Deep learning architectures have proved versatile in a number of drug discovery applications, including the modelling of in vitro compound activity. While controlling for prediction confidence is essential to increase the trust, interpretability and usefulness of virtual screening models in drug discovery, techniques t…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Deep Set Prediction Network”
NCP improves deep classifier uncertainty quantification efficiency.
problem Uncertainty quantification for deep classifiers in high-stake applications.
method Neighborhood Conformal Prediction (NCP) algorithm.
result NCP produces smaller prediction sets than traditional CP methods.
New measure predicts deep neural network generalization better than existing ones.
problem Existing measures fail to explain generalization in overparameterized deep networks.
method Introduce prunability: smallest fraction of parameters that can be pruned without loss increase.
result Prunability highly correlates with generalization performance across various networks.
Introduces epistemic deep learning for better uncertainty estimation in neural networks.
problem Uncertainty quantification in deep neural networks.
method Random-set convolutional neural networks with belief function-based loss functions.
result Epistemic approach produces better performance in uncertainty estimation.
Improved set prediction model using multiset-equivariant operations and approximate implicit differentiation.
problem Existing set prediction models struggle with multisets and cannot represent certain functions.
method Introduced multiset-equivariance, improved DSPN with approximate implicit differentiation, and applied to CLEVR object property prediction.
result Significantly improved object property prediction on CLEVR dataset.
Develops deep neural network techniques for sets as input and output.
problem Bottlenecks in set representation and discontinuity issues in set prediction.
method Techniques for set representation and prediction, addressing unordered nature and relations.
result Improvements in set prediction and representation across various experiments.
While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we prese…
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to cons…
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.
problem Deep networks are prone to high prediction differences, making them less reproducible.
method Anti-Distillation uses ensembles to force predictions to be more different and diverse.
result Anti-Distillation reduces prediction differences by making ensemble predictions more diverse.
Paper proposes a method to predict deep neural network confidences with guarantees.
problem Quantifying uncertainty in deep neural networks for safety-critical applications.
method Uses Clopper-Pearson confidence intervals and histogram binning for calibrated prediction.
result Demonstrates the effectiveness of predicted confidences in improving DNN performance and safety.
Combining Bayesian deep learning and split conformal prediction affects out-of-distribution coverage.
problem Improving out-of-distribution coverage in multiclass image classification.
method Combining Bayesian deep learning with split conformal prediction methods.
result Combining methods can reduce out-of-distribution coverage in some cases.
New model explains deep learning performance at large learning rates.
problem Understanding deep learning performance at different learning rates.
method Developed neural networks with solvable training dynamics.
result Large learning rates lead to convergence to flatter minima.
This paper describes our UNet based deep convolutional neural network approach on the Traffic4cast challenge 2019. Challenges task is to predict future traffic flow volume, heading and speed on high resolution whole city map. We used UNet based deep convolutional neural network to train predictive model for the short t…
CONFINE enhances neural networks' interpretability without sacrificing accuracy.
problem Lack of interpretability in deep neural networks, especially in healthcare.
method CONFINE uses conformal prediction to generate prediction sets with robust uncertainty estimates.
result CONFINE achieves correct efficiency up to 3.3% higher than original accuracy.
Deep interpretable ensemblesstat.ML
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
Study evaluates deep learning models for cryptocurrency price prediction.
problem Accurate cryptocurrency price forecasting models are needed due to market volatility.
method Reviewed and evaluated deep learning models including LSTM, CNN, and Transformer.
result Convolutional LSTM with multivariate approach provides best prediction accuracy.
Combines Laplace approximations of deep networks for better uncertainty quantification.
problem Overconfident predictions on outliers in deep learning models.
method Gaussian mixture model posterior using weighted sum of Laplace approximations of pre-trained deep networks.
result Mitigates overconfidence 'far away' from training data.
Improved TreNet for trend prediction in time series data.
problem Validation method for TreNet did not account for time series data's sequential nature.
method Walk-forward validation method and multiple independent runs to evaluate model stability.
result TreNet still performs better than vanilla DNN models but not on all data sets.
The paper proposes a method for valid multi-target regression predictions.
problem Valid multi-variate predictions for multi-target regression.
method Copula functions applied to deep neural networks for inductive conformal prediction.
result The proposed method ensures efficiency and validity for multi-target regression problems.
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
Deep learning methods find near-optimal solutions without explicit regularization.
problem Theoretical challenges in understanding deep learning's success.
method Analysis of gradient methods, overparametrization, and implicit regularization.
result Gradient methods can find near-optimal solutions and exhibit excellent predictive accuracy without explicit regularization.
This study compares RNN and CNN for predicting wave propagation using the Saint-Venant equations.
problem Predicting wave propagation over long time periods using deep learning.
method Investigated recurrent and convolutional neural networks for their performance in predicting surface waves governed by the Saint-Venant equations.
result Convolutional networks perform at least as well as recurrent networks in predicting wave propagation.
Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets and avoids this problem. With a single feature vector as input, we show that our m…
In this paper, we tackle the real-world problem of predicting Yelp star-review rating based on business features (such as images, descriptions), user features (average previous ratings), and, of particular interest, network properties (which businesses has a user rated before). We compare multiple models on different s…
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combination of activations of trai…
Bayesian deep ensembles improve prediction accuracy in various settings.
problem Improving prediction accuracy of deep ensembles in out-of-distribution settings.
method Introducing a randomised, untrainable function to each ensemble member, enabling a posterior predictive distribution interpretation.
result Bayesian deep ensembles make more conservative predictions and outperform standard ensembles in various tasks.
We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label. We use a deep lattice network model so we can architect the model structure to enhance interpretability, and add monotonicity constraints between inputs-and-outputs.…
Traffic prediction plays a vital role in efficient planning and usage of network resources in wireless networks. While traffic prediction in wired networks is an established field, there is a lack of research on the analysis of traffic in cellular networks, especially in a content-blind manner at the user level. Here, …
Prostate motion modelling using biomechanically-trained deep neural networks on unstructured nodescs.LG
Deep neural networks predict prostate motion from MR images.
problem Predicting prostate motion during ultrasound-guided interventions.
method Biomechanically-trained deep neural networks on unstructured nodes.
result Trained networks yield near real-time inference with 0.017 mm error.
Oral Disintegrating Tablets (ODTs) is a novel dosage form that can be dissolved on the tongue within 3min or less especially for geriatric and pediatric patients. Current ODT formulation studies usually rely on the personal experience of pharmaceutical experts and trial-and-error in the laboratory, which is inefficient…
Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically …
This paper proposes a deep neural network approach for predicting multiphase flow in heterogeneous domains with high computational efficiency. The deep neural network model is able to handle permeability heterogeneity in high dimensional systems, and can learn the interplay of viscous, gravity, and capillary forces fro…
Paper proposes a method to improve prediction intervals for neural networks.
problem Improving prediction intervals for neural network models.
method Adapting extremely randomized trees to neural networks to create ensembles.
result The method yields gains in out-of-sample accuracy and is superior to existing methods.
Method selects the best deep learner for time-series prediction using Bayesian networks.
problem Selecting the most effective deep learning model for time-series prediction.
method Bayesian network selects deep learners based on input variables and cluster training data.
result Threshold value determines which deep learners predict time-series data robustly.
Deep learning has been used in many areas, such as feature detections in images and the game of go. This paper presents a study that attempts to use the deep learning method to predict turbomachinery performance. Three different deep neural networks are built and trained to predict the pressure distributions of turbine…
Interpreting black box classifiers, such as deep networks, allows an analyst to validate a classifier before it is deployed in a high-stakes setting. A natural idea is to visualize the deep network's representations, so as to "see what the network sees". In this paper, we demonstrate that standard dimension reduction m…
Deep model integrates MRI and DTI for autism severity prediction.
problem Predicting spectrum-level deficits in autism using multimodal brain imaging.
method Generative deep-learning framework combining rs-fMRI and DTI data.
result Hybrid model outperforms existing methods in predicting autism severity.
Hybrid deep learning model predicts urban floods with high accuracy.
problem Urban flood prediction and situation awareness using channel network sensors data.
method FastGRNN-FCN hybrid deep learning model trained on Harris County, Texas flood data.
result Test accuracy and F-measure reach 97.8% and 0.792, respectively.
DeepRSCN models nonlinear systems using stochastic configurations.
problem Modeling nonlinear dynamic systems efficiently.
method Incrementally constructed deep reservoir computing framework with random parameters and online weight updates.
result DeepRSCN outperforms single-layer networks in efficiency, learning, and generalization.
CBDL uses credal sets to improve uncertainty quantification in deep learning.
problem Uncertainty in predictions and robustness to distribution shifts in deep learning.
method Train an infinite ensemble of Bayesian Neural Networks using credal sets.
result CBDL distinguishes between aleatoric and epistemic uncertainties and quantifies them better than single BNNs.
Paper tackles fault classification in time series data with deep neural networks.
problem Fault classification over a future horizon in multidimensional time series data with class imbalances.
method Proposes a multi-label recurrent neural network with a new cost function to address class imbalances.
result The proposed algorithm outperforms state-of-the-art techniques in F1-score, precision, and recall.
Deep learning predicts curvature of 2D interfaces in level-set method.
problem Estimating curvature in level-set method for complex interfaces.
method Deep learning using feed-forward neural networks trained on synthetic data.
result Deep learning models approximate curvature with comparable precision to traditional methods.
Bayesian Neural Networks help quantify uncertainty in deep learning predictions.
problem Uncertainty quantification in deep learning predictions.
method Bayesian statistics applied to neural networks.
result Design, implementation, training, and evaluation of Bayesian Neural Networks.
KCal calibrates deep networks by embedding logits in a metric space.
problem Overconfident predictions from DNNs, especially in high-risk applications.
method KCal learns a metric space on the penultimate-layer latent embedding and generates predictions using kernel density estimates.
result KCal provides a provable full calibration guarantee and consistently outperforms baselines.
An Investigation of Interpretability Techniques for Deep Learning in Predictive Process Analyticscs.LG
The paper investigates interpretability techniques for deep learning models in medical data.
problem Understanding the logic behind predictions of black-box models in medical decision-making.
method Applied deep neural networks and random forests to a medical dataset. Used autoencoders and local interpretable models to provide insights.
result Local interpretable models and autoencoders provide meaningful insights into cancer predictions, identifying distinct and non-generalizable features.
Deep neural nets learn from weakly dependent processes.
problem Learning from -weakly dependent processes.
method Deep neural networks for -weakly dependent processes.
result Established consistency of empirical risk minimization algorithm and generalization bound.
Deep neural network predicts health costs better than traditional models.
problem Accurate prediction of healthcare costs for optimal cost management.
method Developed a deep neural network to predict future health care costs from health insurance claims records.
result Deep neural network outperformed ridge regression and Morbi-RSA models in cost prediction.