arXiv: Learning
Papers
45.4k
Papers 10,000
1 page of 1,000 pages (10k results)
Newest
#1Anmol JainH-Index: 1
#2Aishwary KumarH-Index: 1
Last. Seba SusanH-Index: 13
view all 3 authors...
Deep Neural Networks (DNNs) are prone to overfitting and hence have high variance. Overfitted networks do not perform well for a new data instance. So instead of using a single DNN as classifier we propose an ensemble of seven independent DNN learners by varying only the input to these DNNs keeping their architecture and intrinsic properties same. To induce variety in the training input, for each of the seven DNNs, one-seventh of the data is deleted and replenished by bootstrap sampling from the...
Source
#2Hao Zhu (The University of Texas at Austin)H-Index: 24
Effectively operating electrical vehicle charging station (EVCS) is crucial for enabling the rapid transition of electrified transportation. To solve this problem using reinforcement learning (RL), the dimension of state/action spaces scales with the number of EVs and is thus very large and time-varying. This dimensionality issue affects the efficiency and convergence properties of generic RL algorithms. We develop aggregation schemes that are based on the emergency of EV charging, namely the la...
#1François Rozet (University of Liège)H-Index: 1
#2Gilles Louppe (University of Liège)H-Index: 27
In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods. In this context, performing Bayesian inference can be challenging. In this work, we present a novel method that enables amortized inference over arbitrary subsets of the parameters, without resorting to numerical integration, which makes interpretation of the posterior more convenient. Our method is efficient and can be implem...
#1Yonatan DuklerH-Index: 4
#2Alessandro AchilleH-Index: 17
Last. Stefano SoattoH-Index: 79
view all 6 authors...
We present a method to compute the derivative of a learning task with respect to a dataset. A learning task is a function from a training set to the validation error, which can be represented by a trained deep neural network (DNN). The "dataset derivative" is a linear operator, computed around the trained model, that informs how perturbations of the weight of each training sample affect the validation error, usually computed on a separate validation dataset. Our method, DIVA (Differentiable Vali...
#1Leonard Berrada (University of Oxford)H-Index: 6
#2Sumanth Dathathri (CIT: California Institute of Technology)H-Index: 5
Last. M. Pawan Kumar (University of Oxford)H-Index: 20
view all 8 authors...
Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabilistic. Despite the promise of formal verification in ensuring the reliability of neural networks, progress in the direction of probabilistic specifications has been limited. In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic...
We introduce a deep neural network learning scheme to learn the B\"acklund transforms (BTs) of soliton evolution equations and an enhanced deep learning scheme for data-driven soliton equation discovery based on the known BTs, respectively. The first scheme takes advantage of some solution (or soliton equation) information to study the data-driven BT of sine-Gordon equation, and complex and real Miura transforms between the defocusing (focusing) mKdV equation and KdV equation, as well as the dat...
#1Chen WeiH-Index: 96
Last. Zhifeng Hao (GDUT: Guangdong University of Technology)H-Index: 24
view all 5 authors...
Most existing causal structure learning methods require data to be independent and identically distributed (i.i.d.), which often cannot be guaranteed when the data come from different environments. Some previous efforts try to tackle this problem in two independent stages, i.e., first discovering i.i.d. clusters from non-i.i.d. samples, then learning the causal structures from different groups. This straightforward solution ignores the intrinsic connections between the two stages, that is both t...
#1Robert KirkH-Index: 1
#2Amy ZhangH-Index: 19
Last. Tim RocktäschelH-Index: 33
view all 4 authors...
The study of generalisation in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We provide a unifying formalism and terminology for discu...
#1Michael Matena (UNC: University of North Carolina at Chapel Hill)H-Index: 3
#2Colin RaffelH-Index: 39
Transfer learning provides a way of leveraging knowledge from one task when learning another task. Performing transfer learning typically involves iteratively updating a model's parameters through gradient descent on a training dataset. In this paper, we introduce a fundamentally different method for transferring knowledge across models that amounts to "merging" multiple models into one. Our approach effectively involves computing a weighted average of the models' parameters. We show that this a...
#1Manzoor Hussain (CBNU: Chungbuk National University)H-Index: 1
#2Nazakat Ali (CBNU: Chungbuk National University)H-Index: 3
Last. Jang-Eui Hong (CBNU: Chungbuk National University)H-Index: 6
view all 3 authors...
The deep neural networks (DNNs)based autonomous driving systems (ADSs) are expected to reduce road accidents and improve safety in the transportation domain as it removes the factor of human error from driving tasks. The DNN based ADS sometimes may exhibit erroneous or unexpected behaviors due to unexpected driving conditions which may cause accidents. It is not possible to generalize the DNN model performance for all driving conditions. Therefore, the driving conditions that were not considered...
Source
12345678910
Top fields of study
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.