Complex-valued neural networks (CVNNs) are a powerful modeling tool for domains where data can be naturally interpreted in terms of complex numbers. However, several analytical properties of the complex domain (e.g., holomorphicity) make the design of CVNNs a more challenging task than their real counterpart. In this paper, we consider the problem of flexible activation functions (AFs) in the complex domain, i.e., AFs endowed with sufficient degrees of freedom to adapt their shape given the training data. While this problem has received considerable attention in the real case, a very limited literature exists for CVNNs, where most activation functions are generally developed in a split fashion (i.e., by considering the real and imaginary parts of the activation separately) or with simple phase-amplitude techniques. Leveraging over the recently proposed kernel activation functions (KAFs), and related advances in the design of complex-valued kernels, we propose the first fully complex, non-parametric activation function for CVNNs, which is based on a kernel expansion with a fixed dictionary that can be implemented efficiently on vectorized hardware. Several experiments on common use cases, including prediction and channel equalization, validate our proposal when compared to real-valued neural networks and CVNNs with fixed activation functions.
Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain. One of the major challenges in scaling up CVNNs in practice is the design of complex activation functions. Recently, we proposed a novel framework for learning these activation functions neuron-wise in a data-dependent fashion, based on a cheap one-dimensional kernel expansion and the idea of kernel activation functions (KAFs). In this paper we argue that, despite its flexibility, this framework is still limited in the class of functio…
Dept. Information Eng., Electronics and Telecomm., Sapienza University of Rome（罗马一大信息工程、电子与电信系）；Dept. Communications Eng., University of Cantabria（坎塔布里亚大学通信工程系）
Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in their layers, such as rectifiers or squashing functions. In this paper, we investigate the use of graph convolutional networks (GCNs) when combined with more complex activation functions, able to adapt from the training data. More specifically, we extend the recently proposed kerne…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Cognizant AI Labs（高知特人工智能实验室）
Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and therefore the rectified linear unit (ReLU) is still the most commonly used. This paper proposes a technique for customizing activation functions automatically, resulting in reliable improvements in performance. Evolutionary search is used to discover the general form of the function, and gradient descent to optimize its parameters for different parts of the network …
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 flexi…
Sapienza University of Rome（罗马大学）；University of Cantabria（坎塔布里亚大学）
Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions themselves, endowing them with varying degrees of flexibility. None of these approaches, however, have gained wide acceptance in practice, and research in this topic remains open. In this paper, we introduce a novel family of flexible activation functions that are based on an inexpensive kernel expansion at every neuron. Leveraging over several properties of kernel-ba…
Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization
Department of Computer Science and Engineering（计算机科学与工程系）；Mahindra University（马林达大学）；Department of Applied Mathematics（应用数学系）；Universidade Estadual de Campinas (UNICAMP)（坎皮纳斯州立大学（UNICAMP））；Department of Electronics and Communication Engineering（电子与通信工程系）；Gokaraju Rangraju Institute of Engineering and Technology（戈卡拉朱·拉朱工程与技术学院）
Mila - Quebec Artificial Intelligence Institute（米拉——魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activation functions used in artificial networks are fixed and mostly considered as an inconsequential architecture choice. In this paper, we investigate nonlinear activation function adaptation over the large time scale of learning, and outline its impact on sequential processing in recurrent neural networks. We introduce a novel parametric family of nonlinear activation functions, inspired by input-frequency response curves of biological neurons, which allows…
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…
Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding. Recently, the Exponential Linear Unit (ELU) has been proposed as a key component for managing bias shift in Convolutional Neural Networks (CNNs), but defines a parameter that must be set by hand. In this paper, we propose learning a parameterization of ELU in order to learn the proper activation shape at each layer in the CNNs. Our results on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN, Overfeat, All-CNN and ResNet networks indicate that our proposed Param…
The design of a neural network is usually carried out by defining the number of layers, the number of neurons per layer, their connections or synapses, and the activation function that they will execute. The training process tries to optimize the weights assigned to those connections, together with the biases of the neurons, to better fit the training data. However, the definition of the activation functions is, in general, determined in the design process and not modified during the training, meaning that their behavior is unrelated to the training data set. In this paper we propose the defin…
NVIDIA（英伟达）；Massachusetts Institute of Technology（麻省理工学院）；UC-Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）
Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile platforms such as autonomous vehicles, cameras, and electronic personal assistants. This paper introduces the Sparse CNN (SCNN) accelerator architecture, which improves performance and energy efficiency by exploiting the zero-valued weights that stem from network pruning during training and zero-valued activations that arise from the common ReLU operator applied du…
Technical University Munich（慕尼黑工业大学）；AI Research, Volkswagen Group（大众集团人工智能研究部）
We propose stochastic, non-parametric activation functions that are fully learnable and individual to each neuron. Complexity and the risk of overfitting are controlled by placing a Gaussian process prior over these functions. The result is the Gaussian process neuron, a probabilistic unit that can be used as the basic building block for probabilistic graphical models that resemble the structure of neural networks. The proposed model can intrinsically handle uncertainties in its inputs and self-estimate the confidence of its predictions. Using variational Bayesian inference and the central lim…
