Embed code
Note: this content has been automatically generated.
00:00:01
oh well mine i mean i work in the
00:00:06
c. d. is elaine omission centre imagery spain
00:00:10
yeah today oh i'm going to compliment ah beside us talk about it and so slow
00:00:16
and then we're going to to talk about three taste
00:00:19
also use a using this machine learning library
00:00:22
i first i will ah do you ah classification problem
00:00:26
comparing a psychic learn code into the tense are
00:00:30
after that we will these into the analysis based apps challenge
00:00:33
uh focus on that ah i won't these a
00:00:37
year uh doing a program with a for classification of an impact pretty soon for as there right
00:00:43
and after that i will be eating she'll uh the mixed system reverse engineer brain
00:00:48
a project that i'm i'm working on it so how many of these are
00:00:53
i'll actually working with some machines are there any library river has
00:01:00
okay nice so um former former these uh interaction
00:01:06
i'm just going to want to talk about the circle come pray tour
00:01:11
to see how easy ease to make like any kind of
00:01:15
classification problem you since i keep uh out there
00:01:18
and the a. p. i. often surfer for that i will use the titanic data
00:01:24
set trying to classify how you're probably t. to downright or to see inc
00:01:30
depending on the data of the passengers okay so i misinterpreted
00:01:37
file like a cheese is all the data does survive
00:01:41
h. and class uh in that data set why because ah
00:01:47
yeah with the titanic has signed a people will say like okay lest oh let's uh
00:01:52
safe first the tile and women are man and after they well i'll
00:01:58
look in after a at the fair or the amount of money
00:02:02
that the person you're we're paying for for the dated panic uh i'm bart said
00:02:08
something that i have a first i will like eh
00:02:12
comparing call for the uh second there and use it and that's for for importing like
00:02:18
the data and then i'm going to use like the one in and or like it's the regression model
00:02:25
and then it got also going to learn all like the matrix
00:02:28
that's like to learn kind deep gave us about the classification
00:02:31
uh i'm uh putting like the data uh as we teen
00:02:37
uh the training and the test they date that because this is very important in machine learning
00:02:43
we have like a data set and then we test data and then
00:02:47
we say o. k. a. from the side you're going to lair
00:02:50
from the training data and the test a you're going to test
00:02:54
if the state that uh ease oh it is good
00:02:57
i know or is not so at the end i owe us is split it with aside in a random state
00:03:04
but yeah the are the like these the logistic regression with our
00:03:09
so i could learn is no longer than one one line of
00:03:12
code okay like taking like this feat for the trainee
00:03:17
and we print accuracy how well is more of classify and he's doing as you can see
00:03:23
here we have like that all point sixty seven this is the first approach of
00:03:28
so i did learn as me file at all in the in the previous talk if you remember that it's an classifier
00:03:34
we have like an all point forty nine occurrences score
00:03:38
so are we should like also like be some kind of exactly yeah um compare how
00:03:43
well new libraries of machine carotene are doing in compare with tens of role
00:03:49
with tens of harm what i'm going to do you i'm going to import but they're here
00:03:55
but i'm also to import the web metrics because i'm in this approach
00:04:02
uh tons of low is a very like photographs of me highlight our cans eh said and this
00:04:08
room in this very meant i wanted to to put like all the accuracy to test the
00:04:13
a so here as you can see we also like test uh is breathing today training and test data
00:04:20
but here ah we use of the learn the linear classifier
00:04:25
that i haven't had a heart also like a lot done before and we do that
00:04:30
up to my server in the up there uh we use like the learning rate
00:04:34
but it means the how many are times we are going to you tell the
00:04:39
networks you learn from something okay so i'm here how we of freely
00:04:46
and yeah yeah we change the l. s. text the training
00:04:50
is that and they bought size that means that
00:04:53
i'm going to u. r. and put the data or far trainee
00:04:58
and eh tell like as the house instead okay there from a is there from the is there from these ideas there
00:05:04
is like oh i'm computation me doing this that and the learning rate that gave us like the the accuracy
00:05:11
so on this first experiment that conclusion was that okay
00:05:16
oh for the love first approach secular device like more accuracy
00:05:22
but when i was saying will to relieve feed their tents or flow model it works better
00:05:31
oh no it's you talk about our detector how important is to
00:05:35
seize the data and to get the data i mean
00:05:38
uh oh the poor is not um my dick box in which
00:05:42
you can pull on your column surrounding tissue are we soul
00:05:46
they think that has to have be or there and has to have i mean i'm in a
00:05:51
few months ago necessary east oh their main core
00:05:54
problems the they are uh trying to solve
00:05:57
once in here and make that like open for you know a tours all over the wall
00:06:03
one of the main our topics they cannot was to you oh
00:06:07
mm prevents make a program that could uh pretty eat
00:06:12
and classify of me was near or with bill objects
00:06:16
around the around the solar system a cycle
00:06:20
and not a nice they can be like a problem uh this classification
00:06:26
problem this problem is very see a human they have to be
00:06:29
like of serb in all the time they asteroids or the meals
00:06:33
so i'm going to tell you more or less how what
00:06:36
they at first are a no no of their battery or whatever and they all
00:06:41
see something okay they may i'll i'll classify a
00:06:45
base owned several points uh they see
00:06:49
like double c. t. the call or upset there and then they wait out
00:06:53
for awhile and then they officer that as their way through the time
00:06:58
so ah that problem here was how can we do something machine learning
00:07:05
how can we train them i thought that really light gave us like out all these uh human uh work
00:07:12
so we're well uh this project that was cool a beep us the right that
00:07:17
maurice though was that was an hour to get to our uh neural network
00:07:22
that could like help us to to classify i uh
00:07:27
we yeah uh the other night oh six technology geeks on that we
00:07:32
are basically are we're passionate about the potential from our machine learning
00:07:37
and we believe deeply uh in the power of producing knowledge to shoot data
00:07:43
how we knew all we have like the uh this problem of misery in the arts
00:07:48
and we wanted to pretty beat but we also wanted to classify how these uh could work
00:07:54
so at the end uh we went to openness arc that easily hewitt a up a
00:08:00
a platform that got a lot of they don't would you can like vibrate
00:08:04
and it's like the like the most like significant data sets
00:08:08
but who happens to you deal with this problem
00:08:12
uh one of those was the potential hostels as though it's a that that's it
00:08:16
that means like they have like an only me all the where like less than
00:08:20
all point all five has only got a synagogue units because that's the
00:08:25
the order that they asked to really has to our impact on earth once it's it is a those near
00:08:31
and also like the the um the more it's there is like the mini mm armies intersection
00:08:37
distance that we could have like with uh the errors and eh yeah and then you
00:08:44
uh we yeah as you know at the end like a a a and there really is no
00:08:48
no more than an input and an output and we use like several kind of functions
00:08:53
she'll i'll try to she is and give 'em the that a now don't i mean
00:09:00
so what we you know this is okay let saddam less used like o. r. three hundred
00:09:05
take 'em function and wave functions because that's the kind of uh oh our wheat
00:09:11
or trajectory that an asteroid cousin half and the l. e. r. t. team though
00:09:16
out that there were and how how the past it was was movie
00:09:22
so i'll sit me try that has told uh there is actually a surety
00:09:26
and here when when you're doing a a neural net and we were like oh i studied a lot
00:09:33
with mathematicians uh and uh the experts of the feel hot was a
00:09:38
these going to work so i the first uh late here
00:09:42
we were eh with these putting sell hasn't as though it's a
00:09:46
they thought and that is they came up like i classification
00:09:51
and that was like the happy and apollo astronauts those are the ones
00:09:57
uh that we want to you to this study because our there what entirely a dangerous to
00:10:04
impart oh and your bus but as i told
00:10:08
you before um a astronaut meek of
00:10:13
i thought i might feel and astronomical eh that's what we are
00:10:17
a workout with time review if you a way to die
00:10:22
and then you classify again there's the right you might change so
00:10:26
what's important for the for the neural net to know
00:10:30
then we were created another a year it was a a talking about how that time could impact
00:10:36
in the in the us that classification at the end we also like to use that i thought it
00:10:41
was so for you to know it starts with physics okay this is the physics are beta
00:10:47
then we have like they classification with a human knowledge and then we have like they get more chemist
00:10:54
a kind of classification because also when they're asked to come here by
00:10:59
you can see more things about it like the core or so um this is
00:11:03
like a a parity for classification that we put into the into the inordinate
00:11:09
of the uh be okay like tons of low will ones do
00:11:14
they say to you that your neural net is easy
00:11:18
and they have like put the uh based straightforward part that's that's okay but uh you'll have to you
00:11:25
a also have like some kind of a craft might see if a process
00:11:30
uh so i could leave yeah if not where you say okay i want
00:11:33
to sign an hour nap about whatever it ends as their rights
00:11:37
dots wherever at first i was that yeah that a really like a study that
00:11:42
that's it i'm fine a data set that goal from the general knowledge
00:11:47
to all the most out great or small knowledge if i want to classify
00:11:52
cats for example of details at the first layer i'd like eh
00:11:57
the eh uh pictures of uh get there that day and the for lex okay
00:12:01
and then go wow and then maybe i'd only the phase of upkeep and
00:12:06
and then i go up again and then it would only like their hair of updated so if
00:12:11
i saw a picture of a key then there's negative on depends on the cage okay
00:12:17
as i say i have been training all on your own a it didn't really recognise it
00:12:23
this is very important because if you don't know you know that in
00:12:27
only train like image of okay then we for our uh
00:12:31
without pay them for letting you get on our face of the gate and say this is okay and i don't see like
00:12:37
a tail and see so this important to seize the data to be
00:12:41
the yeah i mean it when you're training a neural net
00:12:45
you also have a lot of protocols a in this case we have like when you're recognising protocol that was already apple
00:12:52
that uh i i was too prone a lot of the car and be aware
00:12:56
of uh taking off a lot of the that this is a also important serene
00:13:00
and urinate because if not you are like a put a lot of noise
00:13:05
okay as in these are here to yeah estate off or or training
00:13:10
heart beat at the end this key because it not you do you could be doing all long
00:13:17
i'll be aware of that the uh the light years have to be able eighteen
00:13:21
each time you make a liar okay yes uh probably a in fact tons of low uh it's very
00:13:27
good for that good you can slice it insert or one of the main core units units
00:13:32
and then i put light second there for like a
00:13:37
year whenever you my whatever you want i want
00:13:41
but yeah i'll i'm uh we were we were already and uh one room between
00:13:46
now i'm on both twenty five a best projects are on the wall
00:13:53
in the first uh five for best use of data
00:13:58
right yeah mike aren't as a cool i say okay guys is great because you are like
00:14:03
really really really gain knowledge into a into an it not just like
00:14:08
a seasonal model and probably you i'm giving all the data
00:14:14
and i'm going to talk about what i believe is there are the future of of tons of low
00:14:21
it's more like the uh reverse uh in your uh part of
00:14:26
uh for that i will upload some on uh or that was a real story
00:14:31
that happened to me and how and how and how i deal with that
00:14:37
so um have you it's a goal i happier a troll on the internet in my two year how
00:14:44
it was like with this massive for me and i really really really hard time
00:14:50
and i i i i start to think about the warning us of they turn it on what is that digital wall
00:14:57
i'm in pro and over the human emotions
00:15:02
but i also was like getting to meet and i
00:15:05
get into the our goals busters batteries a case
00:15:10
in which she was like as much into here and some of the ah i realised that it was not i'm
00:15:17
and that uh we were like of implementing hate
00:15:21
a with b. data with data over the internet and what we really are doing without
00:15:28
so i was thinking about how can i i'm the do absolutely sure that really like help
00:15:35
me to to deal with that using maybe like okay yeah uh seventy to eighty channels
00:15:41
but also like artificial intelligence to to transform that we yeah
00:15:46
it to you and to to create something something new
00:15:51
that starts you to you all work with a with a number of
00:15:56
that uh it could help me like to identify those tools
00:16:00
z. you what was happening in like uh on the internet we
00:16:03
with eight and not i um use something uh about it
00:16:11
and then i i realise that the whole i'd say is that they thought was
00:16:14
very important so i'd like to meet basic all five emotion classification okay
00:16:20
uh the last phase like dealing with the during two thousand years and i'm
00:16:26
just uh taking like well what i believe there are high quality models
00:16:30
and implement the implement them into programming language okay so when you talk
00:16:36
about paid eight a. is an emotion that doesn't come along
00:16:40
as far as a hate at times uh uh in a sense of abhorrence of
00:16:44
a boring as a state and it can be like even transform into rage
00:16:50
uh so i created like oh with uh wait a back door thoughts of words
00:16:56
but i believe was like these um a plaster of uh how these emotion
00:17:01
was uh was working from the uh low level okay that was
00:17:05
like those other runs to the high level eh rates
00:17:11
and then we get like darby star tense our own known tons of not
00:17:16
uh we felt like the that much tomb gradient of the motion
00:17:20
oh reckon saying of these okay fine see like oh input other right
00:17:25
a that means that that that person i'm waiting he's oh okay or awards onto your
00:17:32
and then i i kept waiting to there there aren't there hate or there right
00:17:38
ah here is the mathematical model me try that told you
00:17:41
about um that the seas there for the classification
00:17:46
uh as we uh as he told you well uh we were
00:17:50
creating the brambles uh with old ways and i'm bias
00:17:54
and uh we will also like i would be that it's really may
00:17:58
show ten sample how that like the the points of information
00:18:02
is that like oh all these when you're doing a classification of our model and this is what oh out with me
00:18:08
try w. well about the this a multiplication between our the
00:18:13
by asked um we we soon like the bean
00:18:17
what a number are complex and things are not linear
00:18:23
so that yeah like the first like eh a grail of complex c. d.
00:18:28
that you can like give to enter network is making like convolutional
00:18:32
okay so have like these other more let me try that has that told you about
00:18:37
about the this linear function that draws the light you can like apply sigmoid function
00:18:44
but what does is like it transforms the light into
00:18:48
an exponential near well then it a pattern
00:18:52
so from this yes only with these are like well you
00:18:55
transform i it into an arrow um eh classification
00:19:01
also a place holder and stuff like there is a hard to take this space there um do you
00:19:06
need a break even on the court cross entropy like oh me try that they've you talk
00:19:12
about this so much but i think this is like a very important because it tells you like how well
00:19:17
the neural nets do you how well these uh and larry
00:19:22
and the some of the medical function that uh has like these um
00:19:27
the these uh aim to be at the end uh it's very important as
00:19:32
you say it like between instead and how we hope to my seat
00:19:36
we'll start decision because as you know like we're always like competing
00:19:39
wraps and we collect the day pretty sure we've oh on
00:19:45
the evaluation has two steps that are like quite important we correct yeah
00:19:50
then around and we see like that we see that it has
00:19:54
that's why i don't believe like deep learning is a mighty black box which you
00:19:59
put everything and you get like a resorts you have to be light cease
00:20:03
you are at first i will say like okay take like are they tell if
00:20:07
you know and we we sold you might know it as well okay
00:20:11
so you're he yeah and you correct upper these humans and they accuracy that u. k.
00:20:16
so then you can escape employed a lot of data so making like a small first and then a scale up
00:20:24
but you know no sean is not all the that is not like that state
00:20:29
that can like it's not picture motions are things are moving
00:20:34
on and and uh have like their their complexity
00:20:39
and i was like thinking how could i oh i'll start the that
00:20:44
the motion better and try to really really understand the troll
00:20:48
and now on only like make the picture of the troll in a separate time and try to to understand
00:20:54
better to saint uh in um more at great
00:20:58
and um better way so um i was thinking you know a lot about uh bats
00:21:04
because uh our division to inhabit a really out of maps ain't on it you know
00:21:09
what i was thinking about the um they eh imaginary numbers my numbers are great
00:21:16
because there are like that's that things that that's the next east
00:21:20
but when you buy it together they provide we'll things
00:21:24
or is scott r. a. s. colour eh but who's so
00:21:29
idea like i'm uh i was thinking like emotions
00:21:32
also i work as the majority numbers because we have
00:21:36
like they are emotions are like around as
00:21:40
and at the end like oh you drive us to an action that we can measure
00:21:46
so i'll i'll also i was thinking that emotional a hustler gradient
00:21:51
itself before you've got any movie showed you kind of
00:21:55
feel something you have like there but but i it's for you forget it
00:22:00
not like some kind of sensation so at the at this trial you could see okay i have this
00:22:05
notion but before even in motion or before being strong enough for me to to say something
00:22:13
oh it might be some kind of sensation that i could not even on the internet
00:22:18
so yeah i could i could do an awful in which i
00:22:21
got a see some tools actually are not swells yeah
00:22:27
so i can we like these kind of tense or a having like big
00:22:31
great of our of of on motion but also play their motion itself
00:22:37
that you know that like these matrix in which i can put like
00:22:40
how this emotion like uh wasn't working at every complex level
00:22:47
yeah i'd yeah it was great because i would like to do about
00:22:51
numbers like that to get to that sounds unlike loopy telling
00:22:55
to the okay guy i like the racial you cannot be like that and they might you know number like okay like
00:23:01
mm get real don't be like that so id and it's like
00:23:04
a a it's on um i max a conversation in between
00:23:08
in between numbers that you can has to say to you
00:23:12
to compare it to to robert's too complex uh problems
00:23:17
so now i'm okay the it gets better because i can like uh would like these neighbouring e. ah also
00:23:25
like i can like make these uh temple all in with i can put a complex number x.
00:23:30
and i can read also my controls a date i and i can like start
00:23:35
like making like bills downstairs again that have like that a complex eh apart
00:23:42
eh uh this uh complex part and i'll get you i don't know
00:23:46
if you have like been working out of we fed that's awful
00:23:50
right yeah and uh one of the things that i lost all this is that you can like
00:23:54
a size also the type of tense or that you can have
00:23:59
so for example if you're working with images you are going to
00:24:02
use hind i. t. thirty two in this case as i
00:24:05
was working with a complex number with this colour i was using like this kind of our uh this kind of things
00:24:13
so um what we were doing was like we were created a neural net
00:24:18
that was i given as surveys okay so this is i think this
00:24:22
they are the core future or or forty visiting tightly and now
00:24:27
and you'll hours programmers can create were like a like a neural net as a service
00:24:34
that go like be on this uh whereas the service and you can
00:24:37
like sort of a problem um uh you seeing using base
00:24:42
oh i don't know it's me kinda has a told you about this but if you i knew
00:24:46
he uh to tens of uh oh oh good like to you gain too much you're again
00:24:52
i recommend you like these uh oh that's awful later dot o. r. g.
00:24:58
the tissue like baby usually i'll uh with these other in it
00:25:02
and see the lay years that later suffocated we're protein
00:25:06
the relationship out of the data and the kind of problem that you want to solve it easy like out approach
00:25:13
to how the problem is going to to be heaven with is very useful ah and i
00:25:18
always uh when i think about the number that you know it for starting to call
00:25:23
ago here in se more or less the classification and see what davies has like a meeting
00:25:29
or a mom it's coherent so if you guys i neglected going to into neural nets
00:25:36
i really like a recall main this uh this uh website
00:25:41
and oh here i put like oh well it's a male than it in terms of goal
00:25:46
because okay uh are you you have see like arose data but how can i call
00:25:51
a neural net ah id fly the and run it and then ah
00:25:58
the most important thing that uh you're going to be dealing with and think you are the a heathen units
00:26:04
which may guy that has told you about also active in your own function we have seen
00:26:09
the asteroid exercise are we're dealing with that whole b. c. seemed like the eh
00:26:14
they they functions and re creations that we're going to have like kind
00:26:19
of the final classification problems the big they are going to solve
00:26:23
also that things like the the rainy day larry make the what the end
00:26:27
okay you have like the target audience village does that problem and the
00:26:32
layers of a cake and the function that i'm going to half the the
00:26:36
do you think that i'm going to put and the learning rate
00:26:42
and then i started thinking again that he is and say okay so uh
00:26:47
emotions are complex eh more complex even than that
00:26:51
because we're we're like hitting the internet
00:26:54
either it is a are flowing data all the time and is
00:26:57
changing and artificial intelligence um should be more light up each
00:27:03
are also problem and not d. n. like a brain is oh
00:27:09
um it's a a neural net of the neural nets
00:27:14
what i mean is that we connect a neural nets and we create a brains
00:27:20
okay so i d. and i think this is the problem
00:27:23
that artificial intelligence uh wants to really realise all okay
00:27:28
so i said let's say anything with my i'm actually i'm hitting with my my here troll
00:27:34
um i was thinking that at the end i wanted to have like a negative emotion
00:27:40
and i didn't want like a qwerty level of tool in or wherever i went and fear are real
00:27:46
motion on the on the stroll i want to change i want you to give all feedback on
00:27:53
that's for that a minute if uh to meet or met if
00:27:57
bird there is common into ah into a positive uh one
00:28:02
so ah limits is there is a part of the brain
00:28:07
there is like be on the new cortex okay
00:28:10
eh that basically uh it deals with our emotional selves
00:28:15
oh then you're cortex eh i mean dries for general intelligence worries
00:28:20
like oh oh memory and processing but linguistics and is different
00:28:25
it deals with uh oh we're strain for or couple eighteen
00:28:29
danger with uh dealing with o. o. where emotions
00:28:33
so at the end is a part of the brain that uh is like processing uh processing that
00:28:40
ah so ah ah i started seeing how and small oh and
00:28:46
you wear off of how how brains uh really work
00:28:50
and how these part of the brain at the end is like a influencing daniel cortex
00:28:56
and driving us into that ever a motion eh that's that's
00:29:00
generalisation and at the end we have like a structure
00:29:04
that would uh we could like impair or try to do our reverse engineer of that
00:29:09
so are the and uh and uh it's the it has like four main core parts gate
00:29:15
and and different a kind of a impulse we have that animals
00:29:20
and sensory cortex what isn't a recorded we had only for the front part and i mean that
00:29:26
and then we have to kind of different inputs that comes here
00:29:29
okay what we call sensory inputs i mean you might chase
00:29:34
we deal out of images you know where emotional brain wellstone emotional sickness
00:29:40
singers that i interpret their line my mathematical here models
00:29:45
so okay i i it's it's great yeah because i take
00:29:48
like the intention already like want training around it
00:29:52
all school that has without tones of images and i like it
00:29:57
to my emotional mathematical model created more complex a data sets
00:30:03
q. to deal with that uh uh for the it didn't say a um okay so
00:30:09
with input i have like images i have an emotional signal and then have
00:30:14
a a box that you know guys that you is not longer box
00:30:18
and then i have a uh let an output that is going to be another tweaked
00:30:23
this to me is how a is going to have on emotional gradient that goes from the being assertive okay you're
00:30:30
trying to me but i'm going to be as i'm going to put you on a circuit a to e.
00:30:35
jill compassion because at the end like a haters ah
00:30:39
or her like um are like oh own move
00:30:43
i'm so lost souls that have something to say and we shouldn't like just keep eight
00:30:48
apart we should be soon and we should uh also like so some compassion
00:30:54
about bass and now i'm dealing with uh then it's a the next
00:30:58
time it's for the is that is getting they they they tap
00:31:02
yeah i really need because uh i have like the insane shown a model data sets
00:31:07
in which i have like features of of trains or t.
00:31:11
tens or dogs right need a pictures of joy
00:31:16
i need pictures of being sat i need pictures of hate
00:31:20
so the data set that i mean it's like why mm specific for this
00:31:25
and there has to be huge so oh mm i'm a
00:31:29
i'm a working every day all on building this
00:31:33
eh but i yeah i also need like a tones of that uh burbank kind of a beta
00:31:41
that is giving me like those emotional emotional signals so um i
00:31:47
hope to one day like finish my my emotional brain
00:31:52
uh in the mean time if you will have the opportunity to see all of we get
00:31:58
with a troll a side eat uh please um forgive
00:32:03
uh but also stay calm okay and if eh it with
00:32:08
a heart she'll stay just away from from the phone

Share this talk: 


Conference program

Keynote
Jean-Baptiste Clion, Coordinator DevFest Switzerland
26 Nov. 2016 · 9:40 a.m.
How to convince organization to adopt a new technology
Daria Mühlethaler, Swisscom / Zürich, Switzerland
26 Nov. 2016 · 10:14 a.m.
Q&A - How to convince organization to adopt a new technology
Daria Mühlethaler, Swisscom / Zürich, Switzerland
26 Nov. 2016 · 10:38 a.m.
Animations for a better user experience
Lorica Claesson, Nordic Usability / Zürich, Switzerland
26 Nov. 2016 · 11:01 a.m.
Q&A - Animations for a better user experience
Lorica Claesson, Nordic Usability / Zürich, Switzerland
26 Nov. 2016 · 11:27 a.m.
Artificial Intelligence at Swisscom
Andreea Hossmann, Swisscom / Bern, Switzerland
26 Nov. 2016 · 1:01 p.m.
Q&A - Artificial Intelligence at Swisscom
Andreea Hossmann, Swisscom / Bern, Switzerland
26 Nov. 2016 · 1:29 p.m.
An introduction to TensorFlow
Mihaela Rosca, Google / London, England
26 Nov. 2016 · 2:01 p.m.
Q&A - An introduction to TensorFlow
Mihaela Rosca, Google
26 Nov. 2016 · 2:35 p.m.
Limbic system using Tensorflow
Gema Parreño Piqueras, Tetuan Valley / Madrid, Spain
26 Nov. 2016 · 3:31 p.m.
Q&A - Limbic system using Tensorflow
Gema Parreño Piqueras, Tetuan Valley / Madrid, Spain
26 Nov. 2016 · 4:04 p.m.
How Docker revolutionized the IT landscape
Vadim Bauer, 8gears AG / Zürich, Switzerland
26 Nov. 2016 · 4:32 p.m.
Closing Remarks
Jacques Supcik, Professeur, Filière Télécommunications, Institut iSIS, HEFr
26 Nov. 2016 · 5:11 p.m.
Rosie: clean use case framework
Jorge Barroso, Karumi / Madrid, Spain
27 Nov. 2016 · 10:05 a.m.
Q&A - Rosie: clean use case framework
Jorge Barroso, Karumi / Madrid, Spain
27 Nov. 2016 · 10:39 a.m.
The Firebase tier for your app
Matteo Bonifazi, Technogym / Cesena, Italy
27 Nov. 2016 · 10:49 a.m.
Q&A - The Firebase tier for your app
Matteo Bonifazi, Technogym / Cesena, Italy
27 Nov. 2016 · 11:32 a.m.
PERFMATTERS for Android
Hasan Hosgel, ImmobilienScout24 / Berlin, Germany
27 Nov. 2016 · 11:45 a.m.
Q&A - PERFMATTERS for Android
Hasan Hosgel, ImmobilienScout24 / Berlin, Germany
27 Nov. 2016 · 12:22 p.m.
Managing your online presence on Google Search
John Mueller, Google / Zürich, Switzerland
27 Nov. 2016 · 1:29 p.m.
Q&A - Managing your online presence on Google Search
John Mueller, Google / Zürich, Switzerland
27 Nov. 2016 · 2:02 p.m.
Design for Conversation
Henrik Vendelbo, The Digital Gap / Zurich, Switzerland
27 Nov. 2016 · 2:30 p.m.
Q&A - Design for Conversation
Henrik Vendelbo, The Digital Gap / Zurich, Switzerland
27 Nov. 2016 · 3:09 p.m.
Firebase with Angular 2 - the perfect match
Christoffer Noring, OVO Energy / London, England
27 Nov. 2016 · 4:05 p.m.
Q&A - Firebase with Angular 2 - the perfect match
Christoffer Noring, OVO Energy / London, England
27 Nov. 2016 · 4:33 p.m.
Wanna more fire? - Let's try polymerfire!
Sofiya Huts, JustAnswer / Lviv, Ukraine
27 Nov. 2016 · 5 p.m.
Q&A - Wanna more fire? - Let's try polymerfire!
Sofiya Huts, JustAnswer / Lviv, Ukraine
27 Nov. 2016 · 5:38 p.m.
Closing Remarks
Panel
27 Nov. 2016 · 5:44 p.m.

Recommended talks

Torch 2
Soumith Chintala, Facebook
5 July 2016 · 11:21 a.m.