On 25 November 2020, Giovanni Volpe gave an online lecture on Graph Theory Concepts, in the scope of Karolinska Institute graduate course 3064: Imaging in Neuroscience: With a focus on structural MRI methods
The lecture is published online on youtube.
The feature article explains the project and its main aim of creating smart particles that react to their environment to a general audience.
The article is available both in English and in Swedish.
Links:
Skapar smarta partiklar med naturen som förebild (Swedish)
Creating smart particles modeled on nature (English)
Photos of Johan Wingborg, taken from Creating smart particles modeled on nature
The article Enhanced force-field calibration via machine learning
has been featured in: “Machine Learning Outperforms Standard Force-Field Calibration Techniques”, AIP SciLight (November 6, 2020).
Scilight showcases the most interesting research across the physical sciences published in AIP Publishing Journals.
Scilight is published weekly (52 issues per year) by AIP Publishing.
Aykut Argun, Tobias Thalheim, Stefano Bo, Frank Cichos, Giovanni Volpe
Applied Physics Reviews 7, 041404 (2020)
doi: 10.1063/5.0019105
arXiv: 2006.08963
The influence of microscopic force fields on the motion of Brownian particles plays a fundamental role in a broad range of fields, including soft matter, biophysics, and active matter. Often, the experimental calibration of these force fields relies on the analysis of the trajectories of these Brownian particles. However, such an analysis is not always straightforward, especially if the underlying force fields are non-conservative or time-varying, driving the system out of thermodynamic equilibrium. Here, we introduce a toolbox to calibrate microscopic force fields by analyzing the trajectories of a Brownian particle using machine learning, namely recurrent neural networks. We demonstrate that this machine-learning approach outperforms standard methods when characterizing the force fields generated by harmonic potentials if the available data are limited. More importantly, it provides a tool to calibrate force fields in situations for which there are no standard methods, such as non-conservative and time-varying force fields. In order to make this method readily available for other users, we provide a Python software package named DeepCalib, which can be easily personalized and optimized for specific applications.
Funding:
|
H2020 European Research Council (ERC) Starting Grant ComplexSwimmers (677511). |
Optical Tweezers Go Smart
Giovanni Volpe
28 October 2020, 15:00
Invited Talk (Online) at OSA-EPN Student Chapter, Escuela Politécnica Nacional, Ecuador
Active Matter Meets Machine Learning: Opportunities and Challenges
Giovanni Volpe
26 October 2020, 13:45 CEST
Keynote talk (Online) at the Online Conference Motile Active Matter, Jülich Förschungszentrum, 26 October 2020
Abstract: Machine-learning methods are starting to shape active-matter research. Which new trends will this start? Which new groundbreaking insight and applications can we expect? More fundamentally, what can this contribute to our understanding of active matter? Can this help us to identify unifying principles and systematise active matter? This presentation addresses some of these questions with some concrete examples, exploring how machine learning is steering active matter towards new directions, offering unprecedented opportunities and posing practical and fundamental challenges. I will illustrate some most successful recent applications of machine learning to active matter with a slight bias towards work done in my research group: enhancing data acquisition and analysis [1, 2]; providing new data-driven models; improving navigation and search strategies [3, 4]; offering insight into the emergent dynamics of active matter in crowded and complex environments. I will discuss the opportunities and challenges that are emerging: implementing feedback control; uncovering underlying principles to systematise active matter; understanding the behaviour, organisation and evolution of biological active matter; realising active matter with embodied intelligence. Finally, I will highlight how active matter and machine learning can work together for mutual benefit.
References
[1] S. Helgadottir, A. Argun, G. Volpe, Digital video microscopy enhanced by deep learning. Optica 6, 506–513 (2019)
[2] S. Bo, F. Schmidt, R. Eichhorn, G. Volpe, Measurement of anomalous diffusion using recurrent neural networks. Phys. Rev. E 100, 010102(R) (2019)
[3] G. Volpe, G. Volpe, The topography of the environment alters the optimal search strategy for active particles. Proc. Natl. Acad. Sci. 114, 11350–11355 (2017)
[4] S. Colabrese, K. Gustavsson, A. Celani, L. Biferale, Flow navigation by smart microswimmers via reinforcement learning. Phys. Rev. Lett. 118, 158004 (2017).
Quantitative Digital Microscopy with Deep Learning
Giovanni Volpe
22 October 2020, 14:00 CEST
Invited Seminar (Online) at Disruptive & Sustainable Technologies for Agricultural Precision (DiSTAP), Singapore-MIT Alliance for Research and Technology (SMART) Centre, Singapore & Boston (MA)
Abstract: Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we introduce a software, DeepTrack 2.0, to design, train and validate deep-learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user-friendly graphical interface, DeepTrack 2.0 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.
References:
Benjamin Midtvedt, Saga Helgadottir, Aykut Argun, Jesús Pineda, Daniel Midtvedt, Giovanni Volpe, “Quantitative Digital Microscopy with Deep Learning”, arXiv:2010.08260 (2020)
Giovanni Volpe will give an online invited presentation at the First Global Symposium on Janus Particles (GSJP) 2020.
GSJP will bring together a collection of experts who are in the vanguard of scientific and engineering investigations on Janus particles all around the globe.
The contribution of Giovanni Volpe will be presented according to the following schedule:
Giovanni Volpe
Light-controlled Assembly of Active Colloidal Molecules
Activity and life have emerged from a primordial broth of simple building blocks when the presence of energy flows made these blocks come together and interact in non-trivial ways. Here, we use experiments and simulations demonstrating that active molecules can be created and controlled by light. Shining light on a primordial broth containing passive particles of two different species, we create active colloidal molecules of increasing complexity, which behave as migrators, spinners and rotators. This demonstrates a powerful new route for nonequilibrium self-assembly, which may help explaining the emergence of complex systems in living matter and may also proof useful as a design principle for the construction of flexible micromotors and cargo transport in health care applications.
Date: 1 October 2020
Time: 10:10 (EST)
Place: Online
A summary in Swedish of our previously published article “Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning” has been published in Fysikaktuellt, the journal of the Swedish Physical Society (Svenska fysikersamfundet).
Article: “Diagnostisering av sjukdomar förbättras med maskininlärning”, Saga Helgadottir, Giovanni Volpe and Stefano Romeo (in Swedish)
Original article: Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning
Press release:
Algoritm lär sig diagnostisera genetisk sjukdom (in Swedish)
An algorithm that learns to diagnose genetic disease (in English)
Giovanni Volpe will give an online invited presentation at the Student Conference on Optics and Photonics (SCOP), organized by the OSA student chapter of Physical Research Laboratory, Ahmedabad, India.
The conference addresses various topics in optics with an emphasis on non linear optics and quantum optics, will be held during 23-25 September, 2020 at the Physical Research Laboratory (PRL), Ahmedabad, India.
The conference includes invited talks by eminent scientists from India and abroad, as well as posters and oral presentations by student participants and research fellows.
The contribution of Giovanni Volpe will be presented according to the following schedule:
Giovanni Volpe
Deep Learning for microscopy and optical trapping
Date: 25 September 2020
Time: 15:10 IST (GMT+5:30)
Place: Online
