconsistent gains. In this work, we propose to leverage automatic search techniques to discover new activation functions. Using a combination of exhaustive and reinforcement learning-based search, we discover multiple novel activation functions. We verify the …
University of Toronto（多伦多大学）；Stony Brook University（纽约州立大学石溪分校）
Activation functions play a pivotal role in determining the training dynamics and neural network performance. The widely adopted activation function ReLU despite being simple and effective has few disadvantages including the Dying ReLU problem. In order to tackle such problems, we propose a novel activation function called Serf which is self-regularized and nonmonotonic in nature. Like Mish, Serf also belongs to the Swish family of functions. Based on several experiments on computer vision (image classification and object detection) and natural language processing (machine translation, sentime…
Michigan Technological University（密歇根理工大学）；Symbiosis Centre for Medical Image Analysis（共生医学图像分析中心）；Symbiosis Institute of Technology（共生技术学院）
This work introduces a novel activation unit that can be efficiently employed in deep neural nets (DNNs) and performs significantly better than the traditional Rectified Linear Units (ReLU). The function developed is a two parameter version of the specialized Richard's Curve and we call it Adaptive Richard's Curve weighted Activation (ARiA). This function is non-monotonous, analogous to the newly introduced Swish, however allows a precise control over its non-monotonous convexity by varying the hyper-parameters. We first demonstrate the mathematical significance of the two parameter ARiA follo…
In neural networks, non-linearity is introduced by activation functions. One commonly used activation function is Rectified Linear Unit (ReLU). ReLU has been a popular choice as an activation but has flaws. State-of-the-art functions like Swish and Mish are now gaining attention as a better choice as they combat many flaws presented by other activation functions. CoLU is an activation function similar to Swish and Mish in properties. It is defined as f(x)=x/(1-xe^-(x+e^x)). It is smooth, continuously differentiable, unbounded above, bounded below, non-saturating, and non-monotonic. Based on ex…
Microsoft（微软）；Singapore University of Technology and Design（新加坡科技设计大学）；Chulalongkorn University（朱拉隆功大学）；European Center for Theoretical Studies in Nuclear Physics and Related Areas（欧洲核物理及相关领域理论研究中心）；Trento Institute for Fundamental Physics and Applications（特伦托基础物理与应用研究所）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach. We infer that FFN can be understood as performing three basic steps: encoding, representation validation and propagation. From the meanfield solution of the model, we obtain a set of natural activations -- such as Sigmoid, $\tanh$ and ReLu -- together with the state-of-the-art, Swish; this represents the expected information propagating through the network and tends to ReLu in the limit of zero noise.We study the spectrum of the Hessian on an associat…
The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward propagation and the exponential vanishing/exploding of gradients during back-propagation. Understanding the theoretical properties of untrained random networks is key to identifying which deep networks may be trained successfully as recently demonstrated by Schoenholz et al. (2017) who showed that for deep feedforward neural networks only a specific choice of h…
Recent work has shown that the activation function of the convolutional neural network can meet the Lipschitz condition, then the corresponding convolutional neural network structure can be constructed according to the scale of the data set, and the data set can be trained more deeply, more accurately and more effectively. In this article, we have accepted the experimental results and introduced the core block N-Gauss, N-Gauss, and Swish (Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively. Experiments show that N-Gauss gives full play to the m…
Wroclaw University of Science and Technology（弗罗茨瓦夫理工大学）
The primary neural networks decision-making units are activation functions. Moreover, they evaluate the output of networks neural node; thus, they are essential for the performance of the whole network. Hence, it is critical to choose the most appropriate activation function in neural networks calculation. Acharya et al. (2018) suggest that numerous recipes have been formulated over the years, though some of them are considered deprecated these days since they are unable to operate properly under some conditions. These functions have a variety of characteristics, which are deemed essential to …
University of Warwick（华威大学）；Pakistan Institute of Engineering and Applied Sciences (PIEAS)（巴基斯坦工程与应用科学研究院）
An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the activation function of each neuron in an artificial neural network is learned natively from data alone. This is achieved by modelling the activation function of each neuron as a small neural network whose weights are shared by all neurons in the original network. We list our pri…
Qualcomm AI Research, Qualcomm Technologies, Inc.（高通AI研究，高通技术公司）；Qualcomm AI Research, Qualcomm Technologies Netherlands B.V.（高通AI研究，高通技术荷兰有限公司）；Seoul National University（首尔大学）
Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges. Typical learnable quantization schemes [PACT, LSQ] assume unsigned quantization for activations and quantize all negative activations to zero which leads to significant loss in performance. Naively using signed quantization to accommodate these negative values requires an extra sign bit which is expensive for low-bit (2-, 3-, 4-bit) quantization. To solve this problem, we prop…
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful alternatives. These models also deal with activation functions but here they are applied to the so-called classifier function instead. In this paper we investigate successful candidates of activation functions known for MLPs for application in GLVQ and their influence on the per…
In the big data era, cloud-based machine learning as a service (MLaaS) has attracted considerable attention. However, when handling sensitive data, such as financial and medical data, a privacy issue emerges, because the cloud server can access clients' raw data. A common method of handling sensitive data in the cloud uses homomorphic encryption, which allows computation over encrypted data without decryption. Previous research usually adopted a low-degree polynomial mapping function, such as the square function, for data classification. However, this technique results in low classification ac…
Indian Institute of Information Technology, Allahabad（印度理工学院信息技术学院（阿拉哈巴德））；Techno India University（泰克诺印度大学）；Indian Statistical Institute（印度统计研究所）
Neural networks have shown tremendous growth in recent years to solve numerous problems. Various types of neural networks have been introduced to deal with different types of problems. However, the main goal of any neural network is to transform the non-linearly separable input data into more linearly separable abstract features using a hierarchy of layers. These layers are combinations of linear and nonlinear functions. The most popular and common non-linearity layers are activation functions (AFs), such as Logistic Sigmoid, Tanh, ReLU, ELU, Swish and Mish. In this paper, a comprehensive over…
IIIT Delhi（德里英德拉普拉斯塔信息技术学院）；Shaheed Bhagat Singh College, University of Delhi（德里大学沙希德·巴格特·辛格学院）；University of Delhi（德里大学）
An activation function is a crucial component of a neural network that introduces non-linearity in the network. The state-of-the-art performance of a neural network depends also on the perfect choice of an activation function. We propose two novel non-monotonic smooth trainable activation functions, called ErfAct and Pserf. Experiments suggest that the proposed functions improve the network performance significantly compared to the widely used activations like ReLU, Swish, and Mish. Replacing ReLU by ErfAct and Pserf, we have 5.68% and 5.42% improvement for top-1 accuracy on Shufflenet V2 (2.0…
We study the problem of learning a single neuron $\mathbf{x}\mapsto σ(\mathbf{w}^T\mathbf{x})$ with gradient descent (GD). All the existing positive results are limited to the case where $σ$ is monotonic. However, it is recently observed that non-monotonic activation functions outperform the traditional monotonic ones in many applications. To fill this gap, we establish learnability without assuming monotonicity. Specifically, when the input distribution is the standard Gaussian, we show that mild conditions on $σ$ (e.g., $σ$ has a dominating linear part) are sufficient to guarantee the learna…
We propose $\textit{Mish}$, a novel self-regularized non-monotonic activation function which can be mathematically defined as: $f(x)=x\tanh(softplus(x))$. As activation functions play a crucial role in the performance and training dynamics in neural networks, we validated experimentally on several well-known benchmarks against the best combinations of architectures and activation functions. We also observe that data augmentation techniques have a favorable effect on benchmarks like ImageNet-1k and MS-COCO across multiple architectures. For example, Mish outperformed Leaky ReLU on YOLOv4 with a…
Intel Labs（英特尔研究院）；Georgia Institute of Technology（佐治亚理工学院）
We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function TanH for Deep Learning. K-TanH consists of parameterized low-precision integer operations, such as, shift and add/subtract (no floating point operation needed) where parameters are stored in very small look-up tables that can fit in CPU registers. K-TanH can work on various numerical formats, such as, Float32 and BFloat16. High quality approximations to other activation functions, e.g., Sigmoid, Swish and GELU, can be derived from K-TanH. Our AVX512 implementation of K-TanH demonstrates…
Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it also introduces practical challenges: it breaks the independence between training examples within a batch, can incur compute and memory overhead, and often results in unexpected bugs. Building on recent theoretical analyses of deep ResNets at initialization, we propose a simple set of analysis tools to characterize signal propagation on the forward pass, and leverage these tools to design highly performant ResNets without activation normalization layers. Crucial to our success is an adapted version …
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）
College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province（浙江省可视媒体智能处理技术重点实验室）；School of Computer Science and Engineering, Tianjin University of Technology（天津理工大学计算机科学与工程学院）
To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data. In this work, a novel methodology is proposed to adaptively customize activation functions only by adding very few parameters to the traditional activation functions such as Sigmoid, Tanh, and ReLU. To verify the effectiveness of the proposed methodology, some theoretical and experimental analysis on accelerating the convergence and improving the performance is presen…
The most scalable approaches to certifying neural network robustness depend on computing sound linear lower and upper bounds for the network's activation functions. Current approaches are limited in that the linear bounds must be handcrafted by an expert, and can be sub-optimal, especially when the network's architecture composes operations using, for example, multiplication such as in LSTMs and the recently popular Swish activation. The dependence on an expert prevents the application of robustness certification to developments in the state-of-the-art of activation functions, and furthermore …
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）
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）
Microsoft Research India（微软印度研究院）；Cornell University（康奈尔大学）
It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly overparametrized networks under reasonable assumptions. These results either assume that the activation function is ReLU or they crucially depend on the minimum eigenvalue of a certain Gram matrix depending on the data, random initialization and the activation function. In the later case, existing works only prove that this minimum eigenvalue is non-zero and do…
University of Technology Sydney（悉尼科技大学）；Qamcom Research and Technology AB（Qamcom研究与技术公司）
Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically increasing function, where it has an approximately constant negative output for large negative input. In this work, we propose a new activation function to break the monotonicity property of SELU while still preserving the self-normalizing property. Differently from SELU, the new func…
San Jose State University（圣何塞州立大学）；Carnegie Mellon University（卡内基梅隆大学）；Nanyang Technological University（南洋理工大学）
Virtual try-on has garnered interest as a neural rendering benchmark task to evaluate complex object transfer and scene composition. Recent works in virtual clothing try-on feature a plethora of possible architectural and data representation choices. However, they present little clarity on quantifying the isolated visual effect of each choice, nor do they specify the hyperparameter details that are key to experimental reproduction. Our work, ShineOn, approaches the try-on task from a bottom-up approach and aims to shine light on the visual and quantitative effects of each experiment. We build …
In extreme learning machines (ELM) the hidden-layer coefficients are randomly set and fixed, while the output-layer coefficients of the neural network are computed by a least squares method. The randomly-assigned coefficients in ELM are known to influence its performance and accuracy significantly. In this paper we present a modified batch intrinsic plasticity (modBIP) method for pre-training the random coefficients in the ELM neural networks. The current method is devised based on the same principle as the batch intrinsic plasticity (BIP) method, namely, by enhancing the information transmiss…
