In the last decade, an active area of research has been devoted to design novel activation functions that are able to help deep neural networks to converge, obtaining better performance. The training procedure of these architectures usually involves optimization of the weights of their layers only, while non-linearities are generally pre-specified and their (possible) parameters are usually considered as hyper-parameters to be tuned manually. In this paper, we introduce two approaches to automatically learn different combinations of base activation functions (such as the identity function, ReLU, and tanh) during the training phase. We present a thorough comparison of our novel approaches with well-known architectures (such as LeNet-5, AlexNet, and ResNet-56) on three standard datasets (Fashion-MNIST, CIFAR-10, and ILSVRC-2012), showing substantial improvements in the overall performance, such as an increase in the top-1 accuracy for AlexNet on ILSVRC-2012 of 3.01 percentage points.
Indian Institute Of Technology–Roorkee（印度理工学院鲁尔基分校）
Activation functions have come up as one of the essential components of neural networks. The choice of adequate activation function can impact the accuracy of these methods. In this study, we experiment for finding an optimal activation function by defining it as a weighted sum of existing activation functions and then further optimizing these weights while training the network. The study uses three activation functions, ReLU, tanh, and sin, over three popular image datasets, MNIST, FashionMNIST, and KMNIST. We observe that the ReLU activation function can easily overlook other activation func…
Sichuan University（四川大学）；University of Electronic Science and Technology of China（电子科技大学）；Megvii Technology（旷视科技）
Neural Architecture Search (NAS) is an automatic technique that can search for well-performed architectures for a specific task. Although NAS surpasses human-designed architecture in many fields, the high computational cost of architecture evaluation it requires hinders its development. A feasible solution is to directly evaluate some metrics in the initial stage of the architecture without any training. NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer. H…
University of California San Diego（加州大学圣地亚哥分校）；Academia Sinica（中央研究院）；Taiwan AI Labs（台湾人工智能实验室）
Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions still remain unanswered. In this paper, we aim to study the following two research questions: 1) What types of output activation functions form a well-behaved adversarial loss? 2) How different combinations of output activation functions and regularization approaches perform empi…
Inspired by biological neurons, the activation functions play an essential part in the learning process of any artificial neural network commonly used in many real-world problems. Various activation functions have been proposed in the literature for classification as well as regression tasks. In this work, we survey the activation functions that have been employed in the past as well as the current state-of-the-art. In particular, we present various developments in activation functions over the years and the advantages as well as disadvantages or limitations of these activation functions. We a…
In the current research of neural networks, the activation function is manually specified by human and not able to change themselves during training. This paper focus on how to make the activation function trainable for deep neural networks. We use series and linear combination of different activation functions make activation functions continuously variable. Also, we test the performance of CNNs with Fourier series simulated activation(Fourier-CNN) and CNNs with linear combined activation function (LC-CNN) on Cifar-10 dataset. The result shows our trainable activation function reveals better …
Data Science Institute（数据科学研究所）；Imperial College London（帝国理工学院）
Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear activation function in use. Building on those principles, we introduce a process to transform an existing activation function into another one with better properties. We term such transform \emph{static activation normalization}. More specifically we focus on this normalization applied to the ReLU unit, and show empirically that it significantly promotes convergence …
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）
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), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activati…
Pennsylvania State University（宾夕法尼亚州立大学）；University of Southern California（南加州大学）
Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions are two-fold. First, we provide a theoretical explanation for the spectral bias of ReLU neural networks by leveraging connections with the theory of finite element methods. Second, based upon this theory we predict that switching the activation function to a piecewise linear B-spline, namely the Hat function, will remove this spectral bias, which we verify …
Verification of neural networks relies on activation functions being piecewise affine (pwa) -- enabling an encoding of the verification problem for theorem provers. In this paper, we present the first formalization of pwa activation functions for an interactive theorem prover tailored to verifying neural networks within Coq using the library Coquelicot for real analysis. As a proof-of-concept, we construct the popular pwa activation function ReLU. We integrate our formalization into a Coq model of neural networks, and devise a verified transformation from a neural network N to a pwa function r…
University of Prince Edward Island（爱德华王子岛大学）；McGill University（麦吉尔大学）
We propose a novel approach to addressing the vanishing (or exploding) gradient problem in deep neural networks. We construct a new architecture for deep neural networks where all layers (except the output layer) of the network are a combination of rotation, permutation, diagonal, and activation sublayers which are all volume preserving. Our approach replaces the standard weight matrix of a neural network with a combination of diagonal, rotational and permutation matrices, all of which are volume-preserving. We introduce a coupled activation function allowing us to preserve volume even in the …
Institute for Cognitive Science（认知科学研究所）；Osnabrück University（奥斯纳布吕克大学）
The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives have managed to consistently outperform the rest and there is no unified theory connecting properties of the task and network with properties of activation functions for most efficient training. A possible solution is to have the network learn its preferred activation functions. In this work, we introduce Adaptive Blending Units (ABUs), a trainable linear combination of a set of…
Leipzig University（莱比锡大学）；Leipzig University Medical Centre（莱比锡大学医学中心）
The sigmoid activation is the standard output activation function in binary classification and segmentation with neural networks. Still, there exist a variety of other potential output activation functions, which may lead to improved results in medical image segmentation. In this work, we consider how the asymptotic behavior of different output activation and loss functions affects the prediction probabilities and the corresponding segmentation errors. For cross entropy, we show that a faster rate of change of the activation function correlates with better predictions, while a slower rate of c…
The asymptotic mean squared test error and sensitivity of the Random Features Regression model (RFR) have been recently studied. We build on this work and identify in closed-form the family of Activation Functions (AFs) that minimize a combination of the test error and sensitivity of the RFR under different notions of functional parsimony. We find scenarios under which the optimal AFs are linear, saturated linear functions, or expressible in terms of Hermite polynomials. Finally, we show how using optimal AFs impacts well-established properties of the RFR model, such as its double descent curv…
The choice of activation function can significantly influence the performance of neural networks. The lack of guiding principles for the selection of activation function is lamentable. We try to address this issue by introducing our variational neural networks, where the activation function is represented as a linear combination of possible candidate functions, and an optimal activation is obtained via minimization of a loss function using gradient descent method. The gradient formulae for the loss function with respect to these expansion coefficients are central for the implementation of grad…
TU Darmstadt（达姆施塔特工业大学）；Centre for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）
The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron. However, deciding on the best activation is non-trivial, and the choice depends on the architecture, hyper-parameters, and even on the dataset. Typically these activations are fixed by hand before training. Here, we demonstrate how to eliminate the reliance on first picking fixed activation functions by using flexible parametric rational functions instead. The resulting Padé Activation Units (PAUs) can both approximate common activation functions and also l…
In artificial neural network, the activation function and the weight initialization method play important roles in training and performance of a neural network. The question arises is what properties of a function are important/necessary for being a well-performing activation function. Also, the most widely used weight initialization methods - Xavier and He normal initialization have fundamental connection with activation function. This survey discusses the important/necessary properties of activation function and the most widely used activation functions (sigmoid, tanh, ReLU, LReLU and PReLU)…
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). It acts as a Rectified Linear Unit (ReLU) function for the positive region and a sinus-sigmoidal function for the negative region. In other words, it incorporates a sigmoid and a sine function and gaining new dynamics over classical ReLU. We analyzed the consistency of the Nish for different combinations of essential networks and most common activation funct…
There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functions. This class of activation functions includes most of frequently used activation functions. We derive the required depth, width and sparsity of a deep neural network to approximate any Hölder smooth function upto a given approximation error for the large class of activation fu…
We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal activation function. We extend the dimension independent approximation rates previously obtained to this new class of activation functions. Our second result gives a weaker, but still dimension independent, approximation rate for a larger class of activation functions, removing the polynomial decay assumption. This result applies to any bounded, integrable ac…
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 activation, and the weights capture the scale. Here we propose to train the network over a shape parameter as well. This view allows each neuron to tune its own activation function and adapt the neuron curvature towards a better prediction. This modification only adds one further equation to the back-propagation for each neuron. Re-formalizing activation fun…
Deep Learning-Based Survival Analysis with Copula-Based Activation Functions for Multivariate Response Prediction
Statistics Discipline, Division of Science and Mathematics, University of Minnesota-Morris（明尼苏达州立大学莫里斯分校统计学系）；EGADE Business School, Tecnológico de Monterrey（墨西哥蒙特雷技术学院EGADE商学院）；Department of Statistics and Data Science, Pukyong National University（浦项国立大学统计学与数据科学系）；Department of Management Information Systems, Dong-A University（东阿大学管理信息系）
University of Tsukuba（筑波大学）；Hokkaido University（北海道大学）
We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions. As a result, we found that some kinds of activation functions with an appropriate nonlinearity show high performance compared to the conventional sigmoid function.
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…
We propose a new training method for a feedforward neural network having the activation functions with the geometric contraction property. The method consists of constructing a new functional that is less nonlinear in comparison with the classical functional by removing the nonlinearity of the activation function from the output layer. We validate this new method by a series of experiments that show an improved learning speed and better classification error.
This work contributes to the development of a new data-driven method (D-DM) of feedforward neural networks (FNNs) learning. This method was proposed recently as a way of improving randomized learning of FNNs by adjusting the network parameters to the target function fluctuations. The method employs logistic sigmoid activation functions for hidden nodes. In this study, we introduce other activation functions, such as bipolar sigmoid, sine function, saturating linear functions, reLU, and softplus. We derive formulas for their parameters, i.e. weights and biases. In the simulation study, we evalu…
The reason behind CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. Several advanced activation functions have been discovered to improve the training process of neural networks, as choosing an activation function is a crucial step in the modeling. Recent research has proposed using an oscillating activation function to solve classification problems inspired by the human brain cortex. This paper explores the performance of one of the CNN architecture ALexNet on MNIST and CIFAR10 datasets using oscillatory acti…
In this paper, we explore the concept of adding learn-able slope and mean shift parameters to an activation function to improve the total response region. The characteristics of an activation function depend highly on the value of parameters. Making the parameters learn-able, makes the activation function more dynamic and capable to adapt as per the requirements of its neighboring layers. The introduced slope parameter is independent of other parameters in the activation function. The concept was applied to ReLU to develop Dual Line and DualParametric ReLU activation function. Evaluation on MN…
Artificial neural networks (ANN), typically referred to as neural networks, are a class of Machine Learning algorithms and have achieved widespread success, having been inspired by the biological structure of the human brain. Neural networks are inherently powerful due to their ability to learn complex function approximations from data. This generalization ability has been able to impact multidisciplinary areas involving image recognition, speech recognition, natural language processing, and others. Activation functions are a crucial sub-component of neural networks. They define the output of …
Neural network models are known to reinforce hidden data biases, making them unreliable and difficult to interpret. We seek to build models that `know what they do not know' by introducing inductive biases in the function space. We show that periodic activation functions in Bayesian neural networks establish a connection between the prior on the network weights and translation-invariant, stationary Gaussian process priors. Furthermore, we show that this link goes beyond sinusoidal (Fourier) activations by also covering triangular wave and periodic ReLU activation functions. In a series of expe…
We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization layers. We explore the training of deep vanilla recurrent neural networks (RNNs) with up to 144 layers, and show that bipolar activation functions help learning in this setting. On the Penn Treebank and Text8 language modeling tasks we obtain competitive results, improving on the best reported results for non-gated networks. In experiments with convolutional neur…
Amazon Web Services（亚马逊云科技）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Microsoft Inc.（微软公司）
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact …
Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks
Huawei Noah’s Ark Lab（华为诺亚实验室）；Department of Computing, Imperial College London（帝国理工学院计算机系）；Department of Computer Science, University of Liverpool（利物浦大学计算机科学系）；Department of Engineering, King’s College London（伦敦国王学院工程系）
