Targeted Adversarial Learning Optimized Sampling

2019 ◽  
Author(s):  
Jun Zhang ◽  
Yi Isaac Yang ◽  
Frank Noé
Keyword(s):  
Deep Learning ◽  
Optimal Transport ◽  
Dimensional Space ◽  
Optimization Techniques ◽  
Free Energy Barrier ◽  
Adversarial Learning ◽  
New Approach ◽  
Novel Approach ◽  
Transport Plan ◽  
Sampling Problem

<div>Abstract Boosting transitions of rare events is critical to modern-day simulations of complex dynamic systems. We present a novel approach to modify the potential energy surface in order to drive the system to a user-defined target distribution where the free energy barrier is lowered. The new approach, called targeted adversarial learning optimized sampling (TALOS) combines the strengths of statistical mechanics and deep learning. By casting the enhanced sampling problem as a competing game between a real sampling engine and a virtual discriminator, TALOS enables unsupervised construction of bias potential on an arbitrary dimensional space and seeks for an optimal transport plan that transforms the system into target. Through multiple experiments we show that on-the-fly training of TALOS benefits from the state-of-art optimization techniques in deep learning, thus is efficient, robust and interpretable. Additionally, TALOS is closely connected to actor-critic reinforcement learning, giving rise to a new approach to manipulating the Hamiltonian systems via deep learning.</div>

Targeted Adversarial Learning Optimized Sampling

2019 ◽  
Author(s):  
Jun Zhang ◽  
Yi Isaac Yang ◽  
Frank Noé
Keyword(s):  
Deep Learning ◽  
Optimal Transport ◽  
Dimensional Space ◽  
Optimization Techniques ◽  
Free Energy Barrier ◽  
Adversarial Learning ◽  
New Approach ◽  
Novel Approach ◽  
Transport Plan ◽  
Sampling Problem

<div>Abstract Boosting transitions of rare events is critical to modern-day simulations of complex dynamic systems. We present a novel approach to modify the potential energy surface in order to drive the system to a user-defined target distribution where the free energy barrier is lowered. The new approach, called targeted adversarial learning optimized sampling (TALOS) combines the strengths of statistical mechanics and deep learning. By casting the enhanced sampling problem as a competing game between a real sampling engine and a virtual discriminator, TALOS enables unsupervised construction of bias potential on an arbitrary dimensional space and seeks for an optimal transport plan that transforms the system into target. Through multiple experiments we show that on-the-fly training of TALOS benefits from the state-of-art optimization techniques in deep learning, thus is efficient, robust and interpretable. Additionally, TALOS is closely connected to actor-critic reinforcement learning, giving rise to a new approach to manipulating the Hamiltonian systems via deep learning.</div>

Targeted Adversarial Learning Optimized Sampling

2019 ◽  
Author(s):  
Jun Zhang ◽  
Yi Isaac Yang ◽  
Frank Noé
Keyword(s):  
Deep Learning ◽  
Optimal Transport ◽  
Dimensional Space ◽  
Optimization Techniques ◽  
Free Energy Barrier ◽  
Adversarial Learning ◽  
New Approach ◽  
Novel Approach ◽  
Transport Plan ◽  
Sampling Problem

<div>Abstract Boosting transitions of rare events is critical to modern-day simulations of complex dynamic systems. We present a novel approach to modify the potential energy surface in order to drive the system to a user-defined target distribution where the free energy barrier is lowered. The new approach, called targeted adversarial learning optimized sampling (TALOS) combines the strengths of statistical mechanics and deep learning. By casting the enhanced sampling problem as a competing game between a real sampling engine and a virtual discriminator, TALOS enables unsupervised construction of bias potential on an arbitrary dimensional space and seeks for an optimal transport plan that transforms the system into target. Through multiple experiments we show that on-the-fly training of TALOS benefits from the state-of-art optimization techniques in deep learning, thus is efficient, robust and interpretable. Additionally, TALOS is closely connected to actor-critic reinforcement learning, giving rise to a new approach to manipulating the Hamiltonian systems via deep learning.</div>

scholarly journals Targeted Adversarial Learning Optimized Sampling

2019 ◽  
Author(s):  
Jun Zhang ◽  
Yi Isaac Yang ◽  
Frank Noé
Keyword(s):  
Deep Learning ◽  
Optimal Transport ◽  
Dimensional Space ◽  
Optimization Techniques ◽  
Free Energy Barrier ◽  
Adversarial Learning ◽  
Bias Potential ◽  
Novel Approach ◽  
Transport Plan ◽  
Sampling Problem

<div>Boosting transitions of rare events is critical to modern-day simulations of complex dynamic systems. We present a novel approach to modify the potential energy surface in order to drive the system to a user-defined target distribution where the free energy barrier is lowered. The new approach, called targeted adversarial learning optimized sampling (TALOS), cross-fertilizes statistical mechanics and deep learning. By casting the enhanced sampling problem as a competing game between a real sampling engine and a virtual discriminator, TALOS enables unsupervised construction of bias potential on an arbitrary dimensional space and seeks for an optimal transport plan that transforms the system into target. Through multiple experiments we show that on-the-fly training of TALOS benefits from the state-of-art optimization techniques in deep learning, thus is efficient, robust and interpretable. TALOS can also simultaneously learn to extract good reaction coordinate from a high-dimensional space where bias potential is being constructed. Additionally, TALOS is shown to be closely related to reinforcement learning, giving rise to a new framework of manipulating Hamiltonian in order to fulfill user-specified tasks via deep learning.</div>

scholarly journals Brain Density Clustering Analysis: A New Approach to Brain Functional Dynamics

2021 ◽  
Vol 15 ◽  
Author(s):  
Ashkan Faghiri ◽  
Eswar Damaraju ◽  
Aysenil Belger ◽  
Judith M. Ford ◽  
Daniel Mathalon ◽  
...  
Keyword(s):  
Time Series ◽  
Dimensional Space ◽  
Real Data ◽  
High Dimensional ◽  
Data Set ◽  
High Dimensional Space ◽  
New Approach ◽  
Oscillatory Pattern ◽  
Functional Dynamics ◽  
Novel Approach

BackgroundA number of studies in recent years have explored whole-brain dynamic connectivity using pairwise approaches. There has been less focus on trying to analyze brain dynamics in higher dimensions over time.MethodsWe introduce a new approach that analyzes time series trajectories to identify high traffic nodes in a high dimensional space. First, functional magnetic resonance imaging (fMRI) data are decomposed using spatial ICA to a set of maps and their associated time series. Next, density is calculated for each time point and high-density points are clustered to identify a small set of high traffic nodes. We validated our method using simulations and then implemented it on a real data set.ResultsWe present a novel approach that captures dynamics within a high dimensional space and also does not use any windowing in contrast to many existing approaches. The approach enables one to characterize and study the time series in a potentially high dimensional space, rather than looking at each component pair separately. Our results show that schizophrenia patients have a lower dynamism compared to healthy controls. In addition, we find patients spend more time in nodes associated with the default mode network and less time in components strongly correlated with auditory and sensorimotor regions. Interestingly, we also found that subjects oscillate between state pairs that show opposite spatial maps, suggesting an oscillatory pattern.ConclusionOur proposed method provides a novel approach to analyze the data in its native high dimensional space and can possibly provide new information that is undetectable using other methods.

A Survey of Network Embedding for Drug Analysis and Prediction

2020 ◽  
Vol 21 ◽  
Author(s):  
Zhixian Liu ◽  
Qingfeng Chen ◽  
Wei Lan ◽  
Jiahai Liang ◽  
Yiping Pheobe Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Function ◽  
Dimensional Space ◽  
Auxiliary Information ◽  
Matrix Decomposition ◽  
Drug Analysis ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Network Embedding ◽  
Similarity Estimation

: Traditional network-based computational methods have shown good results in drug analysis and prediction. However, these methods are time consuming and lack universality, and it is difficult to exploit the auxiliary information of nodes and edges. Network embedding provides a promising way for alleviating the above problems by transforming network into a low-dimensional space while preserving network structure and auxiliary information. This thus facilitates the application of machine learning algorithms for subsequent processing. Network embedding has been introduced into drug analysis and prediction in the last few years, and has shown superior performance over traditional methods. However, there is no systematic review of this issue. This article offers a comprehensive survey of the primary network embedding methods and their applications in drug analysis and prediction. The network embedding technologies applied in homogeneous network and heterogeneous network are investigated and compared, including matrix decomposition, random walk, and deep learning. Especially, the Graph neural network (GNN) methods in deep learning are highlighted. Further, the applications of network embedding in drug similarity estimation, drug-target interaction prediction, adverse drug reactions prediction, protein function and therapeutic peptides prediction are discussed. Several future potential research directions are also discussed.

scholarly journals Deep Learning for Transient Image Reconstruction from ToF Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1962
Author(s):  
Enrico Buratto ◽  
Adriano Simonetto ◽  
Gianluca Agresti ◽  
Henrik Schäfer ◽  
Pietro Zanuttigh
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Light Response ◽  
Real Data ◽  
Depth Image ◽  
Learning Approach ◽  
Multiple Reflections ◽  
Noisy Input ◽  
Novel Approach ◽  
Incoming Light

In this work, we propose a novel approach for correcting multi-path interference (MPI) in Time-of-Flight (ToF) cameras by estimating the direct and global components of the incoming light. MPI is an error source linked to the multiple reflections of light inside a scene; each sensor pixel receives information coming from different light paths which generally leads to an overestimation of the depth. We introduce a novel deep learning approach, which estimates the structure of the time-dependent scene impulse response and from it recovers a depth image with a reduced amount of MPI. The model consists of two main blocks: a predictive model that learns a compact encoded representation of the backscattering vector from the noisy input data and a fixed backscattering model which translates the encoded representation into the high dimensional light response. Experimental results on real data show the effectiveness of the proposed approach, which reaches state-of-the-art performances.

scholarly journals The discovery of biological subphenotypes in ARDS: a novel approach to targeted medicine?

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Karin Wildi ◽  
Samantha Livingstone ◽  
Chiara Palmieri ◽  
Gianluigi LiBassi ◽  
Jacky Suen ◽  
...  
Keyword(s):  
Age Groups ◽  
Geographical Location ◽  
High Morbidity ◽  
Shock State ◽  
Pharmacological Agents ◽  
New Approach ◽  
Novel Approach ◽  
Active Research ◽  
Targeted Medicine ◽  
Core Features

AbstractThe acute respiratory distress syndrome (ARDS) is a severe lung disorder with a high morbidity and mortality which affects all age groups. Despite active research with intense, ongoing attempts in developing pharmacological agents to treat ARDS, its mortality rate remains unaltered high and treatment is still only supportive. Over the years, there have been many attempts to identify meaningful subgroups likely to react differently to treatment among the heterogenous ARDS population, most of them unsuccessful. Only recently, analysis of large ARDS cohorts from randomized controlled trials have identified the presence of distinct biological subphenotypes among ARDS patients: a hypoinflammatory (or uninflamed; named P1) and a hyperinflammatory (or reactive; named P2) subphenotype have been proposed and corroborated with existing retrospective data. The hyperinflammatory subphenotyope was clearly associated with shock state, metabolic acidosis, and worse clinical outcomes. Core features of the respective subphenotypes were identified consistently in all assessed cohorts, independently of the studied population, the geographical location, the study design, or the analysis method. Additionally and clinically even more relevant treatment efficacies, as assessed retrospectively, appeared to be highly dependent on the respective subphenotype. This discovery launches a promising new approach to targeted medicine in ARDS. Even though it is now widely accepted that each ARDS subphenotype has distinct functional, biological, and mechanistic differences, there are crucial gaps in our knowledge, hindering the translation to bedside application. First of all, the underlying driving biological factors are still largely unknown, and secondly, there is currently no option for fast and easy identification of ARDS subphenotypes. This narrative review aims to summarize the evidence in biological subphenotyping in ARDS and tries to point out the current issues that will need addressing before translation of biological subohenotypes into clinical practice will be possible.

scholarly journals Unimodular vs nilpotent superfield approach to pure dS supergravity

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Sukruti Bansal ◽  
Silvia Nagy ◽  
Antonio Padilla ◽  
Ivonne Zavala
Keyword(s):  
String Theory ◽  
General Framework ◽  
Recent Progress ◽  
High Energy ◽  
De Sitter Spacetime ◽  
De Sitter ◽  
New Approach ◽  
Sitter Spacetime ◽  
Novel Approach ◽  
De Sitter Vacua

Abstract Recent progress in understanding de Sitter spacetime in supergravity and string theory has led to the development of a four dimensional supergravity with spontaneously broken supersymmetry allowing for de Sitter vacua, also called de Sitter supergravity. One approach makes use of constrained (nilpotent) superfields, while an alternative one couples supergravity to a locally supersymmetric generalization of the Volkov-Akulov goldstino action. These two approaches have been shown to give rise to the same 4D action. A novel approach to de Sitter vacua in supergravity involves the generalisation of unimodular gravity to supergravity using a super-Stückelberg mechanism. In this paper, we make a connection between this new approach and the previous two which are in the context of nilpotent superfields and the goldstino brane. We show that upon appropriate field redefinitions, the 4D actions match up to the cubic order in the fields. This points at the possible existence of a more general framework to obtain de Sitter spacetimes from high-energy theories.

scholarly journals Compiling Life-Oriented Moral Education Textbooks for Elementary Schools in China: The Mimetic Approach in Morality and Law

2021 ◽  
pp. 209653112098296
Author(s):  
Yan Tang
Keyword(s):  
Elementary Schools ◽  
Moral Education ◽  
Life Events ◽  
Theoretical Perspective ◽  
Building Blocks ◽  
Learning Activities ◽  
Design Approach ◽  
New Approach ◽  
Novel Approach

Purpose: This study explores a novel approach to compiling life-oriented moral textbooks for elementary schools in China, specifically focusing on Morality and Law. Design/Approach/Methods: Adopting Aristotle’s Poetics as its theoretical perspective, this study illustrates and analyzes the mimetic approach used in compiling the life-oriented moral education textbook, Morality and Law. Findings: The mimetic approach involves imitating children's real activities, thoughts, and feelings in textbooks. The mimetic approach to compiling life-oriented moral textbooks comprises three strategies: constructing children's life events as building blocks for textbook compilation, designing an intricate textual device exposing the wholeness of children's life actions, and designing inward learning activities leading to children's inner worlds. Originality/Value: From the perspective of Aristotle's Poetics, the approach to compilation in Morality and Law can be defined as mimetic. And the compilation activity in the life-oriented moral education textbook also can be described as a processes of mimesis. So this article presents a new approach to compile moral education textbooks, and  an innovative way to understand the nature of one compiling activity.

Sign in / Sign up

Export Citation Format

Share Document