GENERATING TV SCRIPTS WITH DEEP LEARNING | 100 Days of Code 7

GENERATING TV SCRIPTS WITH DEEP LEARNING | 100 Days of Code 7

I completed an interesting project recently, generating a TV script of a scene at Moe’s Tavern from the Simpsons completely from scratch.

It’s still early days but I can see techniques like this being used to write books and create box office hits in the future.

Medium link mentioned in the show:

Thank you for watching!

Say Hi to me anywhere:

Web:
Writing:
Instagram:
Facebook:
Twitter:

#code #deeplearning #udacity

well it's good job day 26 is 100 days ago I didn't film yesterday because I was so wrecked from the boot camp like that the two days and three days and whatever I haven't coded for three days so I guess you could say it's not not really a hundred days of code but that's alright I'm going to get back into it today my goal for today is to finish my deep learning assignment it's qu today 6th of June 2017 Ed's um the 8th so I'm trying to submit it today and then see where I go from there but that's my main goal for today I'm going to edit some videos while watching the Apple Keynote that just dropped and then I'll get into doing my assignment and I can show up with with my favorite things from me from the Apple Keynote it's the WWC conference 2017 so see you soon so if y'all concurred and our own ends all day trying to finish up this Udacity deep learning project by this evening but I haven't had a break yet or a proper break had some food Eve I'm going to go work out clear my head and then come home and try to submit it tonight I've only got a little bit to done I'm probably probably about 7080 percent of the way through I gotta improve the training of my neural network so it's it's not our it fits the data better right now my training loss is about to after 100 or so epochs like iterations I want to get it to blow one so we'll see how we go all I'll hit you up one side and once i've reached that point and when i'm about to submit it hopefully is tonight if not it'll be first thing tomorrow so catch you soon day 27 good morning so I've been training my neural network here as you can see it's going down getting some batches going using AWS because my computer is nowhere near powerful enough to do this and I'm looking to generate a new TV script of The Simpsons of a scene that most happen based off the previous twenty seven seasons of The Simpsons and so I've got some change logs here so I'm recording how I'm changing my parameters how I'm changing my build RNN functions and whatnot and here was the first output so you can see most is like what's the matter home and letting that yah-yah-yah and so now I'm just trying to refine it I should be done within the next hour or so and submit it and then it's all done yesterday afternoon I know I was supposed to finish it but I went worked out I was a bit tired after that when spoke with my friend so now this morning first thing jump straight into it I'm going to submit this and then do machine learning assignment later probably after an out though because this is pretty as well as computationally intensive it's brain intensive but we'll see you soon the moment of truth here we're hitting it oh yeah project three Udacity deep learning nanodegree foundations found a steep learning combinations nanodegree submitted if everything's all good I'm officially past the halfway mark of the course so I'm very excited this is from not knowing anything about code well any Python code about two months ago so I'm happy I'm going to take a break now I'm going to get something to eat and then get back into machine learning I've got an assignment that was doodled some day I didn't get it because I got a boot camp but that's alright I'm going to get into that this week and then fix up the rest of the course lots of learning to come lots of learning to go I'll catch it soon hopefully I can finish the machine learning assignment today – we've got their two assignments done in one day so far program assignment physically the hardest one yet on Coursera normal Network learning check it out in MATLAB oh there you got here I don't like MATLAB probably cuz I'm not good look and a lot of help from the forums check this out got all these tabs open whatnot but that's week five done I'm still three days at least behind in the machine learning course I've got a whole bunch of classes to do it's up to week six now the machine learning course and I think it's week eleven or twelve in the deep learning course but that is two major pieces of work out for the day you know it's administered a maybe just going over some Python or getting started on the next series of classes rather than doing assessment but start for another break Tony get something to eat or actually this is my coding music at the moment time by hans zimmer i just have that on repeat you can't see that I will literally just have that playing on repeat I would have played it at least 50 times this morning however long that is fifty times four minutes so I can't do math at the moment 20 minutes 200 minutes yeah few hours four or five four or four or so hours but time for brains to check it out great job and congrats on finishing project three I don't really have any improvements for you hello world it's the 28th of June 2017 aka day 28 Oh No so at the 8th of June 2017 ok day 28 of the hundred days of code and Here I am learning some sequence to sequence models through my Udacity deep learning foundations nanodegree so what a sequence the sequence models well I can't explain them to you yet because I've just done learning about them but essentially with a imagining translator Google Translate you feed it a sequence of words in English and then it gives you a sequence of words back in another language or any language into any other language so Google's sequence Google's translator is based off sequence to sequence models or a chatbot say your example tapping in something to ask a chatbot the reply would come back in a sequence and now a lot of chatbots like mine that I built the personal trainer chat bot are built off rules so it understands what you type in and respond a certain bit of text or block based on what you typed in because there's a rule but what's really hard to do is train a chat bot on a whole bunch of data and then have you type in something to the chat bot like ask it how are you and then the chatbot creates its own reply rather than from a base of rules and that may not be the best example but just understand that rule based is easiest to do and general a a is hardest to do most like in real life like a I sort of is very good like for example that I'll forego that the best go playing robot in the world it's really good at go but if you told it to write a bike it wouldn't be able to do it so we're a far way off general AI but it's a really specific task robots are getting very good if a human can do it in about one second chances are a machine can do it as well so more learning that's my one goal for today it's finish off this little module in deep learning I'm doing 600 hours and deep learning today and then some writing and then I'll I'll get you up what are up to you later this afternoon hello world state 29 100 days of code series and today I'm going to be learning about pipe hem and machine learning so got python learn Python the hard way book ready to go ed it up and machine loading classes I'll get to later last night I actually went to my first brisbane AI meetup so venues are trying to use meetup a lot more lately because what I'm learning is sort of new even though it's been done for 30 plus years or something like that or longer ever since the dawn of computing but the way like that people think about it may old is different to how they thought about in the past so going to the meat of the resume I mean it was really good to to find some people who are and they with the similar mindset to what I am and that's really important thing if you wanted to do anything well surround yourself with the right people like lives anything anything in general because your average of the five people you spend the most time with so getting around the right people is fundamentally important in other news I just posted a post on medium how many more times so what's it mean I'll let you ready to find out but essentially the average person if you're watching this you'll have 30,000 days of your life right from birth to finish 30,000 days give or take a few thousand so if you think about it like that how do you spend each day to the best of your ability don't waste your time here you're going to get one life and I know that Matt might sound sad for some but to me is extremely motivating so check it out I'll put the link in the description medium.com slash @ mr mr deburr vo you okay but for now I'm going to get back into code I'll catch you later this afternoon one of what I've done some study what's up y'all I'm about to go to bed not much filming today but I did do a fair bit of study I know with some friends this afternoon it is my brother's birthday as well so I didn't really want to film too much I want to spend time with the family he's 19 I can't believe it wait my second – second youngest brother at the counter / they had three brothers so it's not hard the middle brother but whole bunch and machine learning study I learned how to adjust machine learning algorithms if they're not training correctly if they're overfitting if they're under fitting changing the parameters changing the data sense things like that tomorrow I'm going to hike a mountain so that's going to be really cool maybe do some code in the evening but that's a wrap on day 29 100 days of code we'll catch you tomorrow day 30 will be officially one month in two days of code and I'm learning a whole bunch it's good to get back into a role study and get back on top of things rather than saying yes to too many things but see you tomorrow so check this out it isn't all sunshine and rainbows when you doing quizzes I got 2 out of 5 on my first attempt at this machine learning quiz using a whole bunch of notes and a whole lot more notes so maybe I didn't understand this modular as well or maybe unknown it's a bit harder than last one but it's weird how it works out right you think you understand something but you get the results back and you don't really understand it so that's alright I'm going to go back to the drawing board and yeah okay I've got two more attempts in this eight hour period and see if we can get 5 out of 5 because that's my goal to get 5 out of 5 but just to show you that I don't always get it right the first time as you see and let the last quiz I did I've got 5 out of 5 in the first try not this time but we'll keep trying we'll see where we end up and Allah I'll hit you up with if I get within the next eight hours or I might just have to try again tomorrow 3 made it 5 out of 5 100% so model of the story if you fellas first-time try again and if you don't get the result you want the second time try again third time lucky so I'm going to keep doing more study here and then hope they'll get this programming assignment finished by this evening and yeah that'll be my coding done for the day and I'll probably upload this video later tonight so this is probably the last day 31 will be the last day that I record in this video that'll be the end of v-log 7 never leave

Tags:

Leave a Reply

Your email address will not be published. Required fields are marked *