Results 1 to 10 of about 7,675,115 (371)
Mastering the game of Go with deep neural networks and tree search
Nature, 2016 David Silver +2 more
exaly +2 more sources
Explanations for Neural Networks by Neural Networks [PDF]
Applied Sciences, 2022 Understanding the function learned by a neural network is crucial in many domains, e.g., to detect a model’s adaption to concept drift in online learning. Existing global surrogate model approaches generate explanations by maximizing the fidelity between the neural network and a surrogate model on a sample-basis, which can be very time-consuming ...
Sascha Marton +2 more
openaire +2 more sources
Neural Networks With Motivation [PDF]
Frontiers in Systems Neuroscience, 2021 Animals rely on internal motivational states to make decisions. The role of motivational salience in decision making is in early stages of mathematical understanding. Here, we propose a reinforcement learning framework that relies on neural networks to learn optimal ongoing behavior for dynamically changing motivation values. First, we show that neural
Marcus Stephenson-Jones +5 more
openaire +5 more sources
Operational neural networks [PDF]
Neural Computing and Applications, 2020 AbstractFeed-forward, fully connected artificial neural networks or the so-called multi-layer perceptrons are well-known universal approximators. However, their learning performance varies significantly depending on the function or the solution space that they attempt to approximate. This is mainly because of their homogenous configuration based solely
Serkan Kiranyaz +3 more
openaire +6 more sources
A Comprehensive Survey on Graph Neural Networks [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2019 Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding.
Zonghan Wu +5 more
semanticscholar +1 more source
Towards Evaluating the Robustness of Neural Networks [PDF]
IEEE Symposium on Security and Privacy, 2016 Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x' that is ...
Nicholas Carlini, D. Wagner
semanticscholar +1 more source
Procedia Computer Science, 2023 Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty estimation in neural networks which, instead of considering a distribution over weights, samples outputs of each layer ...
Oleksiienko, Illia +2 more
openaire +4 more sources
Persistence of shocks in CDS returns on Croatian bonds: Quantile autoregression approach [PDF]
Zbornik radova Ekonomskog fakulteta u Rijeci : časopis za ekonomsku teoriju i praksu, 2019 The paper aims to examine persistence of shocks in returns on CDS for 5Y Croatian bonds. Based on sample of daily data from January 6, 2004 up until December 13, 2019 the paper evaluated research hypothesis that assumed persistence ...
Mile Bošnjak, Ivan Novak, Maja Bašić
doaj +1 more source
Overcoming catastrophic forgetting in neural networks [PDF]
Proceedings of the National Academy of Sciences of the United States of America, 2016 Significance Deep neural networks are currently the most successful machine-learning technique for solving a variety of tasks, including language translation, image classification, and image generation. One weakness of such models is that, unlike humans,
J. Kirkpatrick +13 more
semanticscholar +1 more source
Bioelectronic Medicine, 2021 Background Extracellular recording represents a crucial electrophysiological technique in neuroscience for studying the activity of single neurons and neuronal populations.
Joshua J. Strohl +4 more
doaj +1 more source