scholarly journals POINT AND INTERVAL FORECASTS OF DEATH RATES USING NEURAL NETWORKS

2021 ◽  
pp. 1-28
Author(s):  
Simon Schnürch ◽  
Ralf Korn
Keyword(s):  
Machine Learning Techniques ◽  
Forecast Errors ◽  
Reliable Prediction ◽  
Death Rates ◽  
Stochastic Mortality ◽  
Point Estimates ◽  
Learning Techniques ◽  
Forecasting Performance ◽  
Modern Machine ◽  
Carter Model

Abstract The Lee–Carter model has become a benchmark in stochastic mortality modeling. However, its forecasting performance can be significantly improved upon by modern machine learning techniques. We propose a convolutional neural network (NN) architecture for mortality rate forecasting, empirically compare this model as well as other NN models to the Lee–Carter model and find that lower forecast errors are achievable for many countries in the Human Mortality Database. We provide details on the errors and forecasts of our model to make it more understandable and, thus, more trustworthy. As NN by default only yield point estimates, previous works applying them to mortality modeling have not investigated prediction uncertainty. We address this gap in the literature by implementing a bootstrapping-based technique and demonstrate that it yields highly reliable prediction intervals for our NN model.

scholarly journals Machine learning for metagenomics: methods and tools

Metagenomics ◽  
2017 ◽  
Vol 1 (1) ◽  
Author(s):  
Hayssam Soueidan ◽  
Macha Nikolski
Keyword(s):  
Machine Learning ◽  
Gene Prediction ◽  
Full Range ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
Unified Framework ◽  
Comparative Metagenomics ◽  
Learning Techniques ◽  
Ngs Data ◽  
Modern Machine

AbstractOwing to the complexity and variability of metagenomic studies, modern machine learning approaches have seen increased usage to answer a variety of question encompassing the full range of metagenomic NGS data analysis.We review here the contribution of machine learning techniques for the field of metagenomics, by presenting known successful approaches in a unified framework. This review focuses on five important metagenomic problems:OTU-clustering, binning, taxonomic proffiing and assignment, comparative metagenomics and gene prediction. For each of these problems, we identify the most prominent methods, summarize the machine learning approaches used and put them into perspective of similar methods.We conclude our review looking further ahead at the challenge posed by the analysis of interactions within microbial communities and different environments, in a field one could call “integrative metagenomics”.

scholarly journals Modern machine learning outperforms GLMs at predicting spikes

2017 ◽  
Author(s):  
Ari S. Benjamin ◽  
Hugo L. Fernandes ◽  
Tucker Tomlinson ◽  
Pavan Ramkumar ◽  
Chris VerSteeg ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Activity ◽  
Linear Models ◽  
Feedforward Neural Networks ◽  
Predictive Performance ◽  
Machine Learning Techniques ◽  
Machine Learning Methods ◽  
Learning Techniques ◽  
Neural Spiking ◽  
Modern Machine

AbstractNeuroscience has long focused on finding encoding models that effectively ask “what predicts neural spiking?” and generalized linear models (GLMs) are a typical approach. It is often unknown how much of explainable neural activity is captured, or missed, when fitting a GLM. Here we compared the predictive performance of GLMs to three leading machine learning methods: feedforward neural networks, gradient boosted trees (using XGBoost), and stacked ensembles that combine the predictions of several methods. We predicted spike counts in macaque motor (M1) and somatosensory (S1) cortices from standard representations of reaching kinematics, and in rat hippocampal cells from open field location and orientation. In general, the modern methods (particularly XGBoost and the ensemble) produced more accurate spike predictions and were less sensitive to the preprocessing of features. This discrepancy in performance suggests that standard feature sets may often relate to neural activity in a nonlinear manner not captured by GLMs. Encoding models built with machine learning techniques, which can be largely automated, more accurately predict spikes and can offer meaningful benchmarks for simpler models.

scholarly journals Application of Machine Learning Techniques for Railway Health Monitoring

2010 ◽  
pp. 396-421
Author(s):  
G.M. Shafiullah ◽  
Adam Thompson ◽  
Peter J. Wolfs ◽  
A.B.M. Shawkat Ali
Keyword(s):  
Machine Learning ◽  
Health Monitoring ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Vertical Acceleration ◽  
Lateral Instability ◽  
Learning Techniques ◽  
Safety And Reliability ◽  
Efficient Data ◽  
Modern Machine

Emerging wireless sensor networking (WSN) and modern machine learning techniques have encouraged interest in the development of vehicle health monitoring (VHM) systems that ensure secure and reliable operation of the rail vehicle. The performance of rail vehicles running on railway tracks is governed by the dynamic behaviours of railway bogies especially in the cases of lateral instability and track irregularities. In order to ensure safety and reliability of railway in this chapter, a forecasting model has been developed to investigate vertical acceleration behaviour of railway wagons attached to a moving locomotive using modern machine learning techniques. Initially, an energy-efficient data acquisition model has been proposed for WSN applications using popular learning algorithms. Later, a prediction model has been developed to investigate both front and rear body vertical acceleration behaviour. Different types of models can be built using a uniform platform to evaluate their performances and estimate different attributes’ correlation coefficient (CC), root mean square error (RMSE), mean absolute error (MAE), root relative squared error (RRSE), relative absolute error (RAE) and computation complexity for each of the algorithm. Finally, spectral analysis of front and rear body vertical condition is produced from the predicted data using Fast Fourier Transform (FFT) and used to generate precautionary signals and system status which can be used by the locomotive driver for deciding upon necessary actions.

scholarly journals SPAHM: the Spectrum of Approximated Hamiltonian Matrices representations

2021 ◽  
Author(s):  
Clémence Corminboeuf ◽  
Alberto Fabrizio ◽  
Ksenia Briling
Keyword(s):  
Machine Learning ◽  
Learning Task ◽  
Real Space ◽  
Machine Learning Techniques ◽  
Chemical Information ◽  
Alternative Strategies ◽  
Learning Techniques ◽  
Alternative Approach ◽  
Quantum Machine Learning ◽  
Modern Machine

Abstract Physics-based molecular representations are the cornerstone of all modern machine learning techniques applied to solve chemical problems. While several approaches exist to design ever more accurate fingerprints, the majority resolves in including more physics to construct larger and more complex representations. Here, we present an alternative approach to harness the complexity of chemical information into a lightweight numerical form, naturally invariant under real-space transformations, and seamlessly including the information about the charge state of a molecule. The Spectrum of Approximated Hamiltonian Matrices (SPAHM) leverages the information contained in widely-used and readily-evaluated ``guess'' Hamiltonians to form a robust fingerprint for quantum machine learning. Relying on the origin of the SPAHM fingerprints and a hierarchy of approximate Hamiltonians, we analyze the relative merits of adding physics into molecular representations and find that alternative strategies, focusing more on the machine learning task, represent a clear route towards direct improvements.

Prediction of the Hardness of Cu-Ti-Co Alloy Using Machine Learning Techniques

2018 ◽  
Vol 777 ◽  
pp. 372-376 ◽  
Author(s):  
Shan Feng Fang
Keyword(s):  
Machine Learning ◽  
Copper Alloys ◽  
Least Square ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Approaches ◽  
Forecasting Accuracy ◽  
Learning Techniques ◽  
Vector Machines ◽  
Forecasting Performance

Diverse machine learning approaches were employed to build regression models for predicting mechanical property of Cu-Ti-Co alloy. The forecasting performance of the least-square support vector machines (LSSVM) model has been compared with other artificial intelligence methods such as GRNN, RBF-PLS and RBFNN. The models were developed and validated utilizing a cross-validation (CV) procedure to improve the forecasting accuracy and generalization ability. The result demonstrates that the generalization performance of the new LSSVM is slightly better or superior to those acquired using GRNN, RBF-PLS and RBFNN. In future, it would be expected that the relatively new model based on machine learning is used as an especially helpful implement to accelerate materials design of copper alloys.

Learning Lyapunov stable Dynamical Embeddings of Geophysical Dynamics

2020 ◽  
Author(s):  
Said Ouala ◽  
Lucas Drumetz ◽  
Bertrand Chapron ◽  
Ananda Pascual ◽  
Fabrice Collard ◽  
...  
Keyword(s):  
Network Architecture ◽  
Hidden Variables ◽  
Training Data ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Great Success ◽  
Initial Condition ◽  
Learning Techniques ◽  
Forecasting Performance ◽  
Short Term Forecasting

<p>Within the geosciences community, data-driven techniques have encountered a great success in the last few years. This is principally due to the success of machine learning techniques in several image and signal processing domains. However, when considering the data-driven simulation of ocean and atmospheric fields, the application of these methods is still an extremely challenging task due to the fact that the underlying dynamics usually depend on several complex hidden variables, which makes the learning and simulation process much more challenging.</p><p>In this work, we aim to extract Ordinary Differential Equations (ODE) from partial observations of a system. We propose a novel neural network architecture guided by physical and mathematical considerations of the underlying dynamics. Specifically, our architecture is able to simulate the dynamics of the system from a single initial condition even if the initial condition does not lie in the attractor spanned by the training data. We show on different case studies the effectiveness of the proposed framework both in capturing long term asymptotic patterns of the dynamics of the system and in addressing data assimilation issues which relates to the short term forecasting performance of our model.</p>

scholarly journals Performance Analysis of Deep Neural Networks in piRNAs Classification

2018 ◽  
Author(s):  
Alisson Hayasi Da Costa ◽  
Renato Augusto Corrêa Dos Santos ◽  
Ricardo Cerri
Keyword(s):  
Neural Networks ◽  
Performance Analysis ◽  
Deep Neural Networks ◽  
Biological Data ◽  
Machine Learning Techniques ◽  
Activation Functions ◽  
Feedforward Network ◽  
Number Of Layers ◽  
Learning Techniques ◽  
Modern Machine

Modern machine learning techniques, such as Deep Learning, have been successful in many complex Bioinformatics tasks. The capacity of Deep Neural Networks to handle large volumes of data has made them essential tools for multiple areas of knowledge. However, developing the best model for a given task is a hard work. Deep Neural Networks have a very large number of hyperparameters, making them as powerful as complex to be adjusted. Therefore, in order to better understand the behavior of Deep Neural Networks when applied to biological data, we present in this paper a performance analysis of a Deep Feedforward Network in piRNAs classification. Different configurations of activation functions, initialization of weights, number of layers and learning rate are experienced. The effects of different hyperparameters are discussed and certain organizations are proposed for similar domains of data.

Sign in / Sign up

Export Citation Format

Share Document