Top Research Papers on Neural Networks
Explore our curated list of top research papers on Neural Networks. Delve into cutting-edge innovations and advancements that are shaping the future of artificial intelligence. Perfect for researchers, students, and enthusiasts who want to stay updated with the latest trends and findings in this dynamic field.
Looking for research-backed answers?Try AI Search
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
109 Citations 2020Keyulu Xu, Mozhi Zhang, Jingling Li + 3 more
arXiv (Cornell University)
The success of GNNs in extrapolating algorithmic tasks to new data relies on encoding task-specific non-linearities in the architecture or features, and a hypothesis is suggested for which theoretical and empirical evidence is provided.
Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks
240 Citations 2021Shi-Wee Deng, Shi Gu
ArXiv
A novel strategic pipeline is proposed that transfers the weights to the target SNN by combining threshold balance and soft-reset mechanisms and enables almost no accuracy loss between the converted SNNs and conventional ANNs with only $\sim1/10$ of the typical SNN simulation time.
Graph Neural Networks in Network Neuroscience
341 Citations 2022Alaa Bessadok, Mohamed Ali Mahjoub, Islem Rekik
IEEE Transactions on Pattern Analysis and Machine Intelligence
Current GNN-based methods are reviewed, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification, and charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration.
Graph neural networks
454 Citations 2024Gabriele Corso, Hannes Stark, Stefanie Jegelka + 2 more
Nature Reviews Methods Primers
This Primer provides a practical and accessible introduction to GNNs, describing their properties and applications to the life and physical sciences and explores how they are applied across the life and physical sciences.
Neural Networks for Chemists
190 Citations 2024Qingyang Xiao, Kaiyuan Liu, Yuhui Hong + 1 more
ACS in focus
In recent years, breakthroughs in artificial intelligence (AI) have dramatically transformed many fields. Developments in neural networks primarily drive the advances. These powerful models have demonstrated unprecedented capabilities in learning complex patterns, making predictions, and generating creative content. From the pixels on a smartphone camera to the recommendation systems on a streaming service, neural networks are now ubiquitous and are part of daily interactions. But what exactly are neural networks? They are mathematical models designed to recognize patterns. By learning from da...
Operational neural networks
117 Citations 2020Kiranyaz, Mustafa Serkan, Türker İnce, Alexandros Iosifidis + 1 more
Qatar University QSpace (Qatar University)
This study proposes a novel network model, called operational neural networks (ONNs), which can be heterogeneous and encapsulate neurons with any set of operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data.
The epinet is introduced: an architecture that can supplement any conventional neural network, including large pretrained models, and can be trained with modest incremental computation to estimate uncertainty, and the epistemic neural network (ENN) is introduced as an interface for models that produce joint predictions.
Inductive biases are any assumptions that learners utilize to learn the world and predict the output that reduce the amount of data needed to fit the model while constraining the model’s flexibility.
Neural network approximation
223 Citations 2021Ronald DeVore, Boris Hanin, Guergana Petrova
Acta Numerica
This article surveys the known approximation properties of the outputs of NNs with the aim of uncovering the properties that are not present in the more traditional methods of approximation used in numerical analysis, such as approximations using polynomials, wavelets, rational functions and splines.
This textbook provides a compact but comprehensive treatment that provides analytical and design steps to recurrent neural networks from scratch.
Fundamentals of Neural Networks
100 Citations 2021Amey Thakur
International Journal for Research in Applied Science and Engineering Technology
The purpose of this study is to familiarise the reader with the foundations of neural networks and highlight the different learning approaches and algorithms used in Machine Learning and Deep Learning.
A biomimetic neural encoder for spiking neural network
174 Citations 2021Shiva Subbulakshmi Radhakrishnan, Amritanand Sebastian, Aaryan Oberoi + 4 more
Nature Communications
A biomimetic device based on a dual gated MoS2 field effect transistor capable of encoding analog signals into stochastic spike trains at energy cost of 1–5 pJ/spike is demonstrated.
Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks
180 Citations 2020Fernando Gama, Elvin Isufi, Geert J. T. Leus + 1 more
IEEE Signal Processing Magazine
The role of graph convolutional filters in GNNs is discussed and it is shown that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology.
Complex network classification with convolutional neural network
187 Citations 2020Ruyue Xin, Jiang Zhang, Yitong Shao
Tsinghua Science & Technology
This paper proposes a novel framework of complex network classifier (CNC) by integrating network embedding and convolutional neural network to tackle the problem of network classification and shows CNC can not only classify networks in a high accuracy and robustness, it can also extract the features of the networks automatically.
Neural networks for power flow: Graph neural solver
134 Citations 2020Balthazar Donon, Rémy Clément, Benjamin Donnot + 3 more
Electric Power Systems Research
A novel artificial neural network architecture that achieves a more suitable balance between computational speed and accuracy in this context and is robust to variations of injections, power grid topology, and line characteristics.
Neural Bursting and Synchronization Emulated by Neural Networks and Circuits
148 Citations 2021Hairong Lin, Chunhua Wang, Chengjie Chen + 4 more
IEEE Transactions on Circuits and Systems I Regular Papers
In this paper, neural bursting and synchronization are imitated by modeling two neural network models based on the Hopfield neural network, which consists of four neurons, which correspond to realizing neural bursting firings.
A High-Efficient Hybrid Physics-Informed Neural Networks Based on Convolutional Neural Network
182 Citations 2021Zhiwei Fang
IEEE Transactions on Neural Networks and Learning Systems
This is the first work that the machine learning PDE’s solver has a convergent rate, such as in numerical methods, and can be applied in inverse problems and surface PDEs, although without proof.
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
417 Citations 2021Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux + 1 more
journal unavailable
The Neural Bellman-Ford Network (NBFNet) is proposed, a general graph neural network framework that solves the path formulation with learned operators in the generalized Bell man-Ford algorithm, and outperforms existing methods by a large margin in both transductive and inductive settings.
Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
187 Citations 2021Ameya D. Jagtap, Yeonjong Shin, Kenji Kawaguchi + 1 more
Neurocomputing
A new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions that are designed to get rid of any saturation region by injecting sinusoidal fluctuations, which include trainable parameters.
Brain Tumor Detection and Classification Using Convolutional Neural Network and Deep Neural Network
188 Citations 2020Chirodip Lodh Choudhury, Chandrakanta Mahanty, Raghvendra Kumar + 1 more
journal unavailable
The proposed work involves the approach of deep neural network and incorporates a CNN based model to classify the MRI as "Tumour DETECTED" or "TUMOUR Not DETECTed" and captures a mean accuracy score of 96.08% with fscore of 97.3.
