• arXiv.cs.NE Pub Date : 2020-06-29
Sana Ben Hamida; Wafa Abdelmalek; Fathi Abid

Volatility is a key variable in option pricing, trading and hedging strategies. The purpose of this paper is to improve the accuracy of forecasting implied volatility using an extension of genetic programming (GP) by means of dynamic training-subset selection methods. These methods manipulate the training data in order to improve the out of sample patterns fitting. When applied with the static subset

更新日期：2020-07-15
• arXiv.cs.NE Pub Date : 2020-07-13
Javier Antonio Gonzalez-Trejo; Diego Alberto Mercado-Ravell

In the context of crowd counting, most of the works have focused on improving the accuracy without regard to the performance leading to algorithms that are not suitable for embedded applications. In this paper, we propose a lightweight convolutional neural network architecture to perform crowd detection and counting using fewer computer resources without a significant loss on count accuracy. The architecture

更新日期：2020-07-15
• arXiv.cs.NE Pub Date : 2020-07-13
Uday K. Chakraborty

The Jaya algorithm is arguably one of the fastest-emerging metaheuristics amongst the newest members of the evolutionary computation family. The present paper proposes a new, improved Jaya algorithm by modifying the update strategies of the best and the worst members in the population. Simulation results on a twelve-function benchmark test-suite as well as a real-world problem of practical importance

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Marko Angjelichinoski; Bijan Pesaran; Vahid Tarokh

In this paper, we demonstrate that a neural decoder trained on neural activity signals of one subject can be used to \textit{robustly} decode the motor intentions of a different subject with high reliability. This is achieved in spite of the non-stationary nature of neural activity signals and the subject-specific variations of the recording conditions. Our proposed algorithm for cross-subject mapping

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Victor Costa; Nuno Lourenço; João Correia; Penousal Machado

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model should be previously designed by hand to ensure training success. In this context, evolutionary algorithms such as COEGAN were proposed to solve the challenges in GAN

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Angel Yanguas-Gil

In this work we explore recurrent representations of leaky integrate and fire neurons operating at a timescale equal to their absolute refractory period. Our coarse time scale approximation is obtained using a probability distribution function for spike arrivals that is homogeneously distributed over this time interval. This leads to a discrete representation that exhibits the same dynamics as the

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-11
Wei Fang

The Spiking Neural Networks (SNNs) have attracted research interest due to its temporal information processing capability, low power consumption, and high biological plausibility. The Leaky Integrate-and-Fire (LIF) neuron model is one of the most popular spiking neuron models used in SNNs for it achieves a balance between computing cost and biological plausibility. The most important parameter of a

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-10
Philippe Reiter; Geet Rose Jose; Spyridon Bizmpikis; Ionela-Ancuţa Cîrjilă

The increasing rise in machine learning and deep learning applications is requiring ever more computational resources to successfully meet the growing demands of an always-connected, automated world. Neuromorphic technologies based on Spiking Neural Network algorithms hold the promise to implement advanced artificial intelligence using a fraction of the computations and power requirements by modeling

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Pasquale Minervini; Sebastian Riedel; Pontus Stenetorp; Edward Grefenstette; Tim Rocktäschel

Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Gustav Sourek; Filip Zelezny; Ondrej Kuzelka

We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode relational learning scenarios. When presented with relational data, such as various forms of graphs, the program interpreter dynamically unfolds differentiable computational graphs to be used for the program parameter

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Simone Scardapane; Indro Spinelli; Paolo Di Lorenzo

The aim of this work is to develop a fully-distributed algorithmic framework for training graph convolutional networks (GCNs). The proposed method is able to exploit the meaningful relational structure of the input data, which are collected by a set of agents that communicate over a sparse network topology. After formulating the centralized GCN training problem, we first show how to make inference

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-13
Blaine Rister; Daniel L. Rubin

Neuron death is a complex phenomenon with implications for model trainability, but until recently it was measured only empirically. Recent articles have claimed that, as the depth of a rectifier neural network grows to infinity, the probability of finding a valid initialization decreases to zero. In this work, we provide a simple and rigorous proof of that result. Then, we show what happens when the

更新日期：2020-07-14
• arXiv.cs.NE Pub Date : 2020-07-10
Antoine Cully

Quality-Diversity (QD) optimisation is a new family of learning algorithms that aims at generating collections of diverse and high-performing solutions. Among those algorithms, MAP-Elites is a simple yet powerful approach that has shown promising results in numerous applications. In this paper, we introduce a novel algorithm named Multi-Emitter MAP-Elites (ME-MAP-Elites) that improves the quality,

更新日期：2020-07-13
• arXiv.cs.NE Pub Date : 2020-07-10
Rustam; Agus Yodi Gunawan; Made Tri Ari Penia Kresnowati

This paper examines the use of artificial neural network approach in identifying the origin of clove buds based on metabolites composition. Generally, large data sets are critical for accurate identification. Machine learning with large data sets lead to precise identification based on origins. However, clove buds uses small data sets due to lack of metabolites composition and their high cost of extraction

更新日期：2020-07-13
• arXiv.cs.NE Pub Date : 2020-07-10
Anh Bui; Trung Le; He Zhao; Paul Montague; Olivier deVel; Tamas Abraham; Dinh Phung

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges as the most successful method that consistently resists a wide range of attacks. In this work, based on an observation from a previous study that the representations

更新日期：2020-07-13
• arXiv.cs.NE Pub Date : 2020-07-10
William F. Podlaski; Christian K. Machens

Learning depends on changes in synaptic connections deep inside the brain. In multilayer networks, these changes are triggered by error signals fed back from the output, generally through a stepwise inversion of the feedforward processing steps. The gold standard for this process -- backpropagation -- works well in artificial neural networks, but is biologically implausible. Several recent proposals

更新日期：2020-07-13
• arXiv.cs.NE Pub Date : 2020-07-03

In this brief paper, a learning algorithm is developed for Deep Learning Neuro-Skin Neural Network to improve their learning properties. Neuroskin is a new type of neural network presented recently by the authors. It is comprised of a cellular membrane which has a neuron attached to each cell. The neuron is the cells nucleus. A neuroskin is modelled using finite elements. Each element of the finite

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09

Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with conventional backpropagation techniques. In spite of the significant progress made in training conventional deep neural networks (DNNs), training methods for SNNs

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-06-27
Han Zhang; Jialin Liu; Xin Yao

The reliable facility location problem (RFLP) is an important research topic of operational research and plays a vital role in the decision-making and management of modern supply chain and logistics. Through solving RFLP, the decision-maker can obtain reliable location decisions under the risk of facilities' disruptions or failures. In this paper, we propose a novel model for the RFLP. Instead of assuming

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Lorenzo Federici; Boris Benedikter; Alessandro Zavoli

This paper presents the main characteristics of the evolutionary optimization code named EOS, Evolutionary Optimization at Sapienza, and its successful application to challenging, real-world space trajectory optimization problems. EOS is a global optimization algorithm for constrained and unconstrained problems of real-valued variables. It implements a number of improvements to the well-known Differential

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Colin White; Willie Neiswanger; Sam Nolen; Yash Savani

Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by encoding the adjacency matrix and list of operations as a set of hyperparameters. Recent work has demonstrated that even small changes to the way each architecture is encoded

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-04
Sungsoo Ahn; Junsu Kim; Hankook Lee; Jinwoo Shin

De novo molecular design attempts to search over the chemical space for molecules with the desired property. Recently, deep learning has gained considerable attention as a promising approach to solve the problem. In this paper, we propose genetic expert-guided learning (GEGL), a simple yet novel framework for training a deep neural network (DNN) to generate highly-rewarding molecules. Our main idea

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Jonas D. Hasbach; Maren Bennewitz

Human-swarm interaction (HSI) is an active research challenge in the realms of swarm robotics and human-factors engineering. Here we apply a cognitive systems engineering perspective and introduce a neuro-inspired joint systems theory of HSI. The mindset defines predictions for adaptive, robust and scalable HSI dynamics and therefore has the potential to inform human-swarm loop design.

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Victor-Bogdan Popescu; Krishna Kanhaiya; Iulian Năstac; Eugen Czeizler; Ion Petre

Control theory has seen recently impactful applications in network science, especially in connections with applications in network medicine. A key topic of research is that of finding minimal external interventions that offer control over the dynamics of a given network, a problem known as network controllability. We propose in this article a new solution for this problem based on genetic algorithms

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Ahmed Hallawa; Thorsten Born; Anke Schmeink; Guido Dartmann; Arne Peine; Lukas Martin; Giovanni Iacca; Gusz Eiben; Gerd Ascheid

In this work, we propose a novel approach for reinforcement learning driven by evolutionary computation. Our algorithm, dubbed as Evolutionary-Driven Reinforcement Learning (evo-RL), embeds the reinforcement learning algorithm in an evolutionary cycle, where we distinctly differentiate between purely evolvable (instinctive) behaviour versus purely learnable behaviour. Furthermore, we propose that this

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-09
Colby L. Wight; Jia Zhao

Phase field models, in particular, the Allen-Cahn type and Cahn-Hilliard type equations, have been widely used to investigate interfacial dynamic problems. Designing accurate, efficient, and stable numerical algorithms for solving the phase field models has been an active field for decades. In this paper, we focus on using the deep neural network to design an automatic numerical solver for the Allen-Cahn

更新日期：2020-07-10
• arXiv.cs.NE Pub Date : 2020-07-08
Pedro Carvalho; Nuno Lourenço; Filipe Assunção; Penousal Machado

The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state of the art automatic methods exist that make the search for a good learning rate easier. While these techniques are effective and have yielded good results over

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-08

We recently proposed the S4NN algorithm, essentially an adaptation of backpropagation to multilayer spiking neural networks that use simple non-leaky integrate-and-fire neurons and a form of temporal coding known as time-to-first-spike coding. With this coding scheme, neurons fire at most once per stimulus, but the firing order carries information. Here, we introduce BS4NN, a modification of S4NN in

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-08
Hao Wang; Diederick Vermetten; Furong Ye; Carola Doerr; Thomas Bäck

We propose IOHanalyzer, a new software for analyzing the empirical performance of iterative optimization heuristics (IOHs) such as local search algorithms, genetic and evolutionary algorithms, Bayesian optimization algorithms, and similar optimizers. Implemented in R and C++, IOHanalyzer is available on CRAN. It provides a platform for analyzing and visualizing the performance of IOHs on real-valued

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-08
Kaan Yilmaz; Neil Yorke-Smith

In line with the growing trend of using machine learning to improve solving of combinatorial optimisation problems, one promising idea is to improve node selection within a mixed integer programming branch-and-bound tree by using a learned policy. In contrast to previous work using imitation learning, our policy is focused on learning which of a node's children to select. We present an offline method

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-07
Anya E. Vostinar; Barbara Z. Johnson; Kevin Connors

The understanding and acceptance of evolution by natural selection has become a difficult issue in many parts of the world, particularly the United States of America. The use of games to improve intuition about evolution via natural selection is promising but can be challenging. We propose the use of modifications to commercial games using artificial life techniques to 'stealth teach' about evolution

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-07
Lakshay Chauhan; John Alberg; Zachary C. Lipton

On a periodic basis, publicly traded companies report fundamentals, financial data including revenue, earnings, debt, among others. Quantitative finance research has identified several factors, functions of the reported data that historically correlate with stock market performance. In this paper, we first show through simulation that if we could select stocks via factors calculated on future fundamentals

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-07
E. Paxon Frady; Spencer Kent; Bruno A. Olshausen; Friedrich T. Sommer

The ability to encode and manipulate data structures with distributed neural representations could qualitatively enhance the capabilities of traditional neural networks by supporting rule-based symbolic reasoning, a central property of cognition. Here we show how this may be accomplished within the framework of Vector Symbolic Architectures (VSA) (Plate, 1991; Gayler, 1998; Kanerva, 1996), whereby

更新日期：2020-07-09
• arXiv.cs.NE Pub Date : 2020-07-07
Andrei Ivanov; Ilya Agapov

This paper presents a novel approach for constructing neural networks which model charged particle beam dynamics. In our approach, the Taylor maps arising in the representation of dynamics are mapped onto the weights of a polynomial neural network. The resulting network approximates the dynamical system with perfect accuracy prior to training and provides a possibility to tune the network weights on

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Haowen Fang; Amar Shrestha; Qinru Qiu

There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural network has drawn attention as it enables low power consumption by encoding and processing information as sparse spike events, which can be exploited for event-driven

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Thomas Bartz-Beielstein; Carola Doerr; Jakob Bossek; Sowmya Chandrasekaran; Tome Eftimov; Andreas Fischbach; Pascal Kerschke; Manuel Lopez-Ibanez; Katherine M. Malan; Jason H. Moore; Boris Naujoks; Patryk Orzechowski; Vanessa Volz; Markus Wagner; Thomas Weise

This survey compiles ideas and recommendations from more than a dozen researchers with different backgrounds and from different institutes around the world. Promoting best practice in benchmarking is its main goal. The article discusses eight essential topics in benchmarking: clearly stated goals, well-specified problems, suitable algorithms, adequate performance measures, thoughtful analysis, effective

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
George T. Hall; Pietro Simone Oliveto; Dirk Sudholt

Recent work has shown that the ParamRLS and ParamILS algorithm configurators can tune some simple randomised search heuristics for standard benchmark functions in linear expected time in the size of the parameter space. In this paper we prove a linear lower bound on the expected time to optimise any parameter tuning problem for ParamRLS, ParamILS as well as for larger classes of algorithm configurators

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Yujia Li; Felix Gimeno; Pushmeet Kohli; Oriol Vinyals

We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Anh Tran; Mike Eldred; Scott McCann; Yan Wang

Bayesian optimization (BO) is an efficient and flexible global optimization framework that is applicable to a very wide range of engineering applications. To leverage the capability of the classical BO, many extensions, including multi-objective, multi-fidelity, parallelization, latent-variable model, have been proposed to improve the limitation of the classical BO framework. In this work, we propose

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Kaifeng Bi; Lingxi Xie; Xin Chen; Longhui Wei; Qi Tian

There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and enlarge the search space to contain more than $10^{160}$ candidates. In the new space, most existing differentiable search methods can fail dramatically. We then propose

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Bubacarr Bah; Jannis Kurtz

We study deep neural networks with binary activation functions (BDNN), i.e. the activation function only has two states. We show that the BDNN can be reformulated as a mixed-integer linear program which can be solved to global optimality by classical integer programming solvers. Additionally, a heuristic solution algorithm is presented and we study the model under data uncertainty, applying a two-stage

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Kieran Greer

This paper describes an entropy equation, but one that should be used for measuring energy and not information. In relation to the human brain therefore, both of these quantities can be used to represent the stored information. The human brain makes use of energy efficiency to form its structures, which is likely to be linked to the neuron wiring. This energy efficiency can also be used as the basis

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-07
Zihan Pan; Malu Zhang; Jibin Wu; Haizhou Li

Inspired by the mammal's auditory localization pathway, in this paper we propose a pure spiking neural network (SNN) based computational model for precise sound localization in the noisy real-world environment, and implement this algorithm in a real-time robotic system with a microphone array. The key of this model relies on the MTPC scheme, which encodes the interaural time difference (ITD) cues into

更新日期：2020-07-08
• arXiv.cs.NE Pub Date : 2020-07-06
Elias Najarro; Sebastian Risi

Lifelong learning and adaptability are two defining aspects of biological agents. Modern reinforcement learning (RL) approaches have shown significant progress in solving complex tasks, however once training is concluded, the found solutions are typically static and incapable of adapting to new information or perturbations. While it is still not completely understood how biological brains learn and

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-06
Théo LaduneIETR; Pierrick PhilippeIETR; Wassim HamidoucheIETR; Lu ZhangIETR; Olivier DéforgesIETR

In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable competition among several coding modes. The proposed ModeNet learns and conveys a pixel-wise partitioning of the frame, used to assign each pixel to the most suited coding mode. ModeNet is trained alongside the different coding

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-04
Shihao Song; Anup Das

Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High voltages required to operate certain NVMs such as phase-change memory (PCM) can accelerate aging in a neuron's CMOS circuit, thereby reducing the lifetime of neuromorphic

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-04
Weiyu Chen; Hisao Ishibuhci; Ke Shang

Subset selection is a popular topic in recent years and a number of subset selection methods have been proposed. Among those methods, hypervolume subset selection is widely used. Greedy hypervolume subset selection algorithms can achieve good approximations to the optimal subset. However, when the candidate set is large (e.g., an unbounded external archive with a large number of solutions), the algorithm

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-06
Samiran Ganguly; Avik W. Ghosh

Biologically inspired recurrent neural networks, such as reservoir computers are of interest in designing spatio-temporal data processors from a hardware point of view due to the simple learning scheme and deep connections to Kalman filters. In this work we discuss using in-depth simulation studies a way to construct hardware reservoir computers using an analog stochastic neuron cell built from a low

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-05
Michael Chang; Sidhant Kaushik; S. Matthew Weinberg; Thomas L. Griffiths; Sergey Levine

This paper seeks to establish a framework for directing a society of simple, specialized, self-interested agents to solve what traditionally are posed as monolithic single-agent sequential decision problems. What makes it challenging to use a decentralized approach to collectively optimize a central objective is the difficulty in characterizing the equilibrium strategy profile of non-cooperative games

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-04
Yiwen Guo; Long Chen; Yurong Chen; Changshui Zhang

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-04
Zijian Jiang; Jianwen Zhou; Haiping Huang

Artificial neural networks can achieve impressive performances, and even outperform humans in some specific tasks. Nevertheless, unlike biological brains, the artificial neural networks suffer from tiny perturbations in sensory input, under various kinds of adversarial attacks. It is therefore necessary to study the origin of the adversarial vulnerability. Here, we establish a fundamental relationship

更新日期：2020-07-07
• arXiv.cs.NE Pub Date : 2020-07-02
Farshid Varno; Lucas May Petry; Lisa Di Jorio; Stan Matwin

Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this process. With a focus on classification, we show that current fine-tuning techniques make the pretrained models catastrophically forget the transferred knowledge even before anything about the new task is learned. Such rapid

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-03
Hao Wang; Hao He; Dina Katabi

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one often needs to transfer disease analysis and prediction across patients of different ages, where age acts as a continuous domain index. Such tasks are challenging for

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-03
Sören Dittmer; Carola-Bibiane Schönlieb; Peter Maass

We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals. The training is solely based on samples of noisy data and examples of noise, which -- critically -- do not need to come in pairs. We only need the assumption that the noise is independent and additive (although we describe how this can be extended). The method rests

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-03
Bin Wang; Bing Xue; Mengjie Zhang

Deep convolutional neural networks have demonstrated promising performance on image classification tasks, but the manual design process becomes more and more complex due to the fast depth growth and the increasingly complex topologies of convolutional neural networks. As a result, neural architecture search has emerged to automatically design convolutional neural networks that outperform handcrafted

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-02
Yimeng Min

Most algorithms used in neural networks(NN)-based leaning tasks are strongly affected by the choices of initialization. Good initialization can avoid sub-optimal solutions and alleviate saturation during training. However, designing improved initialization strategies is a difficult task and our understanding of good initialization is still very primitive. Here, we propose persistent neurons, a strategy

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-02
Yifei Wang; Dan Peng; Furui Liu; Zhenguo Li; Zhitang Chen; Jiansheng Yang

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our

更新日期：2020-07-06
• arXiv.cs.NE Pub Date : 2020-07-02
Jibin Wu; Chenglin Xu; Daquan Zhou; Haizhou Li; Kay Chen Tan

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the training of deep SNNs is not straightforward. In this paper, we propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern

更新日期：2020-07-03
• arXiv.cs.NE Pub Date : 2020-07-02
Boyu Zhang; A. K. Qin; Hong Pan; Timos Sellis

Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. The training set is used for training the model while the validation set is used to estimate the generalization performance of the trained model as the training proceeds to avoid over-fitting. There

更新日期：2020-07-03
• arXiv.cs.NE Pub Date : 2020-07-02
Elena Raponi; Hao Wang; Mariusz Bujny; Simonetta Boria; Carola Doerr

Bayesian Optimization (BO) is a surrogate-assisted global optimization technique that has been successfully applied in various fields, e.g., automated machine learning and design optimization. Built upon a so-called infill-criterion and Gaussian Process regression (GPR), the BO technique suffers from a substantial computational complexity and hampered convergence rate as the dimension of the search

更新日期：2020-07-03
Contents have been reproduced by permission of the publishers.

down
wechat
bug