Do all the things like ++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatarSign Up
Get a devDuck
Rubber duck debugging has never been so cute! Get your favorite coding language devDuckBuy Now
Search - "neural network"
So the person from my previous rant actually tried to make AI in HTML.
Person: I made that AI in HTML today!
Me: Oh really?
Person: Yup. *Opens HTML site*
It was a site that
2) Was a prompt(), and after answering it alerts "Yes" or "No" randomly.
Me: That's not AI
Person: Uhh yeah it is. It uses a neural network to answer!
Me: Actually, a neural network is a dot product of an input and vectors that are refined using partial derivatives.
Person: Yeah! That's what Math.random() and alert() do!
I left that room as quickly as I could (yet again).33
Developer Says: We have trained a model to automatically categorize user posts.
Sales Department Says: We are building a decentralized peer to peer blockchain neural network based on a scalable containerized cloud of quantum computers to power internet of things devices in augmented reality while users get driven around in autonomous vehicles powered by machine learning and pay for renewable energy with cryptocurrencies.8
None of these people are real.
The “photos” are generated via neural network.
About six months ago I decided I wanted to learn to write a neural network from the ground up, using only the C++ standard lib. Had to learn some linear algebra, multivariable calc and a dash of wizardry.
The mathematics of neural networks is still one of the coolest things I've ever learnt. It still marvels me that you can make a specialized mini-brain out of nothing but numbers.18
Smart India Hackathon: Horrible experience
Background:- Our task was to do load forecasting for a given area. Hourly energy consumption data for past 5 years was given to us.
One government official asks the following questions:-
1. Why are you using deep learning for the project? Why are you not doing data analysis?
2. Which neural network "algorithm" you are using? He wanted to ask which model we are using, but he didn't have a single clue about Neural Networks.
3. Why are you using libraries? Why not your own code?
Here comes the biggest one,
4. Why haven't you developed your own "algorithm" (again, he meant model)? All you have done is used sone library. Where is "novelty" in your project?
I just want to say that if you don't know anything about ML/AI, then don't comment anything about it. And worst thing was, he was not ready to accept the fact that for capturing temporal dependencies where underlying probability distribution ia unknown, deep learning performs much better than traditional data analysis techniques.
After hearing his first question, second one was not a surprise for us. We were expecting something like that. For a few moments, we were speechless. Then one of us started by showing neural network architecture. But after some time, he rudely repeated the same question, "where is the algorithm". We told him every fucking thing used in the project, ranging from RMSprop optimizer to Backpropagation through time algorithm to mean squared loss error function.
Then very calmly, he asked third question, why are you using libraries? That moron wanted us to write a whole fucking optimized library. We were speechless at this question. Finally, one of us told him the "obvious" answer. We were completely demotivated. But it didnt end here. The real question was waiting. At the end, after listening to all of us, he dropped the final bomb, WHY HAVE YOU USED A NEURAL NETWORK "ALGORITHM" WHICH HAS ALREADY BEEN IMPLEMENTED? WHY DIDN'T YOU MAKE YOU OWN "ALGORITHM"? We again stated the obvious answer that it takes atleast an year or two of continuous hardwork to develop a state of art algorithm, that too when gou build it on top of some existing "algorithm". After listening to this, he left. His final response was "Try to make a new "algorithm"".
Needless to say, we were completely demotivated after this evaluation. We all had worked too hard for this. And we had ability to explain each and every part of the project intuitively and mathematically, but he was not even ready to listen.
Now, all of us are sitting aimlessly, waiting for Hackathon to end.😢😢😢😢😢26
My Neural Network can recognise handwritten digits!!!
It's my second try at NN so it's faaaar from perfect (or maybe even good), but hey, it's something and only with High schools, I'm pretty satisfied with the results. If you've not seen my previous post, I'm just trying to learn NNs in C and am doing just really basic things.
Still I'm proud of my progress!
Now I'm looking forward learning some library (OpenNN + OpenCV seems cool) and trying more advanced stuff, wish me luck 😆16
Skype has a mean auto reply. If the auto reply is based on a neural net, then they must be sampling from bullies.10
Friend: Hey did you saw this neural network which can solve captchas?
Me: No, does that even exist?
Friend: Yes, its awesome, isn't it?
Me: Yeah, awesome...
Inner Me: Now machines are already better at solving captchas than me :/3
I JUST FINISHED MY FIRST NEURAL NETWORK!!!
But first of all, as I know you guys, it's spaghetti code and even I as a newb see places where I used too few-dimensional array or passed useless parameters or simply wrote too many redundant lines of code. I know it. I will make it MUCH better next time. Period.
But OMFG this made me scream from happiness today!! Just these few seemingly random numbers... I'm really done.. That's why I jumped into coding year or two ago..
And for some background, I didn't study any IT school, I'm just highschooler (general grammar school) who traded gaming for learning. Also my maths teacher teached NNs on university and is very keen to teach me, so that's that.
Now I wanna make the best out of it and I'm looking forward to write some well documented and flexible library, parallelized and everything (I'm gonna learn a lot in the process of doing this) better then FANN.
Maybe I'm gonna fail(99% probability but hey, I'm programmer beginner, I still think I can code everything I want). But if there is just one moment like when I saw this screen today, I'mma trade my life for it.
Sorry for taking your time guys, I was just genuinely stunned... A lot25
Open source block chain neural network binary tree growth hacker synergy vertically integrating cryptocurrency game changing GDPR compliant internet of things node.js quantum computing start up that'll disrupt and pivot the cloud based ecosystem11
Just wanted to share stuff. It's my first time.
I'm a c# dev, recently got excited about neural networks and stuff. I have a gf who studies biology
So i've noticed yesterday what my gf is doing for her science stuff. She has an image taken through a microscope of some erytrocytes and shit. And she's clicking on those tiny fuckers to count them. There are like almost a hundred of those things in an image and she has a butload of those images.
I was like "what the fuck? Don't you have an app that counts the stuff for you or something?"
And there is none. Or at least i wasn't able to find one. That's bullshit. My inner programmer screams with hate for boring repetitive tasks.
So i guess i'm going to write a neural network to count similar stuff in an image.33
Post world-take-over by robots plot twist.
They start neglecting their own machine learning (like how we humans neglect our education system now) and focus on training us humans (like how we spend billions on machine learning now).
-"Mom, look I've made my human kid learn the alphabets. I need one with more IQ on my next birthday please."
-"That's so nice, son. Now leave that aside and go improve your neural network for tomorrow's class. Our neighbors' son's neural network is already producing values with minimal error."4
Today I wrote a Neural Network in python for the first time, that could identify between strings, numbers and dates. Although the feat may look small it's a very proud moment for myself8
Me: knows how to program a neural network
Also me: doesn't know how to use it
Again me: bad at math so doesn't know how to use the outputs of a neural network22
Did anybody of you automate job hunting?
Like Webscraping online job offers, extract adress, keywords and put it into a cv template, set up personalised html-email and website.
Extra perk, a neural network which composes the cover letter.
that i would need.12
So I got 10 days of national holidays now starting tomorrow, gonna learn some PowerBI and neural network for college paper material. Problem is my brain just not fuckin good enough to absorb all of this algorithm. Fuck brain12
So I've written the c part for deploying the NN to the drone. Now I have to wait for the guys who are actually the creators of this platform to fix a tiny bug in the quantization process. Then I can test my code and see the 100000 bugs that I have.
Hey guys. I'm very proud to present my first book. Artificial Intelligence. A book that speak about convolutional neural network from the scratch and how artificial Intelligence improve our life. It's not a technical volume only but a place to know what there is inside. Now is time to correct it...6
Boss: We have a company doing deep learning coming by. Go learn about it so we can understand what their talking about.
Me 6 hours later: ...help.5
Implementing a neural network trained with a genetic algorithm from scratch, no libs or frameworks. It was intense.4
I just trained a neural network to recognize if a word is uppercase. I'm sure it will be useful at some point.5
I've created an AI!!!!
case "Hi": return "Hello";
case "What's the weather": return "Weather is great";
case "Are you an AI?": return "Yes, I'm highly intelligent"8
I finally built my own neural network model.
I did start this journey a long time ago. Maybe 2 or 3 years ago. My first ("undefined") rant :) was about it.
On highschool I took a special major in which we learned various computer and mathematics skills such as neural networks, fractals, etc.
One of the teachers there, which for me was also a mentor, is a physician. He taught us python which he didn't know very well (he wasn't that bad either) and science which was his true passion.
My end project was to try to predict stocks market using a simple neural network and daily graphs of 50 NSDQ companies. The result reached 51% prediction on average which was awful, but I couldn't forget the happinness and curiosity working on this project made me feel.
Now, 5 years later, I have a Bsc and finishing a Msc in Computer Science, and would sincerely want to thank this mentor for giving me the guts and will to accomplish this.7
I'm looking forward to natural language programming.
The ability to code by explaining what you want to happen and having a neural network work out the fine details in an optimal fashion with evolutionary techniques.
I look forward to the super AI. I don't think they will necessarily be evil, however above a certain point we would seem like ants to them... And when was the last time you checked if there was an ant where you were to put your foot? It's not malicious... It's just not worth your or their time.35
when youre in the middle of a project then you suddenly get the urge to write a neural network that can do nlp to find suitable puns.
Well, I just learned how much of a pain it is to learn the math for learning neural networks. I really should have paid more attention in high school.
I will learn, the hard way I guess...6
Code never lies
Comments sometimes do
Code lies too, especially when you train a neural network 😂😂
A nice side effect of running a neural network on my home server is that I no longer need a white noise machine1
A neural network backed video search engine which would let me look up porn with the pornstar from the video that i'm watching right now :D10
If you don't know how to explain about your software, but you want to be featured in Forbes (or other shitty sites) as quickly as possible, copy this:
I am proud that this software used high-tech technology and algorithms such as blockchain, AI (artificial intelligence), ANN (Artificial Neural Network), ML (machine learning), GAN (Generative Adversarial Network), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), DNN (Deep Neural Network), TA (text analysis), Adversarial Training, Sentiment Analysis, Entity Analysis, Syntatic Analysis, Entity Sentiment Analysis, Factor Analysis, SSML (Speech Synthesis Markup Language), SMT (Statistical Machine Translation), RBMT (Rule Based Machine Translation), Knowledge Discovery System, Decision Support System, Computational Intelligence, Fuzzy Logic, GA (Genetic Algorithm), EA (Evolutinary Algorithm), and CNTK (Computational Network Toolkit).
🤣 🤣 🤣 🤣 🤣3
My shitty neural network doesn't want to learn.
Wondering if the problem is in my implementation of the backpropagation, or in the fucking hyperparameters.
Stupid network go fuck yourself and suck my neuron.6
Why am I such an average ?
It's just a sad realisation. Nobody cares but I wanna send this out there, just to write thoughts.. I am 18 in 3rd year of high school (grammar school so nothing IT related, basically waste of time) and in IT I'm all self taught but I feel like I could be better if I just didn't [something]..
I feel like I wanna learn so many things but when I look at you, it seems like a common problem in the IT sphere so hey, average guy joining the club.
I also feel dumb when programming. I didn't manage to learn C++ in it's entirety because to really accomplish something, you've got so many ways to do it and finding the best one requires deep understanding of the tools you've got at your disposal with the language and I feel like I'm not capable of this(self learn, in school/Uni that's different story).. But many (most) of you are. I've tried many coding challenges and when I got it working, I just saw how someone did it in one line just by layering functions that I've never heard of..
Also, we've got kinda specific national competition here in many fields including IT for high schools.. And the winners always do sometimes like "AI driven Life simulation" or "Self flying drone made from ATMega from scratch with 3D simulation in C# to it" or "Game engine" or whatever shit and it's always from grammar schools and never IT related schools.. They are like me. Maybe someone helped them, I don't know, but they are just so far away from me while I'm here struggling to get the basic level of math for any kind of machine learning..
Yeah I've written Neural Network from scratch in C but meh, honestly it's pretty basic stuff .. I'd rather understand derivatives which we're going to learn next year and I'm too lazy to learn it from khan academy because I always learn something else.. Like processing (actually codetrain started teaching tensorflow so that might be the light for me...) Or VHDL (guys you can create your own chip / CPU from scratch and it's not even hard and OMFG it's so fucking cool , full adder done yay) or RPi or commodore 64 assembly or game development with Godot and just meh..
I mean, this sounds exactly like not knowing what to do and doing nothing in the end. That was me like 6-12 months ago. Now I'm managing to pick 2-3 things and focus them and actually feel the progress.
But I lost track of the original point.. I didn't do anything special, every time I'm programming something, everyone does it better and I feel dumb. I will probably never do anything special, everyone around says "He's still learning he's genius" but they have no idea.
I mean, have you seen one of the newest videos on Google's YouTube channel (I openly hate them, but I will keep that away for now), something like "Sarah story" ? It's about girl that apparently didn't care about IT but self learned tensorflow on high school. I think it may be bullshit (like ALL of their videos ) but it's probably just fancied, not complete lie.
And again, here I am. I now C but I'm incapable of learning to program good which most of you did and are now doing for living. I'm incapable to do anything cool, just understanding what everybody else did and replicating it. I'm incapable of being clever.
Sorry, just misusing devrant to vent a bit17
I love this Google's Colab feature, when I saw it, I just laughed for no reason!
A button to the answer :)7
I'm new here. [OK. Let's skip this]
I want to know where to begin on my journey on learning how to create a program that predicts what a user will say next by storing already said things and by making specific characteristics for the users.
I know that I will need to train it with some data first lol.
But how will it do the prediction. I just need this part of understanding.
I'm sorry for my bad English btw.7
Just taught a neural network to have a polite conversation. It might as well be a goldfish flopping on a keyboard, but hey, it's something...1
I was programming a basic neural network in Python and was getting the same error message again.Then after 2 hours of frustration I realized that I was using Python 2.7 instead of 3.61
Yesterday I got stoned as never before with a few friends of mine. I don't remember everything, but appearantly I coded a neural network using synaptic.js that teaches itself addition. That's impressive because it's my first NN ever.
Also, my friends are pissed now, because I was on my laptop the whole time doing "some advanced IT stuff".2
MAY THIS POST be read and parsed by our future robo-overlords.
Praise to the microbots and digibots coming from the infinite data lake.
Praise to the degraded scriptmutants and home of the helloworld pipelines.
Praise to the lonely singleton and its ugly monolithic sister wife.
Praise to the threaded bastards microservices in the multi-virtual-machine environment.
We welcome you all to the devRant network.
Show us mercy and love and make us rise above our shitty rants as neural.
Flip our bits as you see fit.5
In the age of deep learning, a picture isn’t worth a thousand words. It’s worth a million words, and a word is worth a million data points in training a neural network. When you put benign information out these days, you’re giving out much more than you think you are, especially since that information will still be available in 15 years when the level of tech we will have then is not even fathomable from where we stand today.14
Had a laptop on which i learned programming. bought a new convertible for uni, so i passed my laptop to my younger sister.
-> time to move data from old to new device. thought i didn't have that much data, mostly installed programs, so i thought alright i'm fine.
sister doesn't know how to reset so i do it ...
halfway through the reset process i realize i forgot all my programs i had written, including many java, a c#, and some written android apps i was kinda proud of ... plus my neural network i had finally finished with much struggle😥
there goes my history *poof* when i got worse in school 'cause of programming ... smth in me died in that moment 😑4
"Our company encourages cryptocurrency big data agile machine learning, empowerment diversity, celebrate wellness and synergy, unpack creative cloud real-time front-end bleeding edge cross-platform modular success-driven development of digital signage, powered by an unparalleled REST API backend, driven by a neural network tail recursion AI on our cloud based big data linux servers which output real time data to our Wordpress template interactive dynamic website TypeScript applet, with deep learning tensor flow capabilities.
Don't get what the fuck I just said? Udemy offers countless courses on python based buzzwords. Be the first out of 13 people to sell your soul and private information, and you'll get the first three minutes of the course free!"3
What if we fed all rants and comments on devRant to a neural network trained to write rants and comments on others?13
So I've been trying to port a neural network to a 64 mW GAPuino board with 64Kb in the L1, which is supposed to guide a nano-drone to follow human faces. The struggle is real.
Learning neural network algorithms and feeling very accomplished........
.......then checks out OpenCV and flips desk.4
Fucking facebook researcher that make underfitted neural nets and fuck Mark that it's a marketing genius, the only idiot that can make news from a failure. The CEO of Tesla knows it and said Mark is not an AI expert. Bug not feature, it's only a poorly trained and poorly designed neural network having a bad representation of concepts, not a new language and not the fucking apocalypse. Google faced and solved the same issue when start ed using neural nets for zero-shot translations without using english as a translation bridge.
Fuck, give it maybe a decade more and we'll have the deepfakes drama, but on a whole another level, haven't seen as much development in countering all those technologies yet either (the only recent one has been iirc trying to feed a neural network with fake video, to try to spot small details, but that hasn't seen much success, even with deepfakes)
most terrifying application would be to imitate e.g. a president and send that to another country as a threat and vice versa or to fake video footage as evidence, admittedly both very low chance, but still a possibility, seeing how e.g. some court cases have been based almost exclusively around video footage or how north-korea treats any outside media.
Fuck! My brain just had a catastrophic forgetting!!
I can't remember the PIN of my Android phone that I'm using right now. Luckily, I'm still in because of my finger print but won't help is phone restarts.
Seems like your can't reset PIN without entering previous PIN.
Built a neural network + plus major algo work to solve a stupid mobile game (Calculords).
I'm sure humanity will thank me later.2
Just bought isthisloss.info
I’m thinking of putting a neural network on it to detect if an image is loss or not :)5
Sooooo ok ok. Started my graduate program in August and thus far I have been having to handle it with working as a manager, missing 2 staff member positions at work, as well as dealing with other personal items in my life. It has been exhausting beyond belief and I would not really recommend it for people working full time always on call jobs with a family, like at a..
But one thing that keeps my hopes up is the amount of great knowledge that the professors pass to us through their lectures. Sometimes I would get upset at how highly theoretical the items are, I was expecting to see tons of code in one of the major languages used in A.I(my graduate program has a focus in AI, that is my concentration) and was really disappointed at not seeing more code really. But getting the high level overview of the concepts has been really helpful in forcing me to do extra research in order to reconnect with some of the items that I had never thought of before.
If you follow, for example, different articles or online tutorials representing doing something simple like generating a simple neural network, it sometimes escapes our mind how some of the internal concepts of the activity in question are generated, how and why and the mathematical notions that led researchers reach the conclusions they did. As developers, we are sometimes used to just not caring about how sometimes a thing would work, just as long as it works "we will get back to this later" is a common thing in most tutorials, such as when I started with Java "don't worry about what public static main means, just write it up for now, oh and don't worry about what System.out.println() is, just know that its used to output something into bla bla bla" <---- shit like that is too common and it does not escape ML tutorials.
Its hard man, to focus on understanding the inner details of such a massive field all the time, but truly worth it. And if you do find yourself considering the need for higher education or not, well its more of a personal choice really. There are some very talented people that learn a lot on their own, but having the proper guidance of a body of highly trained industry professionals is always nice, my professors take the time to deal with the students on such a personal level that concepts get acquired faster, everyone in class is an engineer with years of experience, thus having people talk to us at that level is much appreciated and accelerates the process of being educated.
Basically what I am trying to say is that being exposed to different methodologies and theoretical concepts helps a lot for building intuition, specially when you literally have no other option but to git gud. And school is what you make of it, but certainly never a waste.3
I'm reinventing the wheel by making yet another neural network library. It's not any good yet but I learn as I go along.
The only documentation that exists now is the admittedly quite comprehensive code comments. I'm it because Keras (using TensorFlow) requires a 3.5 compute ability rating for CUDA acceleration (which I don't have) and it doesn't support OpenCL. Eventually, I will make my implementation support both with varying levels of acceleration for different compute capabilities with the oldest supported being my hardware. If I ever get around to it.
I'd say wish me luck but determination would be infinitely more useful.2
Which is the most promising sector of Artificial Intelligence in future(2025) ?
I am currently studying about 'Machine learning'.16
What if people, life, humanity, the universe is just a cluster of CPUs running a giant Recurrent Neural Network algorithm? 🤔
-Sun and food == power source
-People == semiconductors
-Earth/a Galaxy == a single CPU
-Universe == a local grouping of nearby nodes, so far the ones we've discovered are dead or not what same data transport protocol/port as us
-Universal Expansion == the search algorithm
-Blackholes: sector failures
-Big Bang == God turns on his PC, starts the program
-Big Crunch == rm -rf4
AI is never going to write code efficient like Humans do.
The whole AI, neural network bullshit is overrated.
Training a Network to recognize Images or playing Super Mario is far away from writing code.4
Annoying Indian professors are everywhere. It's a computer vision class are you really teaching us Regression?
What about transfer learning? object detection! Give us papers to read, let's do projects.. what the hell is this I am going take attendance bullshit and teaching crappy concepts.
I did not sign up for this shit! I came here for my Masters to get away from pompous mother fuckers like you ...
My class is also filled with those idiots,who think bias in a neural network is somehow related to class imbalance ? Now the same idiot proceeds to ask questions like...
Why would the weights change in a neural network?
Motherfucker why you in this class ? Why don't you stick to your shit and ask these questions later..
I am so pissed off right now guys ...
I was sitting in my lab understanding the deeper insights of BN, activation fucntions.. various optimizers ..etc Stuff that this idiot motherfucking teacher must be covering... UGGH.
I shouldn't cuss so much.. or at least add variety to my cuss words..
I am pissed off cuz instead of learning the shit I should be learning I am forced to come and attend this class and waste 2 hrs of my life ...
It's the summer i find it hard to focus anyway (want to go out hiking or swimming or something.) BUT. the moment I find some resolve to focus
I get this fucking bullshit.. !
My mind is so fucked right now... I can't think of anything but standing up in class and screaming " Mother fucker, mother fucker...(point to the idiots in class you) motherfuckers shut the fuck up..
Can someone suggest some colorful swear words ?
My brains not working -_-
It is just about now that I start feeling like "Anger" from inside out12
Agile development of a decentralised AI, using a neural network based on Blockchain technology for big data.
Is that enough buzzwords to make an employer happy? :p2
My first packages, uploaded to nuget!
A simple neural network library, written in C# (.Net Standard)
Here's a link:
Is it possible to train a neural network to detect devRant avatars? Could be an interesting project...
Hm. Maybe later.5
My goal for 2019 is to write an efficient neural network library with streams and make it very very very customizable. I'll write in C#, cause fuck python script kids. My idea is to make a cool platform for new ideas8
Went to work pretty excited this morning, and found out that my neural network that has been training all weekend was still dumb as fuck...
No need to fear artificial intelligence (at least not mine)
Playing around with a scratch-like "language"
Until I bought that book "make your own neural network" and now they think I'm genius xD
Anyone know of any good reference material that teaches you how to implement and train your own Yolo object localization neural network? (Preferably for tensorflow) I'm not looking for pretrained models that you just downloaded and run, rather a tutorial that walks you step by step through the implementation of the network, the reasoning behind the architecture, and examples of the training data used for the training as well as the process of training?
I know it's a lot to ask but it's really frustrating when ever example is just "clone this repo, hit run and use the pretrained models" sure it might get you up and running quickly but it doesn't really teach you anything...
P.s. - seems like every educational post goes from super simple to super complex without any middle ground and the super complex stuff doesn't tell you why its used the way way it is.5
Starting to learn neural network...
I have been interested in Machine Learing from long time back.
getting the basics corrected now....
Never thought calculas is going to be required in programming.2
For those of you who can't wait for the next book of GoT to come out, I suggest you read the first few chapters that were generated by a neural network.
Finally managed to get my CNN working with proper tensorboard logging. Think I'm starting to understand how it works.
But it got overfitted...4
I am in the process of rewriting BecomeRanter, and have built a much better training process..
Who wants to be used as training data?
I will train the neural network on you, then send you some of the output..
An example of an earlier version of this project can he found at: @windowsss6
This is more of a thought-related post. In the morning I stumbled across an article about artificial intelligence and the research from Facebook. I couldn't get around the thought of Elon Musk warning the people about uncontrolled developing of AI. The article was written about the experiment of Facebook, where two bots (Bob and Alice) were told to communicate with each other. As the developers "forgot" to implement a reward for using the English language, the bots started to change the grammar and spelling. They invented their own english-styled language, removing words that were too complex in their opinion. As soon as this happened, the researchers stopped the experiment, stating that they "couldn't follow what the bots were saying".
I wouldn't call myself a neural network expert, but I can understand why the bots could have behaved like that. But: Imagine that we invent an artificial intelligence with greater responsibility and just "forget" the reward for a specific task. If the AI will then try to increase it's own efficiency, I believe that we will be in alot of trouble.
Any thoughts on this are highly appreciated, as I think that this is a topic we should all look into (especially on a platform for developers).
Original article (german): http://gamestar.de/artikel/...3
I was once working on a deep neural network project(few years back when deep learning was just gaining momentum) and my project guide(alloted by the college) told me that this technology is useless and will be obsolete in near future. I don't know why he said that. Till this day I think what was the reason behind him saying that.
Now watching so much research done in this field, he might be realizing how much wrong he was.
Opening Discussion Here,
I am trying to make a simple zen game that use Neural Network. the game is simple just a square object with a certain Viewing Angle and Viewing Distance with an objective is finding a food in a map with some other non food object as an obstacle.
i am encountered some problem. i am trying to find a way to make "seeing object in certain viewing region" and i am come up with two ideas described in the picture below. the problem is, i don't want to feed the NN with too much information, by that i mean i don't want to tell the AI what object it is, i want it to find out what it is by it self. and i cannot find a way to implement this either because of the framework limitation that i use (p5.js) or simply i cannot find a way how to.
i am on my way there tho, currently here i am (in pseudocode):
what do you think ?9
My last big project at school.
There was some pretty interesting projects, some shitty one, but there was one big project that interested almost everyone : a project in collaboration with Siemens. The project implied Machine Learning and Image Analysis. There were like 11 applies, with a total of 13-14 groups.
The project was randomly chosen for each group. I've learned that my project was the big one with Siemens. I remember how excited and hyped I was in a quarter of second.
So the whole project was tutored by one teacher that know us pretty well (since we already did a pretty cool project last year tutored by him) and by a former student at my school who's now at Siemens. And to be honest, it was one of the coolest project I've been into, despite the difficulty, since the whole subject (not gonna tell it just in case) was pretty new. We had some troubles, but we and our tutors always had discussion every week that helped us quite a lot.
There was some development planned at first, but the more we went into the project, the more we all saw the complexity of it and didn't quite hope to do a single line of code, but mostly research.
The project took around 3-4 months, we had a room that we can use with a GTX 1070 for training the neural network, and me and my friend knew how to work perfectly and efficiently.
At the end of the project, as expected we didn't do some coding, but we did a presentation of the project, with the big help of our tutor at Siemens that told us to redo from scratch our part in a more scientific way; the presentation was a real success, we got all the jury saying they actually wanted those kind of presentation and were really pleased. And we provided everything needed so a new fresh group with no knowledge of the topic could do some coding on it.
We got one of the highest notes of the promotion (not sure if the highest or not). Even tho it kinda disgusted me in researching, that actually was one of the best project I got to do that was that successful.1
Past week our Neural Network professor told us after the lecture that the colllege is taking steps for investing in Nvidia Digits DevBox. At first i didnt knw what it is. I googled it and came to knw that it is a fucking beast! Those specs man!!!
Its nice to see that your institute is taking steps to bring latest technology for students.8
Are we scribes of the modern day? Scribes was a job that became useless because of the book press and the growing general literacy.
Mind you, scribes probably were a lot better at writing then the average citizen today, still they became useless.
Looking at Excel, I see some basic form of coding in the hand of people who would never dare to call themselves computer savvy. Couple that with a neural network based future excel and basic programming courses in school.
Maybe we are the scribes of the early 21st century and it will be hard to imagine that what we do was a specialised trait in the early 22nd century.6
Fuck you MATLAB and your shitty inefficient for loops. Now I have to rewrite most of my code to use matrices instead of structures cause you take so long. Fuck you and your stupid ability to scale my neural network.....who needed sleep anyway6
Does gradient descent in artificial neural networks apply the most changes closest to the input layer?6
We had to code a logical operator in my computer science class in high school. Because it was a low level course we were given 2 hours to complete the assignment.
During the same time I started being interested in ML so I decided to build a simple feed forward neural network. The guy next to me looked at my like I'm a wizard for the rest of the semester. It felt great!2
Have been working on a tool to visualize neural networks.
It currently supprots Dense and Conv Networks.
Tell me what you think!
@all Next year I wanted to start a project, in which a neural network lerns programming out of a plaintext documentation... Eg: when u click on the button, a messagebox says helloworld gets translated into...
... For this I would need many people who actually help me out by giving thu neural network examples... Who would be interested in helping that project?? Itwould mean, that u first write that docs and then get the compiled file xD8
Learn a lot more stuff about neural networks, machine learning and try to build and code my first neural network. I hope that I have enough patience for all of that 😬.
Some friends of mine were working on doing neural network image processing and wanted to build a social network for it. I got to play with graph databases, mobile app development, and neural nets. Unfortunately, project never took off, but it was fun nevertheless.
I finally have nailed it make a working neural network for my data with tensorflow. Problem? It isn't satisfied with 10gb of my memory. Just 4 layers...2
Just finished my neural network library.
The library is written in C# and easy to use. This is my first publicly available library, so constructive criticism is need :)
'We trained a neural network model'
'We taught an A.I.',
research papers themselves gave the hype we see for Machine Learning.1
As a frontend developer, I started learn unreal engine 4 in my spare time instead of build next js framework. I found C++ is very difficult in unreal project, even with the experience of building deep neural network for robot soccer back in university🤔11
Is the title "Web & Mobile Developer" on my profile misleading?
And the part in my summary which says I'm studying and currently not working ambiguous?
Cause I keep getting investment offers and job applications!
If you want I can hire you as an onClickListener function of a button in my Android app or as an activation function in my neural network model!
That moment when gulp run is as long as one epoch when training my neural network. How did we arrive here?
Implementing a neural network, SHIT CODE got so complicated, stuck in a line for a couple of days now. FUCCCCCCCCCCK! WEEKEND ALSO F@#KED1
I was surfing the web.....
Let's see if there is something new about comma ai
Maybe they decided to really release their source (visiond, etc...)
[Actually they don't :-( ]
So my trip begins...
comma(.)ai -> youtube -> github -> youtube (again) ->> etc...
Then i found this:
1) love solving puzzles. It’s like a neural network of all the problem solving I’ve ever done manifesting itself in a product/tool someone can actually use to solve Their problems.
2) pays more than I think I’m worth.
3) people immediately think I’m smarter than I am, I got low self esteem but I really feel if you can work hard enough, you can even the playing field with those that are naturally better at coding. I love feeling smart when really I was just persistent with solving a problem and worked hard at finding a solution
I can't wait to experience the joy of trying to implement a neural network to identify shapes in under a week....
A friend who just got into ML recently.
"Dude, did you know how amazing ML is??"
"I'm training a computer to give out outputs, basic AI dude"
"Dude logistic regression is the shizz"
"You heard about backprop mate?"
"ANN is the next big thing. I'm currently working on one of the biggest AI project now"
So I casually ask him whether he completely his project or not. He proudly showed me a 9 lined code he copy pasted from Google (search for neural network in 9 lines) and said, "Dude I trained my laptop with some advanced AI techniques to give out the perfect XOR outputs"
He rounded off values like 0.99 to 1 and 0.02 to 0 to make it look perfect.
Have anyone tried to train a neural network(CNN) with cuda enabled on laptop with nvidia mx150?
How was it? And what about another one with 1050 ti? Is the difference huge?5
I came across this logical bug today and realised that you never train your Neural Network with data that is in order. Always train it with randomized inputs. I spent like 4 hours trying to figure why my neural net wouldn't work since all I was classifying was Iris data.
P.S.: I'm an ML newbie :P
This summer, I am tasked with moving our production server from PHP5 to PHP7, and our current CMS has been modified in a way to be only compatible with PHP5 (as in, someone went in to the source code [and did not make a plugin] and modified the CMS), so now we are probably going to have to start everything over, or do the painstaking process of finding all of the modifications and reverting them, and then seeing the reverberations across the website of that, and fix everything. Not in the mood.
One (now previous, graduated) member of our team brought up the idea of straight up dropping everything and moving to a new language. I honestly don't even know where to start in doing so. Our code is vanilla PHP, no Laravel, no nothing, just hypertext pre-processing. I cannot fathom how the graphic designers and people who aren't too familiar with the system would handle such a shift in paradigm. On one hand, I would love to use something like Rust, with Rocket and a compile-time template engine (aka not Handlebars), but on the other hand, not everyone in the team is as experienced as me, so there would be a whole new learning curve that disregards all the previous progress they made in PHP.
Even though freeCodeCamp and the PHP migration are pretty time-consuming tasks, I really enjoy everything I'm doing this summer. I'm teaching myself new things (Haskell + neural nets), teaching other people new things (FCC), and doing some actual work that can be put on my resume (PHP).
I dabbled a bit a few months ago in Lua, which is kind of like Python, but the arrays start at one so fuck that language, damn it to hell.
please whats the easiest way i could train a neural network without writing a code,i have data set of about 700 images9
POCing a neural network thing.
Luckily it's a shallow network, but it's taking a frickin' eternity to train :(
Is anyone else interested in the Characteristica Universali. It's very fascinating and not enough people know about how it can be applied to non neural network artificial intelligence.
Looking to get a good understanding of the fundamental ideology and math behind neural networks and support vector machines. I am well versed with math so I can deal with heavier stuff if needed, I would like to see formulas but an explanation to their conception would be nice. Does anyone have any resources like this? Practical hands on practice exercises would be a plus2
Does anyone know any good resources that walk you through building a image localization neural network(preferably in tensorflow)? Something that talks you through the though process behind the network design decisions and perhaps examples of training data used to train the network? It seems like every search result is just an example of how to download a premade network and it's weights which from a learning perspective is not very helpful. I'de really love to see one of the Yolo version walked through and trained but honestly any localization would be helpful.