Learning about Generative Adversarial Networks on Udacity | 100 Days of Code 11

Key Takeaways

guten morgen ohayo gozaimasu oh good morning it's day 49 of the hundred days of code and yes I know I wear the same hoodie almost every day but that's because you know well if it's not getting dirty why do you need to wash it like I don't I don't try to use as many clothes as possible but okay I just passed project fork on the udacity deep loading course that I'm doing check it out meat specification so nothing special we've got good feedback and then a whole bunch of resources here on how I can learn more so I've got an incredible amount of reading to do what am i up to today well I'm doing week 9 all the classes for the machine learning course and Coursera tour by Andrew he's also started a new deep learning course well it's coming up soon deep learning day I hold link down in the description as well so you can check it out it's just a front page of a landing page at the moment that's what it's called but yesterday I was learning all that Python on treehouse almost finished the Python Python track on treehouse and so everything's coming to coming to an end so the courses I'm in this final the second last week of the machine learning course I've got about three weeks left of the Udacity deep learning nanodegree foundations almost too much the Python tracks so I've got to work out what I'm doing next I haven't got to exact route of where I'm going but I know it will be in the field of data science machine learning or deep learning more specifically towards communication something something in that realm but I'll hit you up once I learn about it I've it's 49 days into the days I've got 51 days left to the hundred days of code but it's obviously going to keep going after that anyway and you know the thing about filming on an iPhone is that when you get a phone call the thing cuts out so yeah 51 days later the hundred days of code still filming on the iPhone because my digital camera I haven't got a new lens for it at the moment trying to spend less money more than more money so I might try and find one Gumtree the tape or something like that but no excuses getting it done I'm going to learn about some machines and I'll catch you in a few clips a few seconds big day machine learning today I still haven't finished a programming assignment though the last thing I need to do but I went through all of these lectures here it takes me a while to go through them because I like to take an abundance of notes check out what I learned about today anomaly detection Gaussian distribution probability distribution Gaussian distributions otherwise just known as normal so like just a normal curve what else what's the normal age detection useful for all detection so like say for example you're an online bank and you have millions of ok transactions then all of a sudden you've got one that looks a bit weird or for me exactly right like if I was buying things in Brisbane for months on end and then all of a sudden I have a massive charge over in some other country like Tanzania or something like that I don't know somewhere in the other side of the world my bank might go oh that's probably fraud so we won't let that transaction go through or in manufacturing say you produce 100,000 iPhones like what I'm recording are millions in our / iPhones and all of a sudden one has some weird thing going on with it that's where you can use machine learning and sort of anomaly detection and of course how I just explained it doesn't feel overview but that's that's essentially the gist of it just a really small number in a large data set so only a small amount of positive are positive examples what else did I learn about so when to use anomaly detection versus supervised learning so supervised learning you have a large number of positive and negative examples both labeled whereas a normally small number of y equals one positive example see zero to twenty so really small amount what else do we learn about collaborative filtering algorithms which is similar to what like Netflix or a book recommending system would use if there's a lot of users they can take all the user input of ratings or movies and whatnot and create recommendations for other people so say for example you have a group of people who are interested in romance movies and they're uploading a whole bunch of movies the collaborative together might realize that hold on they're uploading these movies so these movies must be related to romance let's recommend them to other people who are interested in romance so that's pretty cool and yes that's about it collaborative filtering algorithm and was anomaly detection yes see I've done I've done four or so hours of this and I don't know it's gone up one in one ear and out the other that's why I like to take so many notes out to review these at the end of the course and go over it again I think I'll go through this course more than once but something really cool just got released on Coursera as well check this out I'm excited to this actually $65 a month for unlimited access of all the courses on there so when I plan my data science slash artificial intelligence machine learning master's degree over the next six or so months Coursera it may play a big part because $65 a month for unlimited education like that's that's cheap like my university degree I still owe like thirty five thousand dollars or something like that I don't even know I didn't even know how to check it to be honest but yes sixty-five dollars a month for all this access to learning highly recommend so I'm done for learning today I'm going to go edit a video I should really be uploading I'm going to upload on Fridays podcast and a V log so that's what I've worked out it's best to me just fit in with my learning schedule and then writing as much as I can on the hundred days of code series be sure to check that out it's on medium and it's going to be in the description but I'm going to go play I'm going to have some fun my play my brother and chess or something so we'll catch you tomorrow stay 50 well it's good y'all day fifty of the hundred days of code series and it is about 9:30 at night but I've had an amazing day I was working on actually I was facing resistance this morning what does that mean well I just procrastinating right when you don't want to do something or where you do want to do something but you're sort of doing everything else instead of doing that one thing but eventually I got around to working on my messenger bot that I'm building which is kind of like a personal trainer slash nutrition coach in a messenger bot so I'll link that down here in the description it's called the move more messenger bot now I'm doing some reading just in bed is Ray Dalio 'he's a book by Ray Dalio who's the CEO and founder of Bridgewater which is the watan of the largest hedge funds it's called principles just a whole bunch of life lessons that is learned it's so valuable to learn from other people guides like reading has changed my life like why would you want to learn these lessons when you can learn them vicariously through other people and then for the rest of the day before I started reading before I went for a dog for dog walk before I went for a dog had dinner I was working on my website it should be live now it's use any gem calm also in the link in the description ideally if everything goes to plan maybe it will become the Airbnb for gems who knows will it work I don't know I'm going to keep working on it one every Friday for the rest of this year at least and see where it gets to but that's it for day 50 working on projects Friday I've reserved for projects watch this space first see what comes next but tomorrow machine learning assignment and then I don't know I think I'm heading out with my brothers but we'll see you then good morning y'all it's day 51 of the hundred days of code series and I just finished my eighth and think about that for a second I really need to get ready when I do this is actually the first of July we're almost halfway through winter which is exciting I'm still in my pajamas as you can see but I just finished first thing I got up Salem morning I go up and I finished my eighth machine loading assignment check it out submitted 9:14 a.m. this is going to be the majority of my coding done there's two weeks left news machine learning quartz and then I'm not sure what I'm going to do after I'll figure it out though I'm going to do a I don't know syllabus for myself in terms of learning data science and and machine learning and AI and whatnot over the next six months or so but after you in it so what opportunity rest of the day I even do my newsletter so check out my website listed evoke calm if you want to get that and then a workout I got a little bit github quit for v-log I have to write all these little reminders to make sure when I get everything done they keep it visual on my whiteboard but that the majority of coding done today will catch tomorrow so day 54 of the hundred days of code series and I've been learning about where is it go of here ganz generative adversarial networks so what's the whole principle behind gangs well essentially you've got a generator network and a discriminator network so you've got two neural networks that work against each other to work out some sort of input/output so take an input some sort of real data we'll go in and a sample bunch of data will go in and then the generators Network its goal is to fool the discriminator Network by generating fake data and then the discriminating network has to decide which is a real which is the fake data and look here so this is the exercise I did as we started off with some MMS data set I keep forgetting what they call and then so that imports a whole bunch of numbers handwritten digits we go down here and so train two networks to work against each other and this is what it produced it produced it out of nowhere so when you've got these numbers you can sort of see a one here a nine here a nine there and we go down and this is what I came up with at the end some some scrambled it it starts with with nothing than the one one seven seven one it's pretty good by the end and here's the final output nine eight so what's the idea well the generator tries to produce fake numbers and then the discriminator looks at the original data set and goes hey are these fake or are they real and it tries to match them with the probability distribution and of course my explanation is not the best of it but an analogy I like to think of is imagine the police and some criminals and so the criminals are making fake money but the police can keep finding out that they're making safe money so you can imagine the police has been the discriminative network and the criminals has been the generator network and so over time the generator gets better and better which is the criminal at making fake banknotes and the police get better and better at detecting the fake Bateman banknotes and then eventually the the criminals have no choice but to make fake banknotes that are virtually the exact same as real banknotes so that the police can't differentiate from it and that's the whole idea with ganz is that they the generator get become so good at generating new data that the discriminator can't tell what's real or fake and then it produces this new data completely on its own and there's a lot more to learn about games but that's what I've learned so far I've gone through the Ganz class on Udacity all of today and I'll probably go through the videos again a couple more times just to get my head around the concept cuz it's so new but concept like I'm at this is this is really powerful stuff this is like one of the newest things and deep learning it's only came about in 2014 so imagine like a generative network and by generative it means bringing this stuff out of out of nowhere training on so much data imagine it like you can apply it to anything like imagine you could go hey Theory get me a give me a sorry getting interrupted but yeah imagine if you could just ask theory to generate you a video of 2pac teaching your calculus and all of a sudden it goes to the internet finds videos a two-pack finds videos of like Khan Academy or I don't know then teaching calculus and combines them together all of a sudden you've got you've got to pack on your screen here teaching your calculus so that would be amazing and of course that's a few years down the track but they're already if you watch the Rodgers video link it in the description he's generating completely new video clips out of using Gans there's videos of people turning horses into zebras yeah this is is crazy stuff but for the rest of this evening I'm going to do some riding I didn't do any filming yesterday or the day before yesterday I was learning all about github still trying to get my head around using git and github and whatnot get my projects that I'm working on on to my gift github portfolio there's nothing on there at the moment except a few basic things but I'll work it out eventually and then Sunday of course I spent writing you can you can check out what I did actually it's on my Korra profile I'll link that in the description as well but we'll catch it tomorrow it's day 55 tomorrow