arXiv research

Model-based neural networks generalize better than ReLU networks for sparse recovery.

We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal $Q$-func…

Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are we…

Hybrid Bayesian MOT uses neural networks to improve model aspects, achieving state-of-the-art performance.

Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model, typically at the expense of difficulties during inference. In contrast, deterministic deep neural networks a…

We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-d…

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $α$-divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g.…

This paper compares model-based and model-free control methods using neural networks.

This paper presents a study on discriminative artificial neural network classifiers in the context of open-set speaker identification. Both 2-class and multi-class architectures are tested against the conventional Gaussian mixture model based classifier on enrolled speaker sets of different sizes. The performance evalu…

A method of simultaneously optimizing both the structure of neural networks and the connection weights in a single training loop can reduce the enormous computational cost of neural architecture search. We focus on the probabilistic model-based dynamic neural network structure optimization that considers the probabilit…

Graph Neural Networks struggle with generalization, especially OOD data; GRATIN solves this with Gaussian Mixture Model-based augmentation.

Data-driven symbol detection improves performance in complex channels.

A new neural network model improves reinforcement learning efficiency.

RH-UCRL combines pessimism and optimism for robust RL.

End-to-end neural network optimizes portfolios by directly learning allocations from features.

New method identifies latent variables in cognitive models using neural networks.

We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the mode…

Proposes model-based robust deep learning to handle natural variation in data.

UPR hybrid model improves phase retrieval performance.

Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification. However, many short texts occur in sequences (e.g., sentences in a document or utterances in a dialog), and most existing ANN-based systems do not leverage the preceding short texts when classifying …

Model-based machine learning improves communication systems.

In this paper, we investigate the significance of choosing an appropriate tessellation strategy for a spatio-temporal taxi demand-supply modeling framework. Our study compares (i) the variable-sized polygon based Voronoi tessellation, and (ii) the fixed-sized grid based Geohash tessellation, using taxi demand-supply GP…

Traditional recommendation systems rely on past usage data in order to generate new recommendations. Those approaches fail to generate sensible recommendations for new users and items into the system due to missing information about their past interactions. In this paper, we propose a solution for successfully addressi…

Physics-informed neural networks improve model accuracy and efficiency.

This paper introduces 'General Cyclical Training' for neural networks.

DyNODE uses neural ODEs to model system dynamics in continuous control tasks.

DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple …

Researchers develop a neural network that learns like humans, overcoming forgetting and structure issues.

New measure assesses neural network models' functional similarity.

Convolutional neural networks have achieved astonishing results in different application areas. Various methods which allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks seem to be a promising approach for these devices with low computational power. However,…

A new method reduces compounding errors in model-based reinforcement learning.

Neural network with data augmentation improves multi-stage pump prediction accuracy.

Study uses neural networks for fast Hawkes model parameter estimation in finance.

We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the Wasserstein metric. We go on to prove an error bound for the value-function estimate arisi…

Paper proposes a CNN model for improved multi-asset portfolio risk prediction.

In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps. We propose a novel algorithm that can dynamically search for the structure of cells in a recurrent neural network model. Based on a combination of recurrent and recursive neura…

The ConditionaL Neural Networks (CLNN) and the Masked ConditionaL Neural Networks (MCLNN) exploit the nature of multi-dimensional temporal signals. The CLNN captures the conditional temporal influence between the frames in a window and the mask in the MCLNN enforces a systematic sparseness that follows a filterbank-lik…

New RL framework models continuous-time dynamics using neural ODEs.

Efficiently learns MFC systems with unknown dynamics.

Model predicts S&P500 volatility more accurately than existing models.

Paper proposes a new reserving model using machine learning techniques.

CSM-NN uses neural networks to speed up and improve the accuracy of logic circuit simulations.

Elasticity images map biomechanical properties of soft tissues to aid in the detection and diagnosis of pathological states. In particular, quasi-static ultrasonic (US) elastography techniques use force-displacement measurements acquired during an US scan to parameterize the spatio-temporal stress-strain behavior. Curr…

A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.

Study enhances neural network predictions for wave height using topological features.

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…

Recurrent neural networks (RNNs) were designed for dealing with time-series data and have recently been used for creating predictive models from functional magnetic resonance imaging (fMRI) data. However, gathering large fMRI datasets for learning is a difficult task. Furthermore, network interpretability is unclear. T…

Paper proposes Multi-Transformer for more accurate stock volatility forecasts.