Projets
européens Human Brain et FuturICT
Jean-Paul Baquiast 18/10/2013
Lancement
du projet Human Brain
Faute
de temps nous nous bornons à reproduire ici un document
d'actualité publié par le site Kurzweil AI.
Nous avons plusieurs fois précédemment commenté
ce projet, qui est une extension du projet Blue Brain de l'Ecole
polytechnique fédérale de Lausanne. Nous y reviendrons
ultérieurement, en fonction des
compte-rendus publiés.
On
Monday, October 7, 2013, scientists from the 135 partner institutions
of the Human Brain
Project — “the world’s most ambitious neuroscience
project”— met at EPFL (Ecole polytechnique fédérale
de Lausanne), the coordinating institution, in Switzerland.
Over
the course of the coming week, neuroscientists, doctors, computer
scientists, and roboticists will fine-tune the project’s
details.
Six
months after its selection by the EU as one of its FET Flagships,
this project of unprecedented complexity, co-funded by the
EU with an estimated budget of €1.2 billion, has now
been set in motion.
With
more than 130 research institutions from Europe and around
the world on board and hundreds of scientists in a myriad
of fields participating, the Human Brain Project is the most
ambitious neuroscience project ever launched.
Its
goal: develop methods that will enable a deep understanding
of how the human brain operates. The knowledge gained will
be a key element in developing new medical and information
technologies.
Six
research platforms
The
Human Brain Project’s initial mission is to launch its
six research platforms, each composed of technological tools
and methods that ensure that the project’s objectives
will be met.
These
platforms are: neuroinformatics, brain simulation, high-performance
computing, medical informatics, neuromorphic computing and
neurorobotics.
Over
the next 30 months, scientists will set up and test the platforms.
Then, starting in 2016, the platforms will be ready to use
by Human Brain Project scientists as well as researchers from
around the world. These resources — simulations, high-performance
computing, neuromorphic hardware, databases — will be
available on a competitive basis, in a manner similar to that
of other major research infrastructures, such as the large
telescopes used in astronomy.
single_neuron_BlueBrain_web
A
3D model of a neuron: reconstructed from lab data. The sprouting
protuberances are pre-synaptic terminals, the points where
theneuron will form connections (synapse) with other neurons.
(Credit : EPFL/Blue Brain Project)
Neuroscience,
medicine and technology: the Human Brain project’s goals
In
the field of neuroscience, the researchers will have to manage
an enormous amount of data — in particular, the data
that are published in thousands of scientific articles every
year.
The
mission of the neuroinformatics platform will be to extract
the maximum amount of information possible from these sources
and integrate it into a cartography that encompasses all the
brain’s organizational levels, from the individual cell
all the way up to the entire brain.
This
information will be used to develop the brain simulation platform.
The high-performance computing platform must ultimately be
capable of deploying the necessary computational power to
bring these ambitious developments about.
Medical
doctors associated with the project are charged with developing
the best possible methods for diagnosing neurological disease.
Being able to detect and identify pathologies very rapidly
will allow patients to benefit from personalized treatment
before potentially irreversible neurological damage occurs.
This
is the mission of the medical informatics platform, which
will initially concentrate on compiling and analyzing anonymized
clinical data from hundreds of patients in collaboration with
hospitals and pharmaceutical companies.
The
Human Brain Project includes an important component whose
objective is to create neuro-inspired technologies. Microchips
are being developed that imitate how networks of neurons function
— the idea being to take advantage of the extraordinary
learning ability and resiliency of neuronal circuits in a
variety of specific applications. This is the mission of the
neuromorphic computing platform.
The
neurorobotics platform will focus on integrating neural network
simulations into robots (initially virtual ones), who will
benefit from new aptitudes such as learning ability or resiliency.
Next
milestone: 2016
The
platforms will be set up as part of a global, coherent project.
For example, the scientists will depend on the brain simulation
not only to better understand the mechanisms of neurological
disease and identify new therapeutic targets, but also to
update functional principles or even accelerate the development
of neuro-inspired technologies.
In
addition, these same technologies could contribute to meeting
the simulation’s computational requirements.
The
success of the Human Brain Project depends in large part on
the dynamics of exchange that will occur between its six platforms.
The
scientists involved in the Human Brain Project now have two
and a half years to finalize the research platforms. Once
these are established, researchers will have at their disposal
the infrastructures, tools and methods they need in order
to meet their objectives.
Now,
nine months after its selection as a EU Flagship, the project
is officially on its way.
Annonce du projet FuturICT
On
notera que le 2e grand programme équivalent de l'Union
européenne, FuturICT,
vient de démarrer aussi. Ses promoteurs annoncent ce
qui suit:
Grâce
à un financement d'un milliard d'euros en dix ans,
‘ce projet européen vise à ‘comprendre
et à gérer des systèmes sociaux complexes.
FuturICT intègre la technologie de l'information et
de la communication (TIC), les sciences de la complexité
et des sciences sociales, dans le but de modéliser
et simuler les aspects sociaux, technologiques, économiques,
démographiques et environnementaux de la société
européenne’
FuturICT est un effort multidisciplinaire international sans
précédent qui vise à combiner le meilleur
de la connaissance scientifique pour relever les défis
du XXIe siècle grâce à l'utilisation de
la puissance de l'information pour explorer la vie sociale
et économique sur la Terre et découvrir des
options pour un avenir durable »
Il
nous parait probable que le projet va s’appuyer essentiellement
sur les données qu’il est facile de recueillir,
parce que disponibles sur les réseaux numériques.
Ces données seront interprétées par des
"experts" qui ont déjà des idées
sans doute arrêtées sur leur signification.
Ceci d’autant plus que qu’elles seront recueillies
comme les autres Big data, interprétées par
des logiciels statistico-probabilistes qui reflèteront
les intérêts de ceux qui les ont conçus.
Pourquoi pas des services secrets déguisés en
agences gouvernementales ou en partis politiques Au mieux,
ces logiciels ’autonomiseront (en 10 ans, ils auront
le temps de le faire, nous expliquera Alain Cardon) et dans
ce cas, ne diront-ils pas n’importe quoi.
Mais que faire d’autre, sinon capituler devant un inobservable/inconnaissable?
Disons que pour améliorer la qualité scientifique
des travaux, il faudra impérativement diversifier les
intervenants. Vu la ruée des labos sur la manne proposée,
ce ne sera certainement pas le cas. Il faudra aussi intervenir
sur le web pour poser des questions un peu curieuses. Mais
sans grand espoir de voir ces questions recevoir des réponses.
Quant au fait qu’il n’y ait pas (ou presque pas)
de français dans la liste des Partners, cela n'est
pas étonnant. On peut penser que ces sujets dépassent
leur entendement.
Automates
Intelligents s'enrichit du 