This work explains in detail the theory behind Complex-Valued Neural Network (CVNN), including Wirtinger calculus, complex backpropagation, and basic modules such as complex layers, complex activation functions, or complex weight initialization. We also show the impact of not adapting the weight initialization correctly to the complex domain. This work presents a strong focus on the implementation of such modules on Python using cvnn toolbox. We also perform simulations on real-valued data, casting to the complex domain by means of the Hilbert Transform, and verifying the potential interest of CVNN even for non-complex data.
Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance. When comparing real-valued versus complex-valued neural networks, existing literature often ignores the number of parameters, resulting in comparisons of neural networks with vastly different sizes. We find that when real and complex neural networks of similar capacity are compared, complex models perform equal to or slightly worse than real-valued models for a range of real-valued classification tasks. …
Prairie View A&M University（普雷里维尤农工大学）；Texas A&M University System（得克萨斯农工大学系统）
Artificial neural networks (ANNs) based machine learning models and especially deep learning models have been widely applied in computer vision, signal processing, wireless communications, and many other domains, where complex numbers occur either naturally or by design. However, most of the current implementations of ANNs and machine learning frameworks are using real numbers rather than complex numbers. There are growing interests in building ANNs using complex numbers, and exploring the potential advantages of the so-called complex-valued neural networks (CVNNs) over their real-valued count…
Federal Institute of Education, Science and Technology of Espírito Santo（圣埃斯皮里图联邦教育、科学与技术学院）；University of Campinas（坎皮纳斯大学）
In this paper, we address the stability of a broad class of discrete-time hypercomplex-valued Hopfield-type neural networks. To ensure the neural networks belonging to this class always settle down at a stationary state, we introduce novel hypercomplex number systems referred to as real-part associative hypercomplex number systems. Real-part associative hypercomplex number systems generalize the well-known Cayley-Dickson algebras and real Clifford algebras and include the systems of real numbers, complex numbers, dual numbers, hyperbolic numbers, quaternions, tessarines, and octonions as parti…
KU Eichstätt–Ingolstadt（艾希施泰特-英戈尔施塔特天主教大学）；Technical University of Munich（慕尼黑工业大学）
Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for appr…
Many real-world signal sources are complex-valued, having real and imaginary components. However, the vast majority of existing deep learning platforms and network architectures do not support the use of complex-valued data. MRI data is inherently complex-valued, so existing approaches discard the richer algebraic structure of the complex data. In this work, we investigate end-to-end complex-valued convolutional neural networks - specifically, for image reconstruction in lieu of two-channel real-valued networks. We apply this to magnetic resonance imaging reconstruction for the purpose of acce…
Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a new vector neural architecture called the Arbitrary BIlinear Product Neural Network (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convoluti…
Technical University of Munich（慕尼黑工业大学）；University of Vienna（维也纳大学）；Catholic University of Eichstätt-Ingolstadt（艾希施泰特-因戈尔施塔特天主教大学）
We generalize the classical universal approximation theorem for neural networks to the case of complex-valued neural networks. Precisely, we consider feedforward networks with a complex activation function $σ: \mathbb{C} \to \mathbb{C}$ in which each neuron performs the operation $\mathbb{C}^N \to \mathbb{C}, z \mapsto σ(b + w^T z)$ with weights $w \in \mathbb{C}^N$ and a bias $b \in \mathbb{C}$, and with $σ$ applied componentwise. We completely characterize those activation functions $σ$ for which the associated complex networks have the universal approximation property, meaning that they can…
Universal approximation with complex-valued deep narrow neural networks
Mathematical Institute for Machine Learning and Data Science (MIDS), Catholic University of Eichstätt–Ingolstadt (KU)（艾希施泰特-英戈尔施塔特天主教大学 机器学习与数据科学数学研究所）
Montreal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））；Microsoft Research（微软研究院）；Element AI（元素人工智能公司）；Ecole Polytechnique（巴黎综合理工学院）
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis suggests that complex numbers could have a richer representational capacity and could also facilitate noise-robust memory retrieval mechanisms. Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks require…
From Distributions to Stochastic Processes: Neural Approximation of Measure-Valued Maps
Shanghai Center for Mathematical Sciences（上海数学中心）；Department of Mathematics, Fudan University（复旦大学数学系）；Center for Applied Mathematics, Fudan University（复旦大学应用数学中心）；Alibaba Group（阿里巴巴集团）；Shanghai, China（（此处为城市信息，非机构，按要求不提取））；Hangzhou, China（（此处为城市信息，非机构，按要求不提取））；Fudan University（复旦大学）
The contributions of this paper are twofold. First, we show the potential interest of Complex-Valued Neural Network (CVNN) on classification tasks for complex-valued datasets. To highlight this assertion, we investigate an example of complex-valued data in which the real and imaginary parts are statistically dependent through the property of non-circularity. In this context, the performance of fully connected feed-forward CVNNs is compared against a real-valued equivalent model. The results show that CVNN performs better for a wide variety of architectures and data structures. CVNN accuracy pr…
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that QRPNNs overcome the cross-talk problem of QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that QRPNNs exhibit greater storage capacity and …
Institute of Mathematics, Statistics, and Scientific Computing（数学、统计与科学计算研究所）；University of Campinas（坎皮纳斯大学）
Recurrent correlation neural networks (RCNNs), introduced by Chiueh and Goodman as an improved version of the bipolar correlation-based Hopfield neural network, can be used to implement high-capacity associative memories. In this paper, we extend the bipolar RCNNs for processing hypercomplex-valued data. Precisely, we present the mathematical background for a broad class of hypercomplex-valued RCNNs. Then, we provide the necessary conditions which ensure that a hypercomplex-valued RCNN always settles at an equilibrium using either synchronous or asynchronous update modes. Examples with bipolar…
University of Memphis（孟菲斯大学）；Department of Mathematical Sciences（数学科学系）；Memphis, TN 38152, U.S.A.（美国田纳西州孟菲斯市 38152）
Here we research the univariate quantitative approximation, ordinary and fractional, of Banach space valued continuous functions on a compact interval or all the real line by quasi-interpolation Banach space valued neural network operators. These approximations are derived by establishing Jackson type inequalities involving the modulus of continuity of the engaged function or its Banach space valued high order derivative of fractional derivatives. Our operators are defined by using a density function generated by an algebraic sigmoid function. The approximations are pointwise and of the unifor…
JD Explore Academy, JD.com Inc.（京东探索研究院）；Faculty of Science, University of Hong Kong（香港大学理学院）
Complex-valued neural networks (CVNNs) have been widely applied to various fields, especially signal processing and image recognition. However, few works focus on the generalization of CVNNs, albeit it is vital to ensure the performance of CVNNs on unseen data. This paper is the first work that proves a generalization bound for the complex-valued neural network. The bound scales with the spectral complexity, the dominant factor of which is the spectral norm product of weight matrices. Further, our work provides a generalization bound for CVNNs when training data is sequential, which is also af…
South China University of Technology（华南理工大学）；Shanghai Jiao Tong University（上海交通大学）
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy degradation. We propose a generic method to revise the neural network to boost the challenge of inferring input attributes from features, while maintaining highly accurate outputs. In particular, the method transforms real-valued features into complex-valued ones, in which the input is hidden in a randomized phase of the transformed features. The knowledge of the pha…
In recent years, hyper-complex deep networks (such as complex-valued and quaternion-valued neural networks) have received a renewed interest in the literature. They find applications in multiple fields, ranging from image reconstruction to 3D audio processing. Similar to their real-valued counterparts, quaternion neural networks (QVNNs) require custom regularization strategies to avoid overfitting. In addition, for many real-world applications and embedded implementations, there is the need of designing sufficiently compact networks, with few weights and neurons. However, the problem of regula…
Deep learning has become an area of interest in most scientific areas, including physical sciences. Modern networks apply real-valued transformations on the data. Particularly, convolutions in convolutional neural networks discard phase information entirely. Many deterministic signals, such as seismic data or electrical signals, contain significant information in the phase of the signal. We explore complex-valued deep convolutional networks to leverage non-linear feature maps. Seismic data commonly has a lowcut filter applied, to attenuate noise from ocean waves and similar long wavelength con…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
A "wireless fingerprint" which exploits hardware imperfections unique to each device is a potentially powerful tool for wireless security. Such a fingerprint should be able to distinguish between devices sending the same message, and should be robust against standard spoofing techniques. Since the information in wireless signals resides in complex baseband, in this paper, we explore the use of neural networks with complex-valued weights to learn fingerprints using supervised learning. We demonstrate that, while there are potential benefits to using sections of the signal beyond just the preamb…
SRI International（SRI国际）；University of Guelph（圭尔夫大学）
We present a novel optimization strategy for training neural networks which we call "BitNet". The parameters of neural networks are usually unconstrained and have a dynamic range dispersed over all real values. Our key idea is to limit the expressive power of the network by dynamically controlling the range and set of values that the parameters can take. We formulate this idea using a novel end-to-end approach that circumvents the discrete parameter space by optimizing a relaxed continuous and differentiable upper bound of the typical classification loss function. The approach can be interpret…
The logcosh loss function for neural networks has been developed to combine the advantage of the absolute error loss function of not overweighting outliers with the advantage of the mean square error of continuous derivative near the mean, which makes the last phase of learning easier. It is clear, and one experiences it soon, that in the case of clustered data, an artificial neural network with logcosh loss learns the bigger cluster rather than the mean of the two. Even more so, the ANN, when used for regression of a set-valued function, will learn a value close to one of the choices, in othe…
Université d'Avignon（阿维尼翁大学）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；Orkis（奥基斯公司）；Element AI（Element AI公司）
Recently, the connectionist temporal classification (CTC) model coupled with recurrent (RNN) or convolutional neural networks (CNN), made it easier to train speech recognition systems in an end-to-end fashion. However in real-valued models, time frame components such as mel-filter-bank energies and the cepstral coefficients obtained from them, together with their first and second order derivatives, are processed as individual elements, while a natural alternative is to process such components as composed entities. We propose to group such elements in the form of quaternions and to process thes…
Université d’Avignon（阿维尼翁大学）；Orkis（奥基斯公司）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）
Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoustic input features remain almost unchanged. Traditional ASR systems rely on multidimensional acoustic features such as the Mel filter bank energies alongside with the first, and second order derivatives to characterize time-frames that compose the signal sequence. Considering that these components describe three different views of the same element, neural networks have to learn both the internal relations that exist w…
