scholarly journals Deep Semantic Protein Representation for Annotation, Discovery, and Engineering

2018 ◽  
Author(s):  
Ariel S Schwartz ◽  
Gregory J Hannum ◽  
Zach R Dwiel ◽  
Michael E Smoot ◽  
Ana R Grant ◽  
...  
Keyword(s):  
Neural Network ◽  
In Silico ◽  
Deep Neural Network ◽  
Unsolved Problem ◽  
High Dimensional ◽  
Protein Annotation ◽  
Functional Effect ◽  
Cohesive Model ◽  
Traditional Approaches ◽  
Related Proteins

AbstractComputational assignment of function to proteins with no known homologs is still an unsolved problem. We have created a novel, function-based approach to protein annotation and discovery called D-SPACE (Deep Semantic Protein Annotation Classification and Exploration), comprised of a multi-task, multi-label deep neural network trained on over 70 million proteins. Distinct from homology and motif-based methods, D-SPACE encodes proteins in high-dimensional representations (embeddings), allowing the accurate assignment of over 180,000 labels for 13 distinct tasks. The embedding representation enables fast searches for functionally related proteins, including homologs undetectable by traditional approaches. D-SPACE annotates all 109 million proteins in UniProt in under 35 hours on a single computer and searches the entirety of these in seconds. D-SPACE further quantifies the relative functional effect of mutations, facilitating rapid in silico mutagenesis for protein engineering applications. D-SPACE incorporates protein annotation, search, and other exploratory efforts into a single cohesive model.

scholarly journals A Deep Neural Network Algorithm for Semilinear Elliptic PDEs with Applications in Insurance Mathematics

Risks ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 136
Author(s):  
Stefan Kremsner ◽  
Alexander Steinicke ◽  
Michaela Szölgyenyi
Keyword(s):  
Neural Network ◽  
Partial Differential Equations ◽  
Differential Equations ◽  
Deep Neural Network ◽  
Risk Measure ◽  
Elliptic Partial Differential Equations ◽  
High Dimensional ◽  
Control Problems ◽  
Partial Differential ◽  
Neural Network Algorithm

In insurance mathematics, optimal control problems over an infinite time horizon arise when computing risk measures. An example of such a risk measure is the expected discounted future dividend payments. In models which take multiple economic factors into account, this problem is high-dimensional. The solutions to such control problems correspond to solutions of deterministic semilinear (degenerate) elliptic partial differential equations. In the present paper we propose a novel deep neural network algorithm for solving such partial differential equations in high dimensions in order to be able to compute the proposed risk measure in a complex high-dimensional economic environment. The method is based on the correspondence of elliptic partial differential equations to backward stochastic differential equations with unbounded random terminal time. In particular, backward stochastic differential equations—which can be identified with solutions of elliptic partial differential equations—are approximated by means of deep neural networks.

scholarly journals Performance-optimized neural networks as an explanatory framework for decision confidence

2021 ◽  
Author(s):  
Taylor W Webb ◽  
Kiyofumi Miyoshi ◽  
Tsz Yan So ◽  
Sivananda Rajananda ◽  
Hakwan Lau
Keyword(s):  
Neural Network ◽  
Signal Detection Theory ◽  
Deep Neural Network ◽  
High Dimensional ◽  
Decision Variable ◽  
Sensory Inputs ◽  
Decision Confidence ◽  
Dimensional Modeling ◽  
Principled Explanation ◽  
Low Dimensional

Previous work has sought to understand decision confidence as a prediction of the probability that a decision will be correct, leading to debate over whether these predictions are optimal, and whether they rely on the same decision variable as decisions themselves. This work has generally relied on idealized, low-dimensional modeling frameworks, such as signal detection theory or Bayesian inference, leaving open the question of how decision confidence operates in the domain of high-dimensional, naturalistic stimuli. To address this, we developed a deep neural network model optimized to assess decision confidence directly given high-dimensional inputs such as images. The model naturally accounts for a number of puzzling dissociations between decisions and confidence, suggests a principled explanation of these dissociations in terms of optimization for the statistics of sensory inputs, and makes the surprising prediction that, despite these dissociations, decisions and confidence depend on a common decision variable.

scholarly journals Vector Quantization of High-Dimensional Speech Spectra Using Deep Neural Network

2019 ◽  
Vol E102.D (10) ◽  
pp. 2047-2050
Author(s):  
JianFeng WU ◽  
HuiBin QIN ◽  
YongZhu HUA ◽  
LiHuan SHAO ◽  
Ji HU ◽  
...  
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Deep Neural Network ◽  
High Dimensional

scholarly journals Integrating Extracted Information from Bert and Multiple Embedding Methods with the Deep Neural Network for Humour Detection

2021 ◽  
Vol 10 (02) ◽  
pp. 11-21
Author(s):  
Rida Miraj ◽  
Masaki Aono
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Written Text ◽  
Kernel Convolution ◽  
Traditional Approaches ◽  
News Headlines ◽  
Embedding Methods ◽  
Extract Information

Humour detection from sentences has been an interesting and challenging task in the last few years. In attempts to highlight humour detection, most research was conducted using traditional approaches of embedding, e.g., Word2Vec or Glove. Recently BERT sentence embedding has also been used for this task. In this paper, we propose a framework for humour detection in short texts taken from news headlines. Our proposed framework (IBEN) attempts to extract information from written text via the use of different layers of BERT. After several trials, weights were assigned to different layers of the BERT model. The extracted information was then sent to a Bi-GRU neural network as an embedding matrix. We utilized the properties of some external embedding models. A multi-kernel convolution in our neural network was also employed to extract higher-level sentence representations. This framework performed very well on the task of humour detection.

scholarly journals A Formation Flight Method with an Improved Deep Neural Network for Multi-UAV System

2020 ◽  
Vol 38 (2) ◽  
pp. 295-302
Author(s):  
Wenguang Xie ◽  
Kang Wu ◽  
Fang Yan ◽  
Haobin Shi ◽  
Xiaocheng Zhang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Pid Controller ◽  
Deep Neural Network ◽  
High Dimensional Data ◽  
Formation Flight ◽  
High Dimensional ◽  
Electronic Warfare ◽  
The Real ◽  
Multi Uav

It is crucial to develop an effective controller for the multi-UAV system to contribute to the frontier fields, such as the electronic warfare. To address the dilemma of the cooperative formation with the high dimensional data, a deep neural network(NN) controller is developed in this paper. Firstly, a deep NN model is used to tune parameters of PID controller online. Secondly, this paper introduces an improved deep NN model integrating the momentum to improve the performance of the classical NN model and satisfy the condition for the real time cooperative formation. Lastly, the cooperative formation task is achieved by extending the proposed cooperative controller with an improved NN to the complex multi-UAV system. The simulation result of multi-UAV formation demonstrates the effectiveness of the proposed method, which achieves a faster formation than competitors.

Sign in / Sign up

Export Citation Format

Share Document