[PIDSIA] Amphibious Krock 2 robot and challenges in multimodal locomotion by Matthew Estrada, September 23 at 11.30, room 222
2:16 p.m.
*Title:
Amphibious Krock 2 robot and challenges in multimodal locomotion
*Abstract:
Salamander inspired platforms have been used to study robotic/biological
locomotion in the Biorobotics Laboratory at EPFL for over a decade, drawing
parallels between humanmade and natural systems to improve our understanding
of both. Our most recent iteration, Krock 2, is targeted towards search and
rescue applications within the NCCR Robotics program. Previously
demonstrated in terrestrial applications, it is now being introduced into
the water through the use of a dry suit and undulatory swimming gait.
Multimodal locomotion carries the inherent challenge that the morphology and
actuation for one mode may not be useful, or even present a hindrance, for
another. On the other hand, unique synergies between modes of locomotion can
present themselves. Its sprawling-posture gait and capability to swim along
the water's surface manage to avoid the persistent challenge of balance
within legged locomotion. However, this comes with inherent challenges in
the perception of the environment, which we are addressing in
collaborations.
*Speaker:
Matthew Estrada is a Postdoctoral Researcher at the Biorobotics Laboratory
(https://www.epfl.ch/labs/biorob/), EPFL. He is currently leading the
hardware development, control, and simulation of the amphibious Krock 2
robot under the Swiss NCCR Robotics program.
*Date:
Wednesday, September 23, 2020, at 11:30
*Location:
Manno, Galleria 1, 2nd floor, room 222
*Doodle registration:
Due to COVID19 guidelines, there are limited available places in the booked
room. Please state your attendance or virtual attendance in this doodle:
https://doodle.com/poll/vqhsnkvw3ufwawh5
*Pizza:
Due to COVID19 restrictions, there will be no pizza after the meeting.
--
This message was scanned by SUPSI mail-scanner and is believed to be clean.
1:55 p.m.
New subject: [virtual PIDSIA] Metabolic windows into ageing by Janna Hastings, October 29 at 11.30
*Title:
Metabolic windows into ageing: A multi-omics metabolic modelling approach to understanding
ageing at a systems level
*Abstract:
Metabolism is central to all processes of life and the metabolome -- large-scale
measurement of the quantities of small molecular entities in cells and tissues -- gives a
readout of cellular functioning at a point in time. Harnessing metabolomic information
together with transcriptomic information about gene expression allows for multi-level
insights into genetic dysregulation and its cellular effects. I will describe a
multi-omics approach based on genome-scale modelling that is able to integrate the two
levels and provide insights into the systems-level deregulation of cellular function due
to ageing by transforming the cellular reaction space into a constraint-based linear
optimisation problem. Metabolic models such as these and their interpretation depends on
publicly available data about small molecular metabolites. Chemical ontologies provide
structured classifications of chemical entities that can be used for navigation and
filtering of chemical space. ChEBI is a prominent example of a chemical ontology, widely
used in life science contexts including to annotate metabolites in genome-scale models.
However, ChEBI is manually maintained and as such does not scale to the full range of
metabolites in all organisms. There is a need for tools that are able to automatically
classify chemical data into chemical ontologies, which can be framed as a hierarchical
multi-class classification problem, based on chemical structures, which are represented as
connected graphs of atoms and bonds. I will discuss recent efforts to evaluate machine
learning approaches for this task, comparing different learning frameworks including
logistic regression, decision trees and LSTMs, and different encoding approaches for the
chemical structures, including cheminformatics 'fingerprints' (feature vectors)
and character-based encodings from chemical line notation structural representations.
*Speaker:
Janna Hastings is a computer scientist who applies semantic technologies to address
challenges in scientific data management and discovery. She is currently a post-doctoral
researcher at the Department of Theoretical Computer Science, Otto-von-Guericke University
Magdeburg, Germany, and an expert consultant to the Center for Behaviour Change,
University College London. She holds a PhD in Computational Biology, an MSc in Computer
Science and an MA in Philosophy.
For a full list of publications, see Google Scholar:
https://scholar.google.com/citations?hl=en&user=cz-hhPUAAAAJ
<https://scholar.google.com/citations?hl=en&user=cz-hhPUAAAAJ>;.
*Date:
Thursday, October 29, 2020, at 11:30
*Zoom link:
https://supsi.zoom.us/j/98358510987?pwd=Z2hLRTY4TytweDRCcHB4MkFFaTIzdz09
ID meeting: 983 5851 0987
Passcode: 183530
--
This message was scanned by SUPSI mail-scanner and is believed to be clean.
11:29 a.m.
New subject: [virtual PIDSIA] Metabolic windows into ageing by Janna Hastings, October 29 at 11.30
*Title:
Metabolic windows into ageing: A multi-omics metabolic modelling approach to understanding
ageing at a systems level
*Abstract:
Metabolism is central to all processes of life and the metabolome -- large-scale
measurement of the quantities of small molecular entities in cells and tissues -- gives a
readout of cellular functioning at a point in time. Harnessing metabolomic information
together with transcriptomic information about gene expression allows for multi-level
insights into genetic dysregulation and its cellular effects. I will describe a
multi-omics approach based on genome-scale modelling that is able to integrate the two
levels and provide insights into the systems-level deregulation of cellular function due
to ageing by transforming the cellular reaction space into a constraint-based linear
optimisation problem. Metabolic models such as these and their interpretation depends on
publicly available data about small molecular metabolites. Chemical ontologies provide
structured classifications of chemical entities that can be used for navigation and
filtering of chemical space. ChEBI is a prominent example of a chemical ontology, widely
used in life science contexts including to annotate metabolites in genome-scale models.
However, ChEBI is manually maintained and as such does not scale to the full range of
metabolites in all organisms. There is a need for tools that are able to automatically
classify chemical data into chemical ontologies, which can be framed as a hierarchical
multi-class classification problem, based on chemical structures, which are represented as
connected graphs of atoms and bonds. I will discuss recent efforts to evaluate machine
learning approaches for this task, comparing different learning frameworks including
logistic regression, decision trees and LSTMs, and different encoding approaches for the
chemical structures, including cheminformatics 'fingerprints' (feature vectors)
and character-based encodings from chemical line notation structural representations.
*Speaker:
Janna Hastings is a computer scientist who applies semantic technologies to address
challenges in scientific data management and discovery. She is currently a post-doctoral
researcher at the Department of Theoretical Computer Science, Otto-von-Guericke University
Magdeburg, Germany, and an expert consultant to the Center for Behaviour Change,
University College London. She holds a PhD in Computational Biology, an MSc in Computer
Science and an MA in Philosophy.
For a full list of publications, see Google Scholar:
https://scholar.google.com/citations?hl=en&user=cz-hhPUAAAAJ
<https://scholar.google.com/citations?hl=en&user=cz-hhPUAAAAJ>;.
*Date:
Thursday, October 29, 2020, at 11:30
*Zoom link:
https://supsi.zoom.us/j/98358510987?pwd=Z2hLRTY4TytweDRCcHB4MkFFaTIzdz09
<https://supsi.zoom.us/j/98358510987?pwd=Z2hLRTY4TytweDRCcHB4MkFFaTIzdz09>
ID meeting: 983 5851 0987
Passcode: 183530
--
This message was scanned by SUPSI mail-scanner and is believed to be clean.
9:34 a.m.
New subject: [virtual PIDSIA] Monte Carlo Planning and Applications by Oleg Szehr, Dec. 10th at 11.30
*Title: Monte Carlo Planning and Applications
*Abstract: Multi-period planning problems have experienced an increasing industry interest
reflected within IDSIA's project pipeline. On the research side, this demand is
complemented by the emergence of strong Monte Carlo search techniques over the recent
years. The resulting decision-making agents have demonstrated super-human performance in
complicated toy scenarios, such as game-play of Hex, Go, Chess, StarCraft, ... This talk
introduces Monte Carlo planning theory and applies it to two planning problems to serve
industry demand: The hedging of financial derivative contracts (with UBS) and military
decision making (with ArmaSuisse).
*Speaker: Oleg Szehr studied at ETH Zurich and followed a scholarship of the Bavarian
academy of sciences to conduct a PhD in Mathematics at the MPQ Garching.
After a PostDoc as a Mathematician at the University of Cambridge, OS was working for
several years as an Investment Banking Quant. In this role he was responsible for the
deployment and risk-monitoring of statistical models for investment firms like Aareal,
Allianz GI, Credit Suisse, SEB,... OS has also supervised a Quant Developer/ Programmer
team at Credit Suisse. OS joined IDSIA as a researcher in 2019.
*Date:
Thursday, December 10th, 2020, at 11:30
*Teams link:
https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZmQ0OGNhMTgtMzZmMS...
12:29 p.m.
New subject: [NEW LINK virtual PIDSIA] Monte Carlo Planning and Applications by Oleg Szehr, Dec. 10th at 11.30
Dear all,
Due to some technical issues. Oleg’s PIDSIA, planned for this Thursday, December 10th, at
11:30, will *not* take place on Teams but on Zoom.
New link to the talk.
https://supsi.zoom.us/j/91843278932
ID meeting: 918 4327 8932
no password
*****
*Title: Monte Carlo Planning and Applications
*Abstract: Multi-period planning problems have experienced an increasing industry interest
reflected within IDSIA's project pipeline. On the research side, this demand is
complemented by the emergence of strong Monte Carlo search techniques over the recent
years. The resulting decision-making agents have demonstrated super-human performance in
complicated toy scenarios, such as game-play of Hex, Go, Chess, StarCraft, ... This talk
introduces Monte Carlo planning theory and applies it to two planning problems to serve
industry demand: The hedging of financial derivative contracts (with UBS) and military
decision making (with ArmaSuisse).
*Speaker: Oleg Szehr studied at ETH Zurich and followed a scholarship of the Bavarian
academy of sciences to conduct a PhD in Mathematics at the MPQ Garching.
After a PostDoc as a Mathematician at the University of Cambridge, OS was working for
several years as an Investment Banking Quant. In this role he was responsible for the
deployment and risk-monitoring of statistical models for investment firms like Aareal,
Allianz GI, Credit Suisse, SEB,... OS has also supervised a Quant Developer/ Programmer
team at Credit Suisse. OS joined IDSIA as a researcher in 2019.
*Date:
Thursday, December 10th, 2020, at 11:30
1230
days inactive
1310
days old
4 comments
2 participants
participants (2)
-
Announcements of talks＠IDSIA -
IDSIA Announcements of talks＠IDSIA