Deep learning talk @Zalendo Tech Event

First Zalendo Tech Event at their Tech HQ nearby Alexanderplatz yesterday evening. To open their series of Meetup event Zalendo invited Professor Sepp Hochreiter of Johannes Kepler University in Linz to talk about deep learning. 

attentive crowd

About the talk
The talk was good but not adapted to an academic audience. If you are familiar with the topic you probably wouldn't have learned something new. But the talk did lead to interesting - and often expected - questions around and about deep learning. Sadly - to me - it was more where does it work?, what are the best parameters? than how does it work actually? 

As the speaker did remind to us, neural networks (NNs) aren't new on the market. They were discoveries years ago, it was promising and then nothing, other techniques were used, leaving specialists in their niche. I do remember courses during my master in image processing about 15 years ago [in Pierre et Marie Curie Paris VI] where the person teaching and introducing KNN and NNs sounds both excited and disenchanted. This until computers got faster (thanks to cpu, gpu, many-core, cluster, graphic card programming "et j'en passe") and suddenly it was possible to use NNs, to get results, to reproduce them and to beat classification challenges by far comparing to the expert of the field.

For every new promising technique there is the temptation to use if for everything in a brute force manner. But it doesn't work all the time. One remark given by the speaker is these solutions work when you are overloaded with data, when you immersed into data. It's not a surprise that big players such as Google, Facebook, Amazon and more are heavy on growing their deep learning team.

About automation, AI and drugs
You hear and see more and more presentations about deep learning, artificial intelligence (AI) where people are dreaming of AI being able to put words on a given image in a similar way a human will do. It's kind of working but there is no magic. It made me remember about an experiment where the researchers claimed to be able to produce images/video corresponding to the images we see in our dreams. Often people fear - and they can - about computer taking control over us, making decisions for us until we start working for them.

It is interesting to understand why pharmacy companies - those making drugs - are so big into deep learning. Bio-Informatics offer the perfect environment for developing big data solution. Here I'm not talking about the phase where drug need to be tested and evaluated on human but what happen before. Biology and chemistry (or computer chemistry) can be simulated using pretty accurate models, meaning you don't need to run an actual biological or chemical experiment. You can simulate the experiment, generate a huge amount of data and let your algorithm do the analysis. And guess what, computer vision, machine learning, deep learning - not to mention optimization - are part of the solution. And the faster you get your results, the faster you have a new drug to potentially introduce on the market hopefully before your competitor. I'm not sure "normal" people got a glimpse on that side of research, in that field it's actually the biological/chemical experiment that will validate a virtual experiment (remember to watch Terminator 4 or 5 at leas the last on screen...).

About the big brain project and graphic cards and evolution
Research is cool. It's very interesting to see how connections/links between highly specialized fields are happening to build a new framework for research. The big brain project (not sure about the name but there is the US and the EU version) is the perfect example, different fields from neuroscientists to computer graphics and hardware manufacturers need to collaborate to build this virtual brain model.

One of the last comment from the speaker yesterday had a pertinent echo in my head. This comment illustrates perfectly how technology is evolving and frameworks are crossing their paths. He told us that graphic card manufacturer (such as nvidia to not name them) are now developing hardware dedicated to run deep learning process, once again the hardware architecture helping to fasten a programmed algorithm. But until when and is it a good approach? 

Years ago and not so long time ago when computers were already getting faster, people were designing hardware to run image processing/computer vision algorithms. This because the computers in their at-this-time state weren't fast enough. Like the brain was too small and needed to grow or modify its physical body to evolve. But then computer became faster and those special design weren't adaptable enough, too specialized. I feel that we are living a similar state with deep learning. The question will be is hyper-specialization of computer hardware the solution - momentarily for sure - for deep learning or not?

About the future
We are all doomed. Soon computer will be smart enough to redesign their body when they will reach their limits to overpass them. I haven't any spoiler about how and when, out Mayan friends had a big fail about it three years ago, we have to be patient.



Dans l'enfer du Märkisches Schweiz

We did it, after 12hours we did it! We went through all normal stages of an impossible bike mission. Small teaser we did follow a kind of a non logical order to do these stages, meaning we first took a lot of breaks and detours and then we started the tour. Also we weren't completely lucky. The tale step by step.

11:37 Lichtenberg train station
The five fantastics are almost all in time for the regional bahn. First detail thousand people with bikes were also in time and the train only have 5 bike places... It's a no go. We change platform and take the S-Bahn until the end to S-Strausberg and decide to do the planned bike tour in reverse mode. The goal once in Strausberg will be to cycle 35km to the Bahn station Obersdorf.

Coffee and bockwurst break in Strausberg
Already 5km (!!!) and first stop in the lovely old Strausberg village tiny burg. Train in Obersdorf is scheduled for 18:39, we have time. We completely deserved this coffee break at Milchbar.

After getting lost in the big city Strausberg while trying to start pursue our soon to be called odyssey we arrive at the lost Pyramide Grazau. Nice little village around and about 15km on the counter. It's also our first detour as leaving the pyramid part of the team decided - unintentional of course - to go toward Ekner which absolutely on the opposite direction of our planned trip.

15:03 picnic at the lac
Back on track we make our first real stop for the picnic. The public beach of Lange See is just for us. Incredible birds are flying around - mostly ducks - and it's a lovely Saturday with friends. Only thing is we started the trip 2hours ago and have done only 20km on the 35km, also some drops are coming.

In the heart of Märkisches Schweiz
The next 15km allows to experience the beautiful region despite the clouds. It's going up and down but completely doable even with shitty bikes. Thanks to our guide tour leader - we call it the PR girl or Anne who is screaming about the beauty of the region while cycling in the middle of the roads with the wind we barely understand what she says but she looks happy so we don't disturb her - we discover more lovely villages.

In Buckow - also called the pearl of the Märkishes Schweiz - the rain shower is a kind of warning: do we continue to Obersdorf under the rain or we go back now to where we start??? We decide to now listen to the sky messages and pursue again our trip.

18:15 Seeing Obersdorf and leaving
The landscape is still lovely and hilly.  Three hamlets further full of white and black sheeps we finally reach - in time we thought - our final destination and train station of Obersdorf.

The story is repeating itself, the train is full of bikes and we can't get in...

After strong negotiation between the five fantastics two main ideas arise on the top of the consensus being we go back to Strausberg where we know there will be S-Bahn every 10min, this instead of waiting one hour for the next train still with the chance to not have places, again.

The Obersdorf agreement
First idea is we follow the same way, we know it and it's all along a bike way which is good when we don't have lights on our bikes. Second idea is we take short-cuts by going on roads we don't know with cars on it and we don't have lights... First option is chosen, the reason win, Cartesian spirit for life, on the road again, only 35km remains.

21:12 Strausberg again
A last rush on the platform to change train with bags on our shoulder, open beers in hand and the door closing... But we made it and we are mainly dead.


Voir des oeuvres d'art ou voir des gens regardant des oeuvres d'art?

La bonne question me direz vous. Ayant fini ma journée tôt - car elle avait elle même débuté très tôt - je décidais d'occuper mes trois heures de libre avant d'aller diner chez des amis en début de soirée par un mini opening-marathon-challenge. Challenge qui s'est aussi transformé en une course contre la montre et un jeu de piste avec l'orage qui tourbillonnait et se rapprochait de Berlin en fin d'après-midi.

18:40 direction la Loock Galerie sur la Postdamer Straße. A mi-chemin je fais une mini-pause Côtes du Rhône aux autres Galeries, par mini-pause j'entends "achat d'un bouteille et non dégustation". Je poursuis, traverse Potsdamer Platz, slalome entre les touristes, passe la Philharmonie et arrive dans le quartier des galeries. Trois voir quatre galeries sont ouvertes, du monde dedans et du monde dehors. J'aime bien cet endroit, les bâtiments sont propices à héberger des lieux d'exposition, suffisamment neutres et modulables et parfois des belles images.

Des belles images donc, en grand, en noir&blanc, de lieux et gens aux Etats-Unis. Rien de très nouveau mais je me répète, des belles images, bien composées, propres, pour des vues presque figées, on ne sent pas vraiment l'instantané, mais au moins ca me parle. En bonus la bière du vernissage est une Flensburger, un gage de gout de de qualité. La population est assez anglophone, américaine dirais-je et je glane quelques bouts de conversation où chacun y va de son anecdote géographique pour montrer qu'on voyage.

Environ douze minutes après avoir averti FourSquare de ma présence je file. J'ai encore au programme trois lieux et un diner dans moins de trois heures. Dehors le vent souffle et le gros nuage gris foncé tonne et des éclaires sont visible.

19.46 je pénètre dans la WeGalery. Le temps de souffler je crée le lieu sur FourSquare et commence à regarder autour de moi. Nous sommes dans le bas de Friedrichstrasse vers la Mehringplatz. La rue est un mélange de vieux bâtiment assez beaux et d'autre reconstruits assez laids. Il n'y a pas grand monde et le vernissage a débuté il y a déjà une heure. Dehors c'est l'apocalypse, les gens arriveront plus tard ou mouillé ou les deux.

Une exposition groupée, des artistes italiens, d'ailleurs la population est majoritairement italienne, habillée classe sobre avec gout à l'italienne. Le stagiaire ou l'assistant de la galerie est en panique et commence à courir partout et en prenant des photos avec son téléphone pommé. On doit être une vingtaine, probablement le record du jour et il veut en garder des preuves! Dans son rush il shoote du pied un bout d'une des oeuvres d'art exposée, au moins ils se passent des choses. Les oeuvres sont à l'image des visiteurs, propres, ca brille d'argent mais pas d'or, les formes sont plaisantes à l'oeil, déjà vu mais harmonieux, penchant parfois vers le design. Une connaissance arrive mais je dois filer, de plus la tempête fait une pause et je me dois d'en profiter! De plus mauvais choix de bière.

20:14 changement de lieu et de décor pour le Kunstquartier Bethanien et une autre exposition vernissage appelée hate10 - Kongress der Moglichkeiten ou le congrès des possibles? Ca se passe dans une partie uniquement du bâtiment où ils  passent parfois des choses intéressantes en particulier dans les ateliers et autres workshops. Mais pas cette fois. C'est hipster à souhait, tout parait bricolé, pas fini, bancal, cheap. Ca contraste pas mal avec ce que je viens de quitter. Population assez jeune avec au milieu un ou deux vieux artistes habillés jeunes essayent de communiquer. Tout ca pour dire que je ne reste pas longtemps. Un gros cliché que cet évènement.

Les jours de vernissages sont comme du pain béni pour nos amis outre-quiévrains sociologues ou anthropologistes. Le moment parfait pour observer des tribus, pas forcément pour voir des oeuvres d'art... Les vêtements changent mais les rapports de force restent les mêmes. Il faudra sans doute revenir une autre fois pour revoir quelque unes des images et installations aperçues ce soir.

20:58 je me rapproche de la Zion Kirche, en traversant Berlin j'ai pu voir barricades prêtes pour aujourd'hui, les colonnes de voiture Polizei prêtes, le gros de l'orage est passé mais comme chaque 30 avril au soir la ville s'attend au pire pour le lendemain. Mal sehen comme on dit.

Puis le dîner eu lieu, la dégustation de vin aussi et la soirée fût très agréable. Pour nos amis statisticiens, quatre personnes, trois nationalités - française, espagnole et anglaise - avec au menu un plat italien, tout ca dans une ville allemande.


An evening in the beer garden

For the fan of Community, my cake - a modified version of the classic "gateau au yaourt" with blueberries and a tiny bit of coco nuts flakes - with the candles on the top looks pretty much like an attempt of diorama where it would been asked to the students to illustrate the Vesuvius eruption. The cake almost exploded, "a brillé de mille feux" said some people and was delicious.

I swear I'm telling the truth
Alcohol makes you more confident. The proof? Being able to tell in a conversation to an American, a Japanese and a Portuguese that yes there is often big snowstorm in Cap Verde. To help my listeners were also drinking, but at some point I could see the confusion on their faces until I realize that the wrong word was coming out of my mouth. I meant sandstorm but said snowstorm, probably the charm of  French people speaking English...


Run forest, run and don't forget to drink water

10:33am wake up with the feeling maybe you drunk one or two beers too much yesterday evening, this despite the good evening. Without a good evening the morning would have been terrible. It was a classic international Friday: meet the spotters from Berlin plus the spotters bosses from Amsterdam plus a visiting spotter from Vilnius and later re-meeting for the first time in 14 years a fellow from Ecole Polytechnique de Montréal and Polyscope. All and all a blast :-)

Some statistic for Friday evening: talked with 10 people, 8 different nationalities. Take that morons.

3:33pm getting some rest in order to give to my body the time to reload before the run. I register for the airport night run in Berlin. They do it regularly and after some years I finally did register, not for the 10km but for the half-marathon.

7:01pm  in night run there is night. The half-marathon group starts now and the 10km group one hour later. The feeling you have for this run is pretty cool. The new airport BER is there but empty and you are running on the landing area and tarmac. Two loops to do of 11km something and 10km and the first line is toward the East, the sun is going down, there is nothing miles around you, just some clouds, look to the North and you can see the top of the tv tower and you keep running.

Passing the sign 7km is nice, a third of the run is down! The group is now stretched, I'm running alone, my time after 5km is in my range (below 25min), but sadly I'n not fast enough to keep the same speed of the few jogging babes... my first attempt to drink water without stopping is a big failure as I only manage to spread water in my face.

8:00pm First loop done, meaning for me 11km something in less than an hour, I'm in my time track. As we reach 8:00pm the second group of runners is launched and soon two speed groups are mixing. It's a bit like in zombies movie when a crowd of zombies are all running in the same direction. If you have seen War Z and remember the scene with airplanes chased then it's the same, except there are no planes as the airport is still not open...

8:55pm I'm crossing the arrival line. I'm relieved, less than two hours as I was planning/hoping to do! The temperature is freaking cold, near 4 degrees Celsius only, so fast changing clothes and I leave.

11:04pm S-Bahn, tramway and bike later and I enter the Studios-ID in the middle of Alt-Hohenschönhausen. It's their open studio evening event where I know some the artists (check the website of Kyle Fitzpatrick).

I'm a bit destroyed but I managed to stand on my legs. I talk with many people, once again it's über international, Americans from Miami and Chicago, Russian, German, Portuguese and many more. English, French and German in the same conversation, after my legs it's my brain which is working. And at the question so you are an artist too the response is always or becomes complicated. Well I say, I'm working with color, I'm a color and imaging scientist bla bla bla... but it's usually a good start.

1:04am time to go home, I jump on my bike, 7km to do to reach my bed. The night is fresh but the stars visible. Another full day full of new images in my head.