BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132530Z
LOCATION:Henry Dunant
DTSTART;TZID=Europe/Stockholm:20210707T110000
DTEND;TZID=Europe/Stockholm:20210707T130000
UID:submissions.pasc-conference.org_PASC21_sess143@linklings.com
SUMMARY:Recasting Brain Tissue Simulations as a Machine Learning Problem?
DESCRIPTION:Minisymposium\n\nWith the recent success of machine learning, 
 interest was sparked in various computational domains to use those methods
  to recast certain simulation problems as machine learning problems. In ne
 uroscience, simulating biophysically detailed models of neurons and brain 
 tissue models has become an important tool, complementing experiments and 
 theory. However, already simulating a single detailed neuron may require t
 he solving of 10,000 differential equations, which is computationally cost
 ly and sparks the desire to explore whether a recasting of the problem is 
 possible. This mini-symposium explores this question through three present
 ations and a panel discussion:  A first presentation will describe how qua
 ntum mechanics can be recast as a machine learning problem. Next, we will 
 learn about the possibilities of approximating detailed models of neurons 
 through deep artificial neural networks. The third talk will introduce how
  physics-informed neural networks can be used to compute forward and inver
 se problems for partial differential equations. Finally, the panel discuss
 ion will explore what we can learn from these approaches for recasting the
  simulation of brain tissue as machine learning problems.\n\nMany-Body Qua
 ntum Mechanics as a Machine Learning Problem\n\nCarleo\n\nThe theoretical 
 description of many-body quantum phenomena fundamentally relies on the sol
 ution of a “big-data” problem. In recent years, several machin
 e learning approaches have been developed in quantum physics, aiming at ta
 ckling the infamous quantum many-body problem from a new persp...\n\n-----
 ----------------\nRecasting Brain Tissue Simulations as a Machine Learning
  Problem - Panel Discussion\n\nSchürmann, Awile\n\nThe panel assembles the
  speakers of this minisymposium and will animate a discussion on what can 
 be learnt from their research for recasting other scientific simulation mo
 dels as a machine learning problem. More specifically, we will discuss whe
 ther this approach could help reduce the time-to-soluti...\n\n------------
 ---------\nApproximating Single Neurons with Deep Convolutional Neural Net
 works\n\nBeniaguev\n\nUtilizing recent advances in machine learning, we in
 troduce a systematic approach to characterize neurons' input/output (I/O) 
 mapping complexity. Deep neural networks (DNNs) were trained to faithfully
  replicate the I/O function of various biophysical models of cortical
  neurons at the millisecon...\n\n---------------------\nPhysics Informed N
 eural Networks for Simulation of PDEs\n\nMishra\n\nComputer simulations of
  systems modelled by partial differential equations is a mature field. How
 ever, several large scale problems are currently unfeasible on account of 
 the computational costs. Machine learning, particularly deep learning tech
 niques are being increasingly used to accelarate or fac...\n\n\nDomain: CS
  and Math, Chemistry and Materials, Physics, Life Sciences, Engineering
END:VEVENT
END:VCALENDAR