AI 安全与对齐 · 全部实体（第 14 / 100 页）

本页收录第 1301–1400 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Activation degree thresholds and expressiveness of polynomial neural networks
  We study the expressive power of deep polynomial neural networks through the geometry of their neurovariety. We introduce the notion of the activation degree threshold of a network architecture to express when the dimension of the neurovariety achieves its the…
  arxiv Bella Finkel, Jose Israel Rodriguez, Chenxi Wu, Thomas Yahl 2024-08-08T16:28:56Z 置信度 0.78 cs.LGcs.NEmath.AGstat.ML
• Physics-Informed Neural Network Super Resolution for Advection-Diffusion Models
  Physics-informed neural networks (NN) are an emerging technique to improve spatial resolution and enforce physical consistency of data from physics models or satellite observations. A super-resolution (SR) technique is explored to reconstruct high-resolution i…
  arxiv Chulin Wang, Eloisa Bentivegna, Wang Zhou, Levente Klein 等 2020-11-04T19:56:11Z 置信度 0.78 cs.CVphysics.geo-ph
• Training End-to-End Analog Neural Networks with Equilibrium Propagation
  We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent. In these analog neural networks, the weights to be adjusted are implemented by the conductances of programmable resistive devices such as memristors [Ch…
  arxiv Jack Kendall, Ross Pantone, Kalpana Manickavasagam, Yoshua Bengio 等 2020-06-02T23:38:35Z 置信度 0.78 cs.NEcs.LG
• Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Series
  Time series models with recurrent neural networks (RNNs) can have high accuracy but are unfortunately difficult to interpret as a result of feature-interactions, temporal-interactions, and non-linear transformations. Interpretability is important in domains li…
  arxiv Asif Rahman, Yale Chang, Jonathan Rubin 2021-09-15T22:30:19Z 置信度 0.78 cs.LGcs.AI
• Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
  The behavior of neural networks still remains opaque, and a recently widely noted phenomenon is that networks often achieve similar performance when initialized with different random parameters. This phenomenon has attracted significant attention in measuring …
  arxiv Yiting Chen, Zhanpeng Zhou, Junchi Yan 2023-10-10T16:27:12Z 置信度 0.78 cs.LGcs.AI
• Leabra7: a Python package for modeling recurrent, biologically-realistic neural networks
  Emergent is a software package that uses the AdEx neural dynamics model and LEABRA learning algorithm to simulate and train arbitrary recurrent neural network architectures in a biologically-realistic manner. We present Leabra7, a complementary Python library …
  arxiv C. Daniel Greenidge, Noam Miller, Kenneth A. Norman 2018-09-11T21:09:25Z 置信度 0.78 cs.NEq-bio.NC
• EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks
  A vast majority of spiking neural networks (SNNs) are trained based on inductive biases that are not necessarily a good fit for several critical tasks that require low-latency and power efficiency. Inferring brain behavior based on the associated electroenchep…
  arxiv Xi Chen, Siwei Mai, Konstantinos Michmizos 2023-04-15T23:30:17Z 置信度 0.78 cs.NEcs.AIcs.HCcs.LG
• Neural networks with dynamical coefficients and adjustable connections on the basis of integrated backpropagation
  We consider artificial neurons which will update their weight coefficients with an internal rule based on backpropagation, rather than using it as an external training procedure. To achieve this we include the backpropagation error estimate as a separate entit…
  arxiv M. N. Nazarov 2018-05-19T07:34:33Z 置信度 0.78 cs.NE
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
  In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' …
  arxiv Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst 2016-06-30T07:42:13Z 置信度 0.78 cs.LGstat.ML
• Clinical Information Extraction via Convolutional Neural Network
  We report an implementation of a clinical information extraction tool that leverages deep neural network to annotate event spans and their attributes from raw clinical notes and pathology reports. Our approach uses context words and their part-of-speech tags a…
  arxiv Peng Li, Heng Huang 2016-03-30T20:57:07Z 置信度 0.78 cs.LGcs.CLcs.NE
• Statistically Significant Stopping of Neural Network Training
  The general approach taken when training deep learning classifiers is to save the parameters after every few iterations, train until either a human observer or a simple metric-based heuristic decides the network isn't learning anymore, and then backtrack and p…
  arxiv J. K. Terry, Mario Jayakumar, Kusal De Alwis 2021-03-01T18:51:16Z 置信度 0.78 cs.LGcs.AIcs.CVcs.NE
• When saliency goes off on a tangent: Interpreting Deep Neural Networks with nonlinear saliency maps
  A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development of any crucial safety protocols. To date, no method exist that can provide full …
  arxiv Jan Rosenzweig, Zoran Cvetkovic, Ivana Rosenzweig 2021-10-13T11:12:57Z 置信度 0.78 cs.LGstat.ML
• Using Program Induction to Interpret Transition System Dynamics
  Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to learn high level func…
  arxiv Svetlin Penkov, Subramanian Ramamoorthy 2017-07-26T12:49:04Z 置信度 0.78 cs.AI
• Exponential Lag Synchronization of Cohen-Grossberg Neural Networks with Discrete and Distributed Delays on Time Scales
  In this article, we investigate exponential lag synchronization results for the Cohen-Grossberg neural networks (C-GNNs) with discrete and distributed delays on an arbitrary time domain by applying feedback control. We formulate the problem by using the time s…
  arxiv Vipin Kumar, Jan Heiland, Peter Benner 2022-09-01T12:25:25Z 置信度 0.78 math.OC
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
  Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets. Moreover, due to DNNs' rich …
  arxiv Zhilu Zhang, Mert R. Sabuncu 2018-05-20T23:01:49Z 置信度 0.78 cs.LGcs.CVstat.ML
• The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
  Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvexity in their loss landscapes. In this work, we show that these common perception…
  arxiv Wei Hu, Lechao Xiao, Ben Adlam, Jeffrey Pennington 2020-06-25T17:42:49Z 置信度 0.78 cs.LGcs.NEstat.ML
• Encoding Involutory Invariances in Neural Networks
  In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures that embed a special…
  arxiv Anwesh Bhattacharya, Marios Mattheakis, Pavlos Protopapas 2021-06-07T16:07:15Z 置信度 0.78 cs.LGcs.AIcs.NE
• Inducing Causal Structure for Interpretable Neural Networks
  In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange intervention traini…
  arxiv Atticus Geiger, Zhengxuan Wu, Hanson Lu, Josh Rozner 等 2021-12-01T21:07:01Z 置信度 0.78 cs.LG
• Compact Deep Convolutional Neural Networks With Coarse Pruning
  The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel leve…
  arxiv Sajid Anwar, Wonyong Sung 2016-10-30T11:57:20Z 置信度 0.78 cs.LGcs.NE
• NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks
  The advancements of deep neural networks (DNNs) have led to their deployment in diverse settings, including safety and security-critical applications. As a result, the characteristics of these models have become sensitive intellectual properties that require p…
  arxiv Mahya Morid Ahmadi, Lilas Alrahis, Alessio Colucci, Ozgur Sinanoglu 等 2022-06-01T11:10:00Z 置信度 0.78 cs.CRcs.LG
• Neural Anisotropy Directions
  In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. To that end, we start by focusing on a very simple problem, i.e., classifying a class of linearly separable distributions, and show that, depending…
  arxiv Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard 2020-06-17T08:36:28Z 置信度 0.78 cs.LGcs.CVstat.ML
• IS2N: Intent-Driven Security Software-Defined Network with Blockchain
  Software-defined network (SDN) is characterized by its programmability, flexibility, and the separation of control and data planes. However, SDN still have many challenges, particularly concerning the security of network information synchronization and network…
  arxiv Yanbo Song, Tao Feng, Chungang Yang, Xinru Mi 等 2023-08-09T00:53:28Z 置信度 0.78 cs.NI
• A recurrent neural network without chaos
  We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable a…
  arxiv Thomas Laurent, James von Brecht 2016-12-19T14:59:14Z 置信度 0.78 cs.NEcs.CLcs.LG
• DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling
  Graph Neural Networks (GNNs) have proven effective in various medical imaging applications, such as automated disease diagnosis. However, due to the local neighborhood aggregation paradigm in message passing which characterizes these models, they inherently su…
  arxiv K. Mancini, I. Rekik 2024-09-29T09:01:22Z 置信度 0.78 cs.LGcs.SI
• Neural Architecture Search in Graph Neural Networks
  Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes (and edges) follow no a…
  arxiv Matheus Nunes, Gisele L. Pappa 2020-07-31T21:04:24Z 置信度 0.78 cs.NEcs.LG
• Improving the Interpretability of fMRI Decoding using Deep Neural Networks and Adversarial Robustness
  Deep neural networks (DNNs) are being increasingly used to make predictions from functional magnetic resonance imaging (fMRI) data. However, they are widely seen as uninterpretable "black boxes", as it can be difficult to discover what input information is use…
  arxiv Patrick McClure, Dustin Moraczewski, Ka Chun Lam, Adam Thomas 等 2020-04-23T12:56:24Z 置信度 0.78 cs.LGcs.CVq-bio.NCstat.ML
• Neural Network Degeneration and its Relationship to the Brain
  This report discusses the application of neural networks (NNs) as small segments of the brain. The networks representing the biological connectome are altered both spatially and temporally. The degradation techniques applied here are "weight degradation", "wei…
  arxiv Jacob Adamczyk 2020-07-31T19:42:23Z 置信度 0.78 q-bio.NCcs.NE
• SCNN: Swarm Characteristic Neural Network
  Deep learning is a powerful approach with good performance on many different tasks. However, these models often require massive computational resources. It is a worrying trend that we increasingly need models that work well on more complex problems. In this pa…
  arxiv Ha-Thanh Nguyen, Le-Minh Nguyen 2021-03-08T01:26:50Z 置信度 0.78 cs.NE
• Evolving Deep Neural Networks for Collaborative Filtering
  Collaborative Filtering (CF) is widely used in recommender systems to model user-item interactions. With the great success of Deep Neural Networks (DNNs) in various fields, advanced works recently have proposed several DNN-based models for CF, which have been …
  arxiv Yuhan Fang, Yuqiao Liu, Yanan Sun 2021-11-15T13:57:31Z 置信度 0.78 cs.NE
• Learning Operations on a Stack with Neural Turing Machines
  Multiple extensions of Recurrent Neural Networks (RNNs) have been proposed recently to address the difficulty of storing information over long time periods. In this paper, we experiment with the capacity of Neural Turing Machines (NTMs) to deal with these long…
  arxiv Tristan Deleu, Joseph Dureau 2016-12-02T20:31:44Z 置信度 0.78 cs.LG
• The Asymptotic Performance of Linear Echo State Neural Networks
  In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive deterministic equival…
  arxiv Romain Couillet, Gilles Wainrib, Harry Sevi, Hafiz Tiomoko Ali 2016-03-25T10:27:00Z 置信度 0.78 cs.LGcs.NEmath.PR
• Control of synaptic plasticity in neural networks
  The brain is a nonlinear and highly Recurrent Neural Network (RNN). This RNN is surprisingly plastic and supports our astonishing ability to learn and execute complex tasks. However, learning is incredibly complicated due to the brain's nonlinear nature and th…
  arxiv Mohammad Modiri 2023-03-10T13:36:31Z 置信度 0.78 cs.NEcs.LGcs.RO
• Training neural audio classifiers with few data
  We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical networks, (iii) tran…
  arxiv Jordi Pons, Joan Serrà, Xavier Serra 2018-10-24T09:59:17Z 置信度 0.78 cs.SDcs.AIcs.LGeess.AS
• Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks
  Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the training data and n…
  arxiv Hojjat Salehinejad, Shahrokh Valaee 2019-02-07T02:21:40Z 置信度 0.78 cs.NEcs.LG
• Option Pricing Using Bayesian Neural Networks
  Options have provided a field of much study because of the complexity involved in pricing them. The Black-Scholes equations were developed to price options but they are only valid for European styled options. There is added complexity when trying to price Amer…
  arxiv Michael Maio Pires, Tshilidzi Marwala 2007-05-11T15:55:31Z 置信度 0.78 cs.CEcs.NE
• Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics
  Deep equilibrium (DEQ) models replace the multiple-layer stacking of conventional deep networks with a fixed-point iteration of a single-layer transformation. Having been demonstrated to be competitive in a variety of real-world scenarios, the adversarial robu…
  arxiv Zonghan Yang, Peng Li, Tianyu Pang, Yang Liu 2023-06-02T10:49:35Z 置信度 0.78 cs.LGstat.ML
• Cross-Frequency Coupling Increases Memory Capacity in Oscillatory Neural Networks
  An open problem in neuroscience is to explain the functional role of oscillations in neural networks, contributing, for example, to perception, attention, and memory. Cross-frequency coupling (CFC) is associated with information integration across populations …
  arxiv Connor Bybee, Alexander Belsten, Friedrich T. Sommer 2022-04-05T17:13:36Z 置信度 0.78 q-bio.NCcs.NE
• Criticality in Neural Network Function Space through Wilsonian Fixed Points and Finite-Width Corrections
  Neural networks can be studied not only as parameterized computational models but also as probability distributions over functions. In this paper we develop a Wilsonian interpretation of criticality in the neural network-quantum field theory correspondence, tr…
  arxiv Eric Howard, Iftekher S. Chowdhury, Hardique Dasore, Hom Nath Dhungana 2026-08-03T22:56:06Z 置信度 0.78 cond-mat.dis-nnquant-ph
• Nonparametric Weight Initialization of Neural Networks via Integral Representation
  A new initialization method for hidden parameters in a neural network is proposed. Derived from the integral representation of the neural network, a nonparametric probability distribution of hidden parameters is introduced. In this proposal, hidden parameters …
  arxiv Sho Sonoda, Noboru Murata 2013-12-23T03:23:04Z 置信度 0.78 cs.LGcs.NE
• Towards Comparative Physical Interpretation of Spatial Variability Aware Neural Networks: A Summary of Results
  Given Spatial Variability Aware Neural Networks (SVANNs), the goal is to investigate mathematical (or computational) models for comparative physical interpretation towards their transparency (e.g., simulatibility, decomposability and algorithmic transparency).…
  arxiv Jayant Gupta, Carl Molnar, Gaoxiang Luo, Joe Knight 等 2021-10-29T15:40:42Z 置信度 0.78 cs.LGcs.AI
• Learning across scales - A multiscale method for Convolution Neural Networks
  In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and learning as controlling…
  arxiv Eldad Haber, Lars Ruthotto, Elliot Holtham, Seong-Hwan Jun 2017-03-06T18:15:40Z 置信度 0.78 cs.NEcs.CV
• Enhancing Information Dissemination in Dynamic Wireless Network using Stability and Beamforming
  Mobility causes network structures to change. In PSNs where underlying network structure is changing rapidly, we are interested in studying how information dissemination can be enhanced in a sparse disconnected network where nodes lack the global knowledge abo…
  arxiv Rachit Agarwal, Vincent Gauthier, Monique Becker 2012-10-19T12:02:32Z 置信度 0.78 cs.NI
• Comparative study of Financial Time Series Prediction by Artificial Neural Network with Gradient Descent Learning
  Financial forecasting is an example of a signal processing problem which is challenging due to Small sample sizes, high noise, non-stationarity, and non-linearity,but fast forecasting of stock market price is very important for strategic business planning.Pres…
  arxiv Arka Ghosh 2011-11-21T16:58:58Z 置信度 0.78 cs.NEcs.AI
• Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz
  This paper demonstrates a method for tensorizing neural networks based upon an efficient way of approximating scale invariant quantum states, the Multi-scale Entanglement Renormalization Ansatz (MERA). We employ MERA as a replacement for the fully connected la…
  arxiv Andrew Hallam, Edward Grant, Vid Stojevic, Simone Severini 等 2017-11-09T12:55:59Z 置信度 0.78 cs.NEcs.CVquant-ph
• Understanding the Role of Individual Units in a Deep Neural Network
  Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically i…
  arxiv David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza 等 2020-09-10T17:59:10Z 置信度 0.78 cs.CVcs.LGcs.NE
• Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
  We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators. Our key observation is that unlike in standard abstract interpretation (AI), typically used to over-approximate all reachable program states,…
  arxiv Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev 2021-10-14T19:08:27Z 置信度 0.78 cs.LGcs.AI
• Training of spiking neural networks based on information theoretic costs
  Spiking neural network is a type of artificial neural network in which neurons communicate between each other with spikes. Spikes are identical Boolean events characterized by the time of their arrival. A spiking neuron has internal dynamics and responds to th…
  arxiv Oleg Y. Sinyavskiy 2016-02-15T17:21:00Z 置信度 0.78 cs.NEq-bio.NC
• On the Depth of Monotone ReLU Neural Networks and ICNNs
  We study two models of ReLU neural networks: monotone networks (ReLU$^+$) and input convex neural networks (ICNN). Our focus is on expressivity, mostly in terms of depth, and we prove the following lower bounds. For the maximum function MAX$_n$ computing the m…
  arxiv Egor Bakaev, Florestan Brunck, Christoph Hertrich, Daniel Reichman 等 2025-05-09T16:19:34Z 置信度 0.78 cs.LGcs.DMcs.NEmath.CO
• Neural Voice Puppetry: Audio-driven Facial Reenactment
  We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the sou…
  arxiv Justus Thies, Mohamed Elgharib, Ayush Tewari, Christian Theobalt 等 2019-12-11T19:00:18Z 置信度 0.78 cs.CVcs.GR
• Feedforward Neural Networks with Diffused Nonlinear Weight Functions
  In this paper, feedforward neural networks are presented that have nonlinear weight functions based on look--up tables, that are specially smoothed in a regularization called the diffusion. The idea of such a type of networks is based on the hypothesis that th…
  arxiv Artur Rataj 2003-10-27T14:27:14Z 置信度 0.78 cs.NE
• Training a Feed-forward Neural Network with Artificial Bee Colony Based Backpropagation Method
  Back-propagation algorithm is one of the most widely used and popular techniques to optimize the feed forward neural network training. Nature inspired meta-heuristic algorithms also provide derivative-free solution to optimize complex problem. Artificial bee c…
  arxiv Sudarshan Nandy, Partha Pratim Sarkar, Achintya Das 2012-09-12T10:25:51Z 置信度 0.78 cs.NEcs.AI
• Channel Estimation for Visible Light Communications Using Neural Networks
  Visible light communications (VLC) is an emerging field in technology and research. Estimating the channel taps is a major requirement for designing reliable communication systems. Due to the nonlinear characteristics of the VLC channel those parameters cannot…
  arxiv Anil Yesilkaya, Onur Karatalay, Arif Selcuk Ogrenci, Erdal Panayirci 2018-05-21T14:02:03Z 置信度 0.78 cs.NEcs.ITeess.SP
• Quality of Service in Quantum Networks
  In the coming years, quantum networks will allow quantum applications to thrive thanks to the new opportunities offered by end-to-end entanglement of qubits on remote hosts via quantum repeaters. On a geographical scale, this will lead to the dawn of the Quant…
  arxiv Claudio Cicconetti, Marco Conti, Andrea Passarella 2022-04-20T15:23:50Z 置信度 0.78 quant-phcs.NI
• Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena
  In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the model perfectly fits th…
  arxiv Matt Emschwiller, David Gamarnik, Eren C. Kızıldağ, Ilias Zadik 2020-03-23T20:09:31Z 置信度 0.78 stat.MLcs.LGcs.NEmath.ST
• SGAD: Soft-Guided Adaptively-Dropped Neural Network
  Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of va…
  arxiv Zhisheng Wang, Fangxuan Sun, Jun Lin, Zhongfeng Wang 等 2018-07-04T02:23:10Z 置信度 0.78 cs.LGcs.CVcs.NEstat.ML
• Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations
  This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes it possible to update…
  arxiv Dmitry Ivanov, Mikhail Kiselev, Denis Larionov 2022-01-07T18:09:23Z 置信度 0.78 cs.LGcs.NE
• Deep Neural Network Optimized to Resistive Memory with Nonlinear Current-Voltage Characteristics
  Artificial Neural Network computation relies on intensive vector-matrix multiplications. Recently, the emerging nonvolatile memory (NVM) crossbar array showed a feasibility of implementing such operations with high energy efficiency, thus there are many works …
  arxiv Hyungjun Kim, Taesu Kim, Jinseok Kim, Jae-Joon Kim 2017-03-30T19:04:55Z 置信度 0.78 cs.ETcs.NE
• Analyze and Design Network Architectures by Recursion Formulas
  The effectiveness of shortcut/skip-connection has been widely verified, which inspires massive explorations on neural architecture design. This work attempts to find an effective way to design new network architectures. It is discovered that the main differenc…
  arxiv Yilin Liao, Hao Wang, Zhaoran Liu, Haozhe Li 等 2021-08-18T06:53:30Z 置信度 0.78 cs.LGcs.AI
• Network Inversion of Convolutional Neural Nets
  Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability and reliability, esp…
  arxiv Pirzada Suhail, Amit Sethi 2024-07-25T12:53:21Z 置信度 0.78 cs.LGcs.CV
• The Probabilistic Fault Tolerance of Neural Networks in the Continuous Limit
  The loss of a few neurons in a brain rarely results in any visible loss of function. However, the insight into what "few" means in this context is unclear. How many random neuron failures will it take to lead to a visible loss of function? In this paper, we ad…
  arxiv El-Mahdi El-Mhamdi, Rachid Guerraoui, Andrei Kucharavy, Sergei Volodin 2019-02-05T14:08:21Z 置信度 0.78 stat.MLcs.DCcs.LGcs.NE
• Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagation
  The timing of individual neuronal spikes is essential for biological brains to make fast responses to sensory stimuli. However, conventional artificial neural networks lack the intrinsic temporal coding ability present in biological networks. We propose a spik…
  arxiv Iulia M. Comsa, Krzysztof Potempa, Luca Versari, Thomas Fischbacher 等 2019-07-30T21:05:18Z 置信度 0.78 cs.NEcs.LGq-bio.NC
• Projectron -- A Shallow and Interpretable Network for Classifying Medical Images
  This paper introduces the `Projectron' as a new neural network architecture that uses Radon projections to both classify and represent medical images. The motivation is to build shallow networks which are more interpretable in the medical imaging domain. Radon…
  arxiv Aditya Sriram, Shivam Kalra, H. R. Tizhoosh 2019-03-15T12:13:23Z 置信度 0.78 cs.CV
• Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
  In this work, we explore the intersection of sparse coding theory and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network architectures. We begin by introducing a novel class of Deep Sparse Coding (DSC) mode…
  arxiv Jianfei Li, Han Feng, Ding-Xuan Zhou 2024-08-10T12:43:55Z 置信度 0.78 cs.LGcs.DScs.ITcs.NE
• Neural Network Solutions of Bosonic Quantum Systems in One Dimension
  Neural networks have been proposed as efficient numerical wavefunction ansatze which can be used to variationally search a wide range of functional forms for ground state solutions. These neural network methods are also advantageous in that more variational pa…
  arxiv Paulo F. Bedaque, Hersh Kumar, Andy Sheng 2023-09-05T16:08:48Z 置信度 0.78 nucl-thcond-mat.dis-nncond-mat.quant-gasquant-ph
• Condensation and evolution of space-time network
  In this work, we try to propose, in a novel way using the Bose and Fermi quantum network approach, a framework studying condensation and evolution of space time network described by the Loop quantum gravity. Considering quantum network connectivity features in…
  arxiv Bi Qiao 2008-09-29T14:31:07Z 置信度 0.78 gr-qc
• Solution of a chaotic neural network at fixed connectivity
  We calculate the moments and response functions of a nonlinear random recurrent neural network in the large-$N$ limit using a diagrammatic technique. Our approach does not require averaging over synaptic weights and gives the first nontrivial term in a $1/\sqr…
  arxiv Albert J. Wakhloo 2026-04-27T07:52:10Z 置信度 0.78 cond-mat.dis-nnq-bio.NC
• Sound Logical Explanations for Mean Aggregation Graph Neural Networks
  Graph neural networks (GNNs) are frequently used for knowledge graph completion. Their black-box nature has motivated work that uses sound logical rules to explain predictions and characterise their expressivity. However, despite the prevalence of GNNs that us…
  arxiv Matthew Morris, Ian Horrocks 2025-10-27T13:23:21Z 置信度 0.78 cs.LGcs.AIcs.LO
• DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
  Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, …
  arxiv Changhao Chen, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni 等 2019-08-11T15:03:24Z 置信度 0.78 cs.LGcs.CVcs.ROstat.ML
• Design Space Exploration of Neural Network Activation Function Circuits
  The widespread application of artificial neural networks has prompted researchers to experiment with FPGA and customized ASIC designs to speed up their computation. These implementation efforts have generally focused on weight multiplication and signal summati…
  arxiv Tao Yang, Yadong Wei, Zhijun Tu, Haolun Zeng 等 2018-09-22T14:57:46Z 置信度 0.78 cs.NE
• Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
  In our previous work [Ma and Chan (2023)], we presented a feedforward unitary equivariant neural network. We proposed three distinct activation functions tailored for this network: a softsign function with a small residue, an identity function, and a Leaky ReL…
  arxiv Pui-Wai Ma 2024-11-17T09:46:52Z 置信度 0.78 cs.LGcs.NE
• Graph Rewriting for Graph Neural Networks
  Given graphs as input, Graph Neural Networks (GNNs) support the inference of nodes, edges, attributes, or graph properties. Graph Rewriting investigates the rule-based manipulation of graphs to model complex graph transformations. We propose that, therefore, (…
  arxiv Adam Machowczyk, Reiko Heckel 2023-05-29T21:48:19Z 置信度 0.78 cs.LGcs.NE
• Quaternion-Valued Convolutional Neural Network Applied for Acute Lymphoblastic Leukemia Diagnosis
  The field of neural networks has seen significant advances in recent years with the development of deep and convolutional neural networks. Although many of the current works address real-valued models, recent studies reveal that neural networks with hypercompl…
  arxiv Marco Aurélio Granero, Cristhian Xavier Hernández, Marcos Eduardo Valle 2021-12-13T14:03:09Z 置信度 0.78 cs.CVcs.LGcs.NE
• Revisiting Neural Activation Coverage for Uncertainty Estimation
  Neural activation coverage (NAC) is a recently-proposed technique for out-of-distribution detection and generalization. We build upon this promising foundation and extend the method to work as an uncertainty estimation technique for already-trained artificial …
  arxiv Benedikt Franke, Nils Förster, Frank Köster, Asja Fischer 等 2026-04-24T08:48:49Z 置信度 0.78 cs.LG
• A Structural Approach to the Design of Domain Specific Neural Network Architectures
  This is a master's thesis concerning the theoretical ideas of geometric deep learning. Geometric deep learning aims to provide a structured characterization of neural network architectures, specifically focused on the ideas of invariance and equivariance of da…
  arxiv Gerrit Nolte 2023-01-23T11:50:57Z 置信度 0.78 cs.LGcs.NE
• A Neural Chaos Model of Multistable Perception
  We present a perception model of ambiguous patterns based on the chaotic neural network and investigate the characteristics through computer simulations. The results induced by the chaotic activity are similar to those of psychophysical experiments and it is d…
  arxiv Natsuki Nagao, Haruhiko Nishimura, Nobuyuki Matsui 2000-02-24T17:52:37Z 置信度 0.78 nlin.CDnlin.AOq-bio
• Decomposing neural networks as mappings of correlation functions
  Understanding the functional principles of information processing in deep neural networks continues to be a challenge, in particular for networks with trained and thus non-random weights. To address this issue, we study the mapping between probability distribu…
  arxiv Kirsten Fischer, Alexandre René, Christian Keup, Moritz Layer 等 2022-02-10T09:30:31Z 置信度 0.78 cond-mat.dis-nnstat.ML
• Exponential Capacity in an Autoencoder Neural Network with a Hidden Layer
  A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the input at the output la…
  arxiv Alireza Alemi, Alia Abbara 2017-05-21T12:13:42Z 置信度 0.78 q-bio.NCcond-mat.dis-nn
• Efficient Computation in Adaptive Artificial Spiking Neural Networks
  Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a computationally and energet…
  arxiv Davide Zambrano, Roeland Nusselder, H. Steven Scholte, Sander Bohte 2017-10-13T08:29:50Z 置信度 0.78 cs.NE
• Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks
  The neurons of artificial neural networks were originally invented when much less was known about biological neurons than is known today. Our work explores a modification to the core neuron unit to make it more parallel to a biological neuron. The modification…
  arxiv Rorry Brenner, Laurent Itti 2025-01-29T22:09:45Z 置信度 0.78 cs.NEcs.LGq-bio.NC
• Sufficient conditions for offline reactivation in recurrent neural networks
  During periods of quiescence, such as sleep, neural activity in many brain circuits resembles that observed during periods of task engagement. However, the precise conditions under which task-optimized networks can autonomously reactivate the same network stat…
  arxiv Nanda H. Krishna, Colin Bredenberg, Daniel Levenstein, Blake A. Richards 等 2025-05-22T17:57:59Z 置信度 0.78 q-bio.NCcs.LGcs.NE
• Training of Deep Learning Neuro-Skin Neural Network
  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 h…
  arxiv Mehrdad Shafiei Dizaji 2020-07-03T18:51:45Z 置信度 0.78 cs.NEcs.LG
• Recurrent Neural Networks With Limited Numerical Precision
  Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations perfor…
  arxiv Joachim Ott, Zhouhan Lin, Ying Zhang, Shih-Chii Liu 等 2016-08-24T17:15:29Z 置信度 0.78 cs.NE
• Neural Network Architecture Search with Differentiable Cartesian Genetic Programming for Regression
  The ability to design complex neural network architectures which enable effective training by stochastic gradient descent has been the key for many achievements in the field of deep learning. However, developing such architectures remains a challenging and res…
  arxiv Marcus Märtens, Dario Izzo 2019-07-03T13:40:02Z 置信度 0.78 cs.NE
• A neural network and iterative optimization hybrid for Dempster-Shafer clustering
  In this paper we extend an earlier result within Dempster-Shafer theory ["Fast Dempster-Shafer Clustering Using a Neural Network Structure," in Proc. Seventh Int. Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 98)] …
  arxiv Johan Schubert 2003-05-16T15:54:46Z 置信度 0.78 cs.AIcs.NE
• Uncertainty-Aware Resource Provisioning for Network Slicing
  Network slicing allows Mobile Network Operators to split the physical infrastructure into isolated virtual networks (slices), managed by Service Providers to accommodate customized services. The Service Function Chains (SFCs) belonging to a slice are usually d…
  arxiv Quang-Trung Luu, Sylvaine Kerboeuf, Michel Kieffer 2020-06-01T17:42:40Z 置信度 0.78 cs.NI
• Generalized hetero-associative neural networks
  Auto-associative neural networks (e.g., the Hopfield model implementing the standard Hebbian prescription) serve as a foundational framework for pattern recognition and associative memory in statistical mechanics. However, their hetero-associative counterparts…
  arxiv Elena Agliari, Andrea Alessandrelli, Adriano Barra, Martino Salomone Centonze 等 2024-09-12T15:44:21Z 置信度 0.78 cond-mat.dis-nn
• Simulation-based optimization of a production system topology -- a neural network-assisted genetic algorithm
  There is an abundance of prior research on the optimization of production systems, but there is a research gap when it comes to optimizing which components should be included in a design, and how they should be connected. To overcome this gap, a novel approach…
  arxiv N. Paape, J. A. W. M. van Eekelen, M. A. Reniers 2024-02-02T15:52:10Z 置信度 0.78 cs.NEeess.SY
• Neural Networks Processing Mean Values of Random Variables
  We introduce a class of neural networks derived from probabilistic models in the form of Bayesian belief networks. By imposing additional assumptions about the nature of the probabilistic models represented in the belief networks, we derive neural networks wit…
  arxiv M. J. Barber, J. W. Clark, C. H. Anderson 2004-07-16T12:50:21Z 置信度 0.78 cond-mat.dis-nn
• FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks
  With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While the task of model ex…
  arxiv Hamed Behzadi-Khormouji, José Oramas 2023-05-17T10:59:55Z 置信度 0.78 cs.CV
• Computing frustration and near-monotonicity in deep neural networks
  For the signed graph associated to a deep neural network, one can compute the frustration level, i.e., test how close or distant the graph is to structural balance. For all the pretrained deep convolutional neural networks we consider, we find that the frustra…
  arxiv Joel Wendin, Erik G. Larsson, Claudio Altafini 2025-10-06T18:54:54Z 置信度 0.78 cs.LGcond-mat.dis-nnstat.ML
• Neural Networks for Dynamic Shortest Path Routing Problems - A Survey
  This paper reviews the overview of the dynamic shortest path routing problem and the various neural networks to solve it. Different shortest path optimization problems can be solved by using various neural networks algorithms. The routing in packet switched mu…
  arxiv R. Nallusamy, K. Duraiswamy 2009-11-15T13:04:26Z 置信度 0.78 cs.NEcs.AI
• Self-Correcting Neural Networks For Safe Classification
  Classifiers learnt from data are increasingly being used as components in systems where safety is a critical concern. In this work, we present a formal notion of safety for classifiers via constraints called safe-ordering constraints. These constraints relate …
  arxiv Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson 等 2021-07-23T20:08:52Z 置信度 0.78 cs.LGcs.NE
• Convolutional neural network compression for natural language processing
  Convolutional neural networks are modern models that are very efficient in many classification tasks. They were originally created for image processing purposes. Then some trials were performed to use them in different domains like natural language processing.…
  arxiv Krzysztof Wróbel, Marcin Pietroń, Maciej Wielgosz, Michał Karwatowski 等 2018-05-28T07:40:33Z 置信度 0.78 cs.CLcs.LGcs.NE
• Learning Latent Causal Structures with a Redundant Input Neural Network
  Most causal discovery algorithms find causal structure among a set of observed variables. Learning the causal structure among latent variables remains an important open problem, particularly when using high-dimensional data. In this paper, we address a problem…
  arxiv Jonathan D. Young, Bryan Andrews, Gregory F. Cooper, Xinghua Lu 2020-03-29T20:52:35Z 置信度 0.78 cs.LGcs.NEq-bio.MNstat.ML
• Connectivity determines the capability of sparse neural network quantum states
  The Lottery Ticket Hypothesis (LTH) posits that within overparametrized neural networks, there exist sparse subnetworks that are capable of matching the performance of the original model when trained in isolation from the original initialization. We extend thi…
  arxiv Brandon Barton, Juan Carrasquilla, Christopher Roth, Agnes Valenti 2025-05-28T18:00:08Z 置信度 0.78 quant-phcond-mat.dis-nn
• Gauge Symmetry and Neural Networks
  We propose a new model of neural network. It consists of spin variables to describe the state of neurons as in the Hopfield model and new gauge variables to describe the state of synapses. The model possesses local gauge symmetry and resembles lattice gauge th…
  arxiv Tetsuo Matsui 2001-12-26T22:43:27Z 置信度 0.78 cond-mat.dis-nnhep-latq-bio
• Microscopic and collective signatures of feature learning in neural networks
  Feature extraction - the ability to identify relevant properties of data - is a key factor underlying the success of deep learning. Yet, it has proved difficult to elucidate its nature within existing predictive theories, to the extent that there is no consens…
  arxiv Andrea Corti, Rosalba Pacelli, Pietro Rotondo, Marco Gherardi 2025-08-28T16:49:09Z 置信度 0.78 cond-mat.dis-nncond-mat.stat-mech
• BindsNET: A machine learning-oriented spiking neural networks library in Python
  The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, so…
  arxiv Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Darpan T. Sanghavi 等 2018-06-04T23:09:52Z 置信度 0.78 cs.NEq-bio.NC
• Scalability and Optimization Strategies for GPU Enhanced Neural Networks (GeNN)
  Simulation of spiking neural networks has been traditionally done on high-performance supercomputers or large-scale clusters. Utilizing the parallel nature of neural network computation algorithms, GeNN (GPU Enhanced Neural Network) provides a simulation envir…
  arxiv Naresh Balaji, Esin Yavuz, Thomas Nowotny 2014-12-01T19:12:54Z 置信度 0.78 cs.DCcs.NEq-bio.NC
• Network Inversion of Binarised Neural Nets
  While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical challenge. Network inversion, a technique that aims to reconstruct the input space …
  arxiv Pirzada Suhail, Supratik Chakraborty, Amit Sethi 2024-02-19T09:39:54Z 置信度 0.78 cs.LG