Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I'm preparing to give a talk about some topic I choose from artificial intelligence area (neural networks). I'm looking for something interesting, used in a real life and preferably not too complicated (the simpler it is, the easier it is for students to understand and the more interested they will be). I thought that it's a good place to look for advice ;)
Code applying neural networks to text recognition.
I think the concept of text recognition is interesting and understandable.
Toby Segaran's interesting book "Programming Collective Intelligence" contains a simple neural net example for learning search results relevancy. He offers the code from the book free on his site.
The neural net is in chapter4 code. Not sure if you could figure out the code without the text - if you don't mind spending a little money, the book certainly wouldn't hurt.
Learn your neural net the sine wave. It's simple. You only need 4 neurons. And the weights will clearly show how it's working. It was the example that made it click for me.
The "Real life applications" section of the (english) Wikipedia article about "Artificial neural networks" lists some (quite general) applications of neural networks.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
There's two things I don't know how to do about them.
I trained the network with alexnet, it couldn't converge. And there was no overfiting. However, when I trained the network with lenet, it converged. Why is that?
I trained the network to solve a problem. It converged, however not enough. The softmax loss can't be lower(0.2). And how can I deal about it.
An inability to overfit may be caused by a lack of network capacity or a bug in your code itself. Are you training the model from scratch? Did you write the model yourself? Are you working on a task at a similar scale to Imagenet classification?
Plateauing of a loss is to be expecting during any kind of model training. But without any learning curves showing the loss across epochs, a loss of "0.2" is meaningless.
Without knowing the exact task your're working on, the framework you're using, source code, learning curves, and/or any debugging steps you've taken, nobody will be able to really answer your questions. I suggest you go back to the machine learning basics in the cs231 lectures (particularly Lectures 4,5) or Andrew Ng's Coursera course for a more rudimentary knowledge.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I am currently trying to implement my own neural-network library, and I would like to test it by letting it (and networks made with other librarys) play a 2D game. The problem is I can't really find a good game for a neural network to play.
Requirements for the game:
It should not involve skills like reaction time, precision. It should instead require some tactical skills.
It should be easily scorable, in order to create an efficient evolutional algorithm.
It should be relatively simple.
It does not have to be a game that already exists, you can come up with one if you have an idea.
It may be a single-player game (like mario) or a 1v1 game (like pong).
It must not be any kind of MMO, RPG etc. I am looking for a small kind of mini-game.
The game should be well playable by a neural network. This means it should have a fixed amount of inputs somehow normalizable between 0 and 1. Inputs can be sensors, angles to closest objects etc. inputs should NOT be the pixels of the screen because 3*1920*1080 is just too much. Up to about 100 inputs are manageable (because I am a beginner and can't afford to let my computer calculate for hours just to get one generation evolved or so).
Also the game should definitely be a 2D game since i am going to use a AWT JPanel to draw on.
I'm the main developer of Neataptic.js, basically a neural network library with neuro-evolution built in to it. Just to give you some ideas, you might want to look at my following articles:
Agar.io AI
Target-seeking AI
Some other suggestions:
Snake
Flappy bird
Bomberman
Neural networks have been tested on most simple 2D games, so if you're stuck you will always find code that might help you.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
The title explains it. What computer skills, programs, et cetera are needed to make an operating system? I know I am a long way away in terms of skills to do this but I want to know what I should be aiming to learn to accomplish this goal of mine.
Start with a BS in Computer Science. Then maybe go for a Master's degree. Go heavy on the math.
Generally you need a low level language that you can compile to binary. A shop near me, Green Hills Software makes compilers and is located next to an excellent school. You could look into interning with them.
There are some great books in your area of study too.
You can buy simple chips online and write code for them. I know someone who built little robots in his garage from parts online. He would design super simple motherboards and have them built in China, write the code, and solder wheels, wings, and sensors on. He sold one of his models to NASA.
I hope you do it!
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
I am looking for ideas for my undergraduate project and I quite like the area of High Performance Computing , has got a lot of scope for research . Are there any ideas / already existing open source projects worth looking at ?
One hot field right now is in the area of algorithmic trading. You can sign up for $3000 (if you're under 21 -- it's $10k for over 21) at InteractiveBrokers.com and they will give you a free paper trading account (which is fake money traded using realtime data) of $10,000,000. They have API's in C#, C++, VB, Java and reasonable support... You could write your own stock pair trading algorithm. They have good documentation on how to get started.
You can scale this as high as you want, also a lot of people do high frequency trading which requires hpc and in-depth knowledge of Unix and C++.
Worth looking into, my 2 cents.
Perhaps massively parallel processing? Libraries like Cuda, OpenCL, and DirectCompute are just blossoming, and have a high likelihood of becoming commonplace. In my company, we are researching uses for OpenCL, and we're finding that it has the potential to revolutionize our industry.
Just a thought.
I would suggest looking at Sandia National Labs's SST (The Structural Simulation Toolkit). Its a highly parallel simulator framework used for HPC. It uses and incorporates other simulators from academia and industry. For instance, it currently integrates GEM5, QSim, MacSim, DRAMSim, Merlin, Portals, DRAMSim2, Iris, etc. Moreover, it is open source so you can contribute to the development.
You could work on integrating other academia components into SST, improve the interface of one of the components with SST, or just improve of the components themselves.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
I'm learning about multilayer perceptrons, and looking to tackle some real-world problems in Matlab. Perhaps something like medical diagnosis, or speech recognition... But I'm not really sure where to start here. How should I tackle this?
Geoff Hinton is the man when it comes to multilayer perceptrons. His Science paper from 2006 used a special class of MLP called an "autoencoder" that was successful in digit recognition, facial recognition, and document classification (all of which have real world applications):
Reducing the Dimensionality of Data with Neural Networks
Fortunately, they also published the
Matlab code.