Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series

Brando, Axel; Rodríguez-Serrano, José A.; Ciprian, Mauricio; Maestre, Roberto; Vitrià, Jordi

doi:10.1007/978-3-030-10997-4_20

Cited by 10 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another area is decision-making under uncertainty, such as whenever assessing complex structures [ 158 ] or emotions are expressed in texts [ 159 ]. Finally, the work associated with taking risks under uncertainty has been mentioned, either as analyzed from the perspective of video games, as in [ 160 ], or in financial forecasts for customers [ 161 ].…”

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

Among the several emerging dimensioning, control and deployment of future communication network paradigms stands out the human-centric characteristic that creates an intricate relationship between telematics and human activities. The hard to model dynamics of user behavior introduces new uncertainties into these systems that give rise to difficult network resource management challenges. According to this context, this work reviews several decision-making computational methods under the influence of uncertainties. This work, by means of a systematic literature review, focuses on sensor-based Internet of Things scenarios such as Smart Spaces and Industry 4.0. According to our conclusions, it is mandatory to establish a means for modeling the human behavior context in order to improve resource assignment and management.

show abstract

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…When considering deep learning models, a common choice is to model the target variable distribution as a Normal [6] or Laplacian distribution [9] and solve a Maximum Likelihood estimation problem in order to find the optimal network parameters. Both distributions are a sub-case of the parametric family of symmetric distributions known as Generalized Normal Distribution (GND).…”

Section: A Probability Distribution Fittingmentioning

confidence: 99%

“…From now on we refer to this as std. Following [9], our problem is to forecast upcoming monthly expenses and incomes in a certain aggregated financial category for each bank client. Each time series contains 24 points and the goal is to predict the next aggregated month.…”

Section: Volume 4 2016mentioning

confidence: 99%

See 1 more Smart Citation

Building Uncertainty Models on Top of Black-Box Predictive APIs

et al. 2020

Self Cite

View full text Add to dashboard Cite

With the commoditization of machine learning, more and more off-the-shelf models are available as part of code libraries or cloud services. Typically, data scientists and other users apply these models as "black boxes" within larger projects. In the case of regressing a scalar quantity, such APIs typically offer a predict() function, which outputs the estimated target variable (often referred to aŝ y or, in code, y_hat). However, many real-world problems may require some sort of deviation interval or uncertainty score rather than a single point-wise estimate. In other words, a mechanism is needed with which to answer the question "How confident is the system about that prediction?" Motivated by the lack of this characteristic in most predictive APIs designed for regression purposes, we propose a method that adds an uncertainty score to every black-box prediction. Since the underlying model is not accessible, and therefore standard Bayesian approaches are not applicable, we adopt an empirical approach and fit an uncertainty model using a labelled dataset (x, y) and the outputsŷ of the black box. In order to be able to use any predictive system as a black box and adapt to its complex behaviours, we propose three variants of an uncertainty model based on deep networks. The first adds a heteroscedastic noise component to the black-box output, the second predicts the residuals of the black box, and the third performs quantile regression using deep networks. Experiments using real financial data that contain an inproduction black-box system and two public datasets (energy forecasting and biology responses) illustrate and quantify how uncertainty scores can be added to black-box outputs. INDEX TERMS Aleatoric uncertainty, Deep learning, Neural networks, Regression problems.

show abstract

“…Aleatoric uncertainty happens when the data have some kind of noise in the input mea-surements that produce uncertain outputs. Aleatoric uncertainty can either be homoscedastic if the noise is constant for all the inputs or heteroscedastic if the noise varies for every input (Brando et al, 2019). This kind of uncertainty cannot be reduced even if the data set had more instances.…”

Section: Including Uncertainty In Neural Networkmentioning

confidence: 99%

Electrophysiology prediction of single neurons based on their morphology

Michiels

2020

Preprint

View full text Add to dashboard Cite

Electrophysiology data acquisition of single neurons represents a key factor for the understanding of neuronal dynamics. However, the traditional method to acquire this data is through patch-clamp technology, which presents serious scalability flaws due to its slowness and complexity to record at fine-grained spatial precision (dendrites and axon).In silico biophysical models are therefore created for simulating hundreds of experiments that would be impractical to recreate in vitro. The optimal way to create these models is based on the knowledge of the morphological and electrical features for each neuron. Since large-scale data acquisition is often unfeasible for electrical data, previous expert knowledge can be used but it must have an acceptable degree of similarity with the type of neurons that we are trying to model.Here, we present a data-driven machine learning approach to predict the electrophysiological features of single neurons in case of only having their morphology available. To solve this multi-output regression problem, we use an artificial neural network that has the particularity of providing a probability distribution for every output feature, to incorporate uncertainty. Input data to train the model is obtained from from the Allen Cell Types database. The electrical properties can depend on the morphology, whose acquisition technology is highly automated and scalable so there exist large data sets of them. We also provide integrations with the BluePyOpt library to create a biophysical model using the original morphology and the predicted electrical features. Finally, we connect the resulting biophysical model with the Geppetto UI software to run all the simulations in a sophisticated user interface.

show abstract

Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Series

Cited by 10 publications

References 12 publications

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Building Uncertainty Models on Top of Black-Box Predictive APIs

Electrophysiology prediction of single neurons based on their morphology

Contact Info

Product

Resources

About