scholarly journals Tracking Child Language Development With Neural Network Language Models

2021 ◽  
Vol 12 ◽  
Author(s):  
Kenji Sagae
Keyword(s):  
Neural Network ◽  
Language Development ◽  
Child Language ◽  
Structural Characteristics ◽  
Language Models ◽  
Data Driven ◽  
Evaluation Methodology ◽  
Specific Information ◽  
Data Driven Approach ◽  
Cross Lingual

Recent work on the application of neural networks to language modeling has shown that models based on certain neural architectures can capture syntactic information from utterances and sentences even when not given an explicitly syntactic objective. We examine whether a fully data-driven model of language development that uses a recurrent neural network encoder for utterances can track how child language utterances change over the course of language development in a way that is comparable to what is achieved using established language assessment metrics that use language-specific information carefully designed by experts. Given only transcripts of child language utterances from the CHILDES Database and no pre-specified information about language, our model captures not just the structural characteristics of child language utterances, but how these structures reflect language development over time. We establish an evaluation methodology with which we can examine how well our model tracks language development compared to three known approaches: Mean Length of Utterance, the Developmental Sentence Score, and the Index of Productive Syntax. We discuss the applicability of our model to data-driven assessment of child language development, including how a fully data-driven approach supports the possibility of increased research in multilingual and cross-lingual issues.

scholarly journals Application of deep neural network reveals novel effects of maternal pre-conception exposure to nicotine on rat pup behavior

2020 ◽  
Author(s):  
Reza Torabi ◽  
Serena Jenkins ◽  
Allonna Harker ◽  
Ian Q. Whishaw ◽  
Robbin Gibb ◽  
...  
Keyword(s):  
Neural Network ◽  
Motor Development ◽  
Deep Neural Network ◽  
Data Driven ◽  
Nicotine Exposure ◽  
Movement Initiation ◽  
Warm Up ◽  
Rat Pups ◽  
The Neural Network ◽  
Data Driven Approach

We present a deep neural network for data-driven analyses of infant rat behavior in an open field task. The network was applied to study the effect of maternal nicotine exposure prior to conception on offspring motor development. The neural network outperformed human expert designed animal locomotion measures in distinguishing rat pups born to nicotine exposed dams versus control dams. Notably, the network discovered novel movement alterations in posture, movement initiation and a stereotypy in warm-up behavior (the initiation of movement along specific dimensions) that were predictive of nicotine exposure. The results suggest that maternal preconception nicotine exposure delays and alters offspring motor development. In summary, we demonstrated that a deep neural network can automatically assess animal behavior with high accuracy, and that it offers a data-driven approach to investigating pharmacological effects on brain development.

scholarly journals ‘Ring Breaker’: Neural Network Driven Synthesis Prediction of the Ring System Chemical Space

2020 ◽  
Author(s):  
Amol Thakkar ◽  
Nidhal Selmi ◽  
Jean-Louis Reymond ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Network ◽  
Chemical Space ◽  
Ring System ◽  
Data Driven ◽  
Ring Systems ◽  
The Neural Network ◽  
Synthetic Accessibility ◽  
Synthesis Planning ◽  
Data Driven Approach ◽  
Synthetic Routes

<p></p><p>Ring systems in pharmaceuticals, agrochemicals and dyes are ubiquitous chemical motifs. Whilst the synthesis of common ring systems is well described, and novel ring systems can be readily computationally enumerated, the synthetic accessibility of unprecedented ring systems remains a challenge. ‘Ring Breaker’ uses a data-driven approach to enable the prediction of ring-forming reactions, for which we have demonstrated its utility on frequently found and unprecedented ring systems, in agreement with literature syntheses. We demonstrate the performance of the neural network on a range of ring fragments from the ZINC and DrugBank databases and highlight its potential for incorporation into computer aided synthesis planning tools. These approaches to ring formation and retrosynthetic disconnection offer opportunities for chemists to explore and select more efficient syntheses/synthetic routes. </p><br><p></p>

Bundling in Molecular Dynamics Simulations to Improve Generalization Performance in High-Dimensional Neural Network Potentials

2019 ◽  
Author(s):  
Yasuharu Okamoto
Keyword(s):  
Neural Network ◽  
Force Field ◽  
Data Driven ◽  
High Dimensional ◽  
Field Calculation ◽  
Force Field Calculations ◽  
Quantitative Accuracy ◽  
Force Field Calculation ◽  
Data Driven Approach ◽  
Dynamics Simulations

<p>High dimensional neural network potential (HDNNP) is interested as an alternative to classical force field calculations by data-driven approach. HDNNP has an advantage over classical force field calculation, such as being able to handle chemical reactions, but there are many points yet to be understood with respect to the chemical transferability in particular for non-organic compounds. In this paper, we focused on Au<sub>13</sub><sup>+</sup> and Au<sub>11</sub><sup>+</sup> clusters and showed that the energy of clusters of different sizes can be predicted by HDNNP with semi-quantitative accuracy.</p>

Investigating the GDP-CO2 relationship using a neural network approach

2020 ◽  
Author(s):  
Sebastian Jensen ◽  
Eric Hillebrand ◽  
Mikkel Bennedsen
Keyword(s):  
Neural Network ◽  
Co2 Emissions ◽  
Functional Relationship ◽  
National Level ◽  
Data Driven ◽  
Sample Analysis ◽  
Intergovernmental Panel ◽  
Neural Network Approach ◽  
Data Driven Approach ◽  
Complex Relationships

&lt;p&gt;Exploiting a national-level panel of per capita CO2 emissions and GDP data, we investigate the GDP-CO2 relationship, using a data-driven approach. We conduct an in-sample analysis in which we investigate the shape of the GDP-CO2 relationship. Utilizing the shape of the GDP-CO2 relationship learned, we project CO2 emissions through 2100, using the same set of GDP and population growth scenarios as used by the Intergovernmental Panel of Climate Change (IPCC) for their sixth assessment report due for release in 2021-22. Our analysis is carried out at two levels: at a global, and at the level of &amp;#64257;ve large regions of the world. We consider a semiparametric model speci&amp;#64257;cation which places no restrictions on the functional relationship between GDP and CO2, but which allows for country and time speci&amp;#64257;c &amp;#64257;xed e&amp;#64256;ects. The nonparametric component of our model is speci&amp;#64257;ed as a feedforward neural network, ensuring universal approximation capabilities, theoretically. In a simulation study, we show that our model is able to capture various complex relationships in &amp;#64257;nite samples of realistic sizes.&lt;/p&gt;

Data-Driven Simulation for Fast Prediction of Pull-Up Process in Bottom-Up Stereo-Lithography

2016 ◽  
Author(s):  
Jun Wang ◽  
Sonjoy Das ◽  
Chi Zhou ◽  
Rahul Rai
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Stress Distribution ◽  
Material Properties ◽  
Simulation Models ◽  
Data Driven ◽  
Bottom Up ◽  
Grid Mapping ◽  
Data Driven Approach ◽  
Fast Prediction

Developing cohesive finite element simulation models of the pull-up process in bottom-up stereo-lithography (SLA) system can significantly increase the reliability and through-put of the bottom-up SLA process. Pull-up process modeling investigates relation between motion profile and crack initialization and propagation during the separation process. However, finite element (FE) simulation of the pull-up process is computationally very expensive and time-consuming. This paper outlines a method to quickly predict the separation stress distribution based on 2D shape grid mapping and neural network. Sixteen cohesive FE models with various cross-section shapes form our database. Specific 2D shape grid mapping was utilized to describe each shape by generating a sorted binary vector. A backpropagation (BP) neural network was then trained using binary vectors, material properties, and FE simulated pull-up separation stress distribution. Given material properties, the trained model can then be used to predict the pull-up separation stress distribution of a new shape. The results demonstrate that the proposed data driven method can drastically reduce computing costs. The comparison between the predicted values by the data driven approach and simulated FE models verify the validity of the proposed method.

scholarly journals Contributions towards Data driven Deep Learning methods to predict Steady State Fluid Flow in mechanical Heart Valves

2021 ◽  
Vol 7 (2) ◽  
pp. 625-628
Author(s):  
Jan Oldenburg ◽  
Julian Renkewitz ◽  
Michael Stiehm ◽  
Klaus-Peter Schmitz
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Steady State ◽  
Flow Field ◽  
Heart Valves ◽  
Data Driven ◽  
High Shear ◽  
Blood Flows ◽  
The Neural Network ◽  
Data Driven Approach

Abstract It is commonly accepted that hemodynamic situation is related with cardiovascular diseases as well as clinical post-procedural outcome. In particular, aortic valve stenosis and insufficiency are associated with high shear flow and increased pressure loss. Furthermore, regurgitation, high shear stress and regions of stagnant blood flow are presumed to have an impact on clinical result. Therefore, flow field assessment to characterize the hemodynamic situation is necessary for device evaluation and further design optimization. In-vitro as well as in-silico fluid mechanics methods can be used to investigate the flow through prostheses. In-silico solutions are based on mathematical equitation’s which need to be solved numerically (Computational Fluid Dynamics - CFD). Fundamentally, the flow is physically described by Navier-Stokes. CFD often requires high computational cost resulting in long computation time. Techniques based on deep-learning are under research to overcome this problem. In this study, we applied a deep-learning strategy to estimate fluid flows during peak systolic steady-state blood flows through mechanical aortic valves with varying opening angles in randomly generated aortic root geometries. We used a data driven approach by running 3,500 two dimensional simulations (CFD). The simulation data serves as training data in a supervised deep learning framework based on convolutional neural networks analogous to the U-net architecture. We were able to successfully train the neural network using the supervised data driven approach. The results showing that it is feasible to use a neural network to estimate physiological flow fields in the vicinity of prosthetic heart valves (Validation error below 0.06), by only giving geometry data (Image) into the Network. The neural network generates flow field prediction in real time, which is more than 2500 times faster compared to CFD simulation. Accordingly, there is tremendous potential in the use of AIbased approaches predicting blood flows through heart valves on the basis of geometry data, especially in applications where fast fluid mechanic predictions are desired.

Application of Machine Learning in Turbulent Combustion for Aviation Gas Turbine Combustor Design

2021 ◽  
Author(s):  
Vishwas Verma ◽  
Kiran Manoharan ◽  
Jaydeep Basani
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Flow Field ◽  
Gas Turbine ◽  
Computational Cost ◽  
Data Driven ◽  
Navier Stokes ◽  
Computational Time ◽  
Reacting Flow ◽  
Data Driven Approach

Abstract Numerical simulation of gas turbine combustors requires resolving a broad spectrum of length and time scales for accurate flow field and emission predictions. Reynold’s Averaged Navier Stokes (RANS) approach can generate solutions in few hours; however, it fails to produce accurate predictions for turbulent reacting flow field seen in general combustors. On the other hand, the Large Eddy Simulation (LES) approach can overcome this challenge, but it requires orders of magnitude higher computational cost. This limits designers to use the LES approach in combustor development cycles and prohibits them from using the same in numerical optimization. The current work tries to build an alternate approach using a data-driven method to generate fast and consistent results. In this work, deep learning (DL) dense neural network framework is used to improve the RANS solution accuracy using LES data as truth data. A supervised regression learning multilayer perceptron (MLP) neural network engine is developed. The machine learning (ML) engine developed in the present study can compute data with LES accuracy in 95% lesser computational time than performing LES simulations. The output of the ML engine shows good agreement with the trend of LES, which is entirely different from RANS, and to a reasonable extent, captures magnitudes of actual flow variables. However, it is recommended that the ML engine be trained using broad design space and physical laws along with a purely data-driven approach for better generalization.

Sign in / Sign up

Export Citation Format

Share Document