Mack-Net model combines Mack's model with RNNs for better insurance liability estimation.
problem Accurate estimation of insurance liabilities for better financial decision-making.
method Integrates Mack's reserving model with Recurrent Neural Networks (RNNs).
result Improves accuracy of general insurance liability assessment.
A new method uses recurrent nets to efficiently estimate SEIR model parameters.
problem Estimating SEIR model parameters is slow and inaccurate with grid search.
method Transform non-differentiable problem to differentiable one using recurrent nets.
result Significantly better parameter estimations with fewer simulations.
TCNs can approximate complex input-output maps with limited memory.
problem Approximating complex input-output maps with limited memory.
method Proved TCNs can approximate a wide class of input-output maps with arbitrary error tolerance.
result Deep ReLU TCNs can approximate input-output maps with finite memory to arbitrary error.
RE-NET predicts future interactions in temporal knowledge graphs.
problem Predicting future facts in temporal knowledge graphs.
method Autoregressive architecture with recurrent event encoder and neighborhood aggregator.
result State-of-the-art performance on five public datasets.
New neural network design improves speech enhancement metrics.
problem Improving speech enhancement metrics in noisy conditions.
method Combination of convolutional and recurrent layers in U-net architecture.
result Proposed solution outperforms current state-of-the-art in SDR, SIR, and STOI metrics.
Deep neural nets can estimate regression with dependent data without the curse of dimensionality.
problem Regression with dependent data and structural assumptions on the regression function.
method Deep recurrent neural network estimate under suitable structural assumptions.
result Deep neural nets can circumvent the curse of dimensionality for regression with dependent data.
Deep neural nets solve complex stochastic control problems.
problem Solving stochastic optimal control problems with control multiplicative noise.
method Deep recurrent neural networks and LSTM.
result Deep learning algorithm solves complex stochastic control problems efficiently.
RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
problem Efficiently learning rhythmic motion in reinforcement learning.
method Combining RNNs and SCN structures to create RCNs.
result RCNs outperform MLPs and SCNs across all environment tasks.
Improved deep learning optimizers using adaptive stepsize.
problem Improving the performance of deep learning optimizers.
method Adapts stepsize directly with the loss function to make progress on loss.
result Enhanced optimizers outperform Adam and Momentum optimizers without increased computational cost.
Deep learning model predicts subsurface flow dynamics.
problem Predicting dynamic subsurface flow in channelized geological systems.
method Residual U-Net and Convolutional LSTM networks trained on pressure and saturation maps.
result Surrogate model accurately predicts pressure, saturation, and well rates for new realizations.
Proposes a method to learn a transition operator for generating samples.
problem Learning a transition operator for generating samples efficiently and biologically plausibly.
method Directly learns a stochastic transition operator via variational methods, encouraging it to 'walk back' quickly to data points.
result The learned transition operator generates high-quality samples and matches the data distribution well beyond the length of individual training trajectories.
We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously investigated matrix-space models for compositionality, and show they are special cases of the multi…
Generative adversarial networks improve speech synthesis from MFCCs.
problem Synthesizing speech from MFCCs, which are typically unusable for synthesis.
method Predict fundamental frequency and voicing from MFCCs, convert spectral envelope to filters, train excitation model, add noise.
result High quality speech can be reconstructed from MFCCs alone.
This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a plan…
Deep learning models complex dependencies using neural networks.
problem Understanding the new characteristics and theoretical foundations of deep learning.
method Introduction of neural network models and training techniques from a statistical perspective.
result Highlight new characteristics of deep learning like depth and over-parametrization.
SDE-Net quantifies uncertainty in deep nets using stochastic dynamics.
problem Uncertainty quantification in deep neural networks.
method Viewing DNN transformations as state evolution of a stochastic dynamical system, introducing a Brownian motion term for epistemic uncertainty.
result SDE-Net outperforms existing methods in uncertainty estimation across various tasks.
Stochastic models fail to outperform standard recurrent networks in sequence modeling.
problem Discrepancy in performance between stochastic and standard recurrent models in sequence modeling.
method Re-examine roles of latent variables, remove restriction on fully factorized output distribution, compare auto-regressive models.
result Standard recurrent models consistently outperform stochastic models in sequence modeling.
Enhanced ECCD speeds up elastic net model training.
problem Efficiently solving generalized linear models with elastic net constraints.
method Redesigned cyclic coordinate descent with Taylor expansion and batched computations.
result Empirically shows consistent 3imes performance improvement over state-of-the-art solvers. Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a re…
This work introduces a new model for complex stochastic processes.
problem Difficulties in representing non-stationary distributions with conventional models.
method Recurrent Autoregressive Flows using normalizing flows with recurrent neural connections.
result Demonstrates the effectiveness of the proposed model through experiments.
HAD-Net forecasts glucose levels with insights into insulin and carbs diffusion.
problem Inaccurate predictions in glucose level forecasting without context understanding.
method Hybrid model combining deep learning and physiological models, using recurrent attention network.
result Achieves competitive performance in glucose level forecasting with plausible diffusion insights.
Improves neural net generalization by modeling hidden state distribution.
problem Brittleness and failure of existing neural nets, especially with sparse labeled data and adversarial training.
method State reification: modeling hidden state distribution and projecting test states towards it.
result Helps neural nets generalize better, especially with sparse labeled data and adversarial training.
PIP-Net predicts pedestrian crossing intentions with up to 4-second lead.
problem Accurate pedestrian intention prediction for autonomous vehicles in real-world scenarios.
method Recurrent and temporal attention-based model using kinematic and spatial features.
result PIP-Net predicts pedestrian crossing intentions up to 4 seconds in advance.
SIS-RNN improves model flexibility for sequential data.
problem Limited expressive power of existing stochastic RNNs.
method Semi-implicit variational inference for implicit latent representations.
result SIS-RNN outperforms existing methods in various tasks.
The paper analyzes SGD dynamics and generalization using Hessian of deep net losses.
problem Understanding the optimization dynamics and generalization of SGD for deep nets.
method Hessian analysis of training loss and associated quantities.
result New insights into the optimization and generalization of SGD for deep nets.
Deep neural nets approximate random dynamical system trajectories uniformly in time.
problem Approximating trajectories of random dynamical systems over infinite time horizons.
method Recurrent neural networks with simple feedback structures.
result Certain random trajectories can be approximated uniformly in time to any desired accuracy.
BCD-Net uses identical CNN structures for image recovery in undersampled imaging.
problem Challenges in obtaining accurate images from undersampled or noisy measurements.
method Incorporates image mapping CNN into BCD signal recovery method using alternating direction method of multipliers.
result Significantly more accurate image recovery compared to existing methods.
fSDE-Net generates time series with long-term memory using neural networks.
problem Generating time series with long-term memory from irregularly sampled data.
method fSDE-Net: neural fractional Stochastic Differential Equation Network using fractional Brownian motion.
result fSDE-Net can replicate distributional properties of real time-series data.
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The c…
Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinf…
A new meta-learning method improves deep neural net training efficiency.
problem Efficient training of complex deep neural networks with long training processes.
method Meta-learning with Hessian-Free (MLHF) approach based on Hessian-Free optimization.
result MLHF shows good and continuous training performance in deep convolution neural nets.
New algorithm guarantees optimal convergence rate for stochastic optimization.
problem Optimal convergence rate for stochastic optimization algorithms.
method Regularized versions of Minimization by Incremental Surrogate Optimization (MISO) with arbitrary recurrent data sampling.
result Expected optimality gap converges at O(n−1/2) under general recurrent sampling schemes. Unified approach to training stochastic RNNs with latent variables.
problem Training generative latent variable models with autoregressive decoders.
method Amortized variational inference with backward RNN conditioning and auxiliary reconstruction cost.
result Improved performance on speech and sequential MNIST benchmarks.
Bayesian Neural Nets improve model stability and fit.
problem Improving model stability and fit in time series prediction.
method Assign Bayesian Neural Nets to drift and diffusion terms of SDE, infer posterior using SGLD.
result Significantly improved stability and better model fit on benchmarks.
Project condenses neural nets to make ML accessible in healthcare, reducing computational burden.
problem Limited computational resources in healthcare settings, particularly in third-world nations.
method Pruning unused neurons, modifying RNN structure, and quantizing weights to reduce neural net size and complexity.
result Increased computational efficiency without compromising accuracy, some methods even improving accuracy.
The study forecasts, reconstructs, and selects features of ocean waves using neural networks.
problem Forecasting, reconstructing, and feature selection of ocean waves.
method Recurrent and sequence-to-sequence neural networks, Bayesian hyperparameter optimization, Elastic Net method.
result Proposed methods outperform alternatives in significant wave height reconstruction.
Paper uses RNN to predict SaaS user lifetime value.
problem Predicting user lifetime value in SaaS applications.
method Recurrent Neural Network with multi-cell architecture, accounting for cohort, age-in-system, and contemporaneous information.
result Significantly improved prediction accuracy compared to existing models.
Delay-SDE-net models time series with memory and uncertainty, outperforming other models.
problem Accurately modeling time series with memory and uncertainty.
method Stochastic delay differential equations (SDDEs) neural network model with aleatoric and epistemic uncertainty.
result The Delay-SDE-net consistently outperforms other models in predicting time series values and uncertainties.
Convolutional attractor nets improve image completion and super-resolution.
problem Construct coherent neural states from noisy data.
method Revisit and extend attractor networks with convolutional bipartite architecture.
result Demonstrates potential for image completion and super-resolution.
Deep state space model forecasts time series with uncertainty.
problem Probabilistic forecasting for risk management.
method Parameterized deep networks for non-linear models, recurrent neural nets for dependency, ARD network for exogenous variables.
result Accurate and sharp probabilistic forecasts with realistic uncertainty growth.
Improves model accuracy for neural nets in stochastic dynamics with partial prior knowledge.
problem Stability and accuracy in neural nets modeling stochastic dynamics with many parameters.
method Three steps: probabilistic weights, partial knowledge incorporation, and PAC-Bayesian training.
result Improved model fit with partial and noisy prior knowledge.
Researchers study heavy-tail properties of SGD using stochastic recurrence equations.
problem Analyzing heavy-tail properties of Stochastic Gradient Descent (SGD).
method Modeling SGD iterations as multivariate affine stochastic recursions and applying the theory of irreducible-proximal (i-p) matrices.
result Extended results of Gürbüzbalaban et al. (2020) by using the theory of i-p matrices.
Improves event prediction in complex processes using Petri nets and deep learning.
problem Predicting the next event in complex processes given a state.
method Enhanced Petri net model with time decay functions and deep learning.
result Significant performance improvements over state-of-the-art methods.
A new method learns brain dynamics from limited rs-fMRI data.
problem Limited training data for brain connectivity dynamics.
method Residual D-net with recurrent multi-scale representation.
result Significantly higher classification accuracy for MCI vs NC.
A neural network, IHT-Net, improves DOA estimation with sparse arrays.
problem Single-snapshot DOA estimation with sparse arrays in dynamic settings.
method IHT-inspired neural network with recurrent neural network and autoencoders.
result IHT-Net achieves faster convergence and higher accuracy in DOA estimation.
This work combines recurrent models with diffusion for probabilistic time series forecasting.
problem Scalability and capturing high-dimensional distributions and cross-feature dependencies in time series forecasting.
method Combines recurrent neural networks' efficiency with diffusion models' probabilistic modeling, using stochastic interpolants and conditional generation.
result Offers scalable probabilistic time series forecasting methods.
Deep neural networks solve stochastic control problems with delay.
problem Challenges in stochastic control problems with delay due to path-dependence and high dimensions.
method Employing recurrent neural networks (RNNs) to parameterize policies and optimize objectives.
result RNNs, especially LSTMs, efficiently capture path-dependence and outperform feedforward networks in training and performance.
Proposes a new deep learning model for uncertainty quantification and propagation.
problem High-dimensional uncertainty quantification and propagation problems.
method Integrates U-net with Gaussian Gated Linear Network (GGLN) to create GLU-net.
result Less complex architecture with 44% fewer parameters than existing models.