Neuroph Studio: train, stop, pause and test button disabled - neural-network

I have installed NeurophStudio 2.91 for Windows. I have created a Neural Network using Multilayer Perceptron and loaded some training data. Now I`d like to train the Neural Network, but the buttons train, stop, pause and test are disabled. How can I enable them? I also had the problem that the program does not react several times and I had to restart it. Installing it new did not help.

Not sure if you're still looking for an answer, but I was struggling with the same this morning. Turned out that you have to drag the training set from the files pane, and drop it on the top-most layer of the NN (input layer). Once you do that, the train, stop, test input buttons become enabled. Consult http://neuroph.sourceforge.net/tutorials/MultiLayerPerceptron.html for more info.
Have only been using Neuroph for a few hours, and it was so erratic that it drove me crazy. But I realized that once you understand how things work, it'll work as expected most of the times. For an example, if you run a training session where your network architecture and training set are such that the training might never converge, and you haven't set a max iterations limit, then it'll keep training forever. Many of the times the graphs aren't showing properly in real-time, so you'd never know that the training is still going on, but it'll slow down your machine to a crawl.
Didn't find 'enough' material for a complete newb to get going, and I'm still struggling with some very basic stuff (like how to reset a Neural Network from the studio), but it seems worth it to plough through the initial stumbles just for the sake of having a tool to design/train/troubleshoot your NN in a gui and then export it to your app, alone.

i also face your problem a hours ago, and that was cus of its version i was using 2.93 then i uninstall it and i install 2.8 and i work perfectly for me
hope this will help u!!!

Related

STM32F103 blue pill ADC example

After searching for a veeery long time (more then 3 months) in all the main places where to get info and reading the datasheet of the chip I would like to ask the STM32 specialists inhere if there is a example for using the ADC maybe with DMA from the arduino IDE. I did see some incomplete parts inhere and for other compiler/IDE environments. But maybe i did not strike the good luck of finding the right info (that even i can understand) yet for what i need.
Your help is much appreciated.
I want to sample audio data, one channel 30KHz plus, 12 bits and each time 16 samples are taken an interrupt to handle the data that is in an array.
I have seen the pigOscope code (it uses analogread) and the info about analogread where there is stated this command is not meant for higher sampling speeds So that got me sort of into conflict with myself .... Who can break me out of my endless brainloop .....?;
Greetings ... Eric.
I have seen the pigOscope code (it uses analogread)
I wrote the Pig-o-scope code, with a lot of input from others at stm32duinocom and if you take the time to read the code, which I will grant you is somewhat simplistic, you will discover that analogRead is only used to trigger. The code uses DMA to do the high speed transfer.
I completely agree with the comment that you dont't need the Arduino IDE, you could "borrow" the DMA code and tailor it to your needs. However if you want a quick and dirty coding and prototyping environment, then there is nothing wrong with using the Arduino IDE. Take a trip to the stm32duino.com site, and you will see that I along with a lot of the other developers use the Arduino IDE, and Eclipse, and Atollic, and roll our own batch files, use vi, etc etc.
It all depends on what you are trying to do, and in many cases using the Arduino IDE gets you to working result a lot faster than learning an entire new IDE, just for one task.
But then again, I'm firmly on the side of vi in the vi/emacs wars, so what the heck do I know. Just don't use nano. ;¬)

How to make code repeat itself every second (Trading Toolbox)

I recently came across the Trading Toolbox in matlab and I was very excited to find out you can do automated trading with it. I read the documentation, which was pretty clear, a couple of functions to connect to a certain broker, some order functions and a disconnect function. What I couldn't find out though is how you can make sure that your code is run constantly, otherwise automated trading isn't possible since trades can only be made or closed once every time you run your code. That shouldn't be the case, the code should be repeated every second or minute for that matter. Does anyone know how this can be achieved?

Visual feedback for area learning and motion tracking in Unity

I'm getting pretty bad results with Area Learning, the localization takes very long and I have no idea what's happening. Did I map the area enough? Is there enough landmarks? Is the ADF alright? No clue.
Is there any way to provide a visual feedback while doing the actual motion tracking and area learning? I keep seeing it in Google videos but didn't find any way of doing it in the Unity SDK.
I would like something like this in my video overlay: https://youtu.be/NTZZCtmR3OY?t=10m57s
Btw my results in Unity are FAR worse than this demo, sometimes it takes minutes for the device to localize and only at a certain spot in the room, the next minute the very same spot doesn't work again. Quite frustrating. No idea what app the presenter uses, for instance, my ADF Inspector reliably crashes every time I try to load any ADF. (Using Wasat and recently I've deleted and re-installed everything.)
It is not supposed to be so. It should not be that bad, under the normal day light condition. If it is a small area, should be able to localize using ADF within 3-5 seconds. The video showed the usual case -- always like this.
If your kernel is up to date, and you are using the correct development kit. I would recommend you to reach the tango team customer service directly.
tango-help#google.com
Perhaps it is caused by your device defective. If so, ask for an exchange would solve the problem.

What happens to a running program when my computer switches to Hibernate?

my laptop goes to hibernate when I'm running a matlab code because of overheating. when I turn it on again, matlab countinue to running my code. I'm worry about the results of my code! what do you think? is there any problem with hibernating and resuming the matlab code?
thank you.
I recommend looking at this: http://www.mathworks.com/matlabcentral/answers/46569-what-happens-to-a-running-program-when-my-computer-switches-to-hibernate
Theoretically, when the computer hibernates, the status of the memory and disk are saved. However, as it is pointed out in the link I provided, this is not very reliable and can lead to corruption of files and/or data.
Instead, I recommend that your program saves necessary variables from time to time using checkpoints, so that your program can run reliably even when your code is paused or your computer hibernates. Take a look at this link to see how to implement checkpoints: http://www.walkingrandomly.com/?p=5343.

How is time-based programming done?

I'm not really sure what the correct term is, but how are time-based programs like games and simulations made? I've just realized that I've only wrote programs that wait for input, then do something, and am amazed that I have no idea how I would write something like pong :)
How would something like a flight simulator be coded? It obviously wouldn't run as fast as the computer could run it. I'm guessing everything is executed on some kind of cycle. But how do you handle it when a computation takes longer than the cycle.
Also, what is the correct term for this? Searching "time-based programming" doesn't really give me helpful results.
Games are split into simulation (decide what appears, disappears or moves) and rendering (show it on the screen, play sounds). Simulation is designed to be time-dependent: you can tell the simulator "50ms have elapsed" and it will compute 50ms worth of simulation. A typical game loop will render (which takes an arbitrary amount of time), then run the simulator for the duration since the last time the simulator was run.
If the code runs fast, then the simulator steps will be short (only a few ms) and the game will render the scene more often.
If the code runs slowly, the simulator steps will have longer steps and there will be proportionally fewer renders.
If the simulator runs slower than the simulation itself (it takes 100ms to compute 50ms worth of simulation) then the game cannot run. But this is an exceedingly rare situation, and games sometimes have emergency systems that drop the quality of the simulation to improve performance when this happens.
Note that time-dependent does not necessarily mean millisecond-level precision. Some systems implement simulations using time-based functions (traveled distance equals speed times elapsed time), while others run fixed-duration simulation steps.
I think the correct term is "Real-time application".
For the first question, I'm with spender's answer.
If you know the elapsed time between two frames, you can calculate (with physics, for example) the new position of the elements based on the previous ones.
There are two approaches to this, each with advantages and disadvantages.
You can either go frame based, whereby a timer signals n new frames every second. You calculate movement simply by counting elapsed frames. In the case that computation exceeds the available time, the game slows down.
...or, keeping the frame concept, but this time you keep an absolute measure of time, when the next frame is signalled, you calculate world movement via the amount of elapsed time. This means that stuff happens in real-time, but in the case of severe CPU starvation, gameplay will become choppy.
There's an old saying that "the clock is an actor". Time-based programs are event-driven programs, but the clock is a constant source of events. At least, that's a fairly common and reasonably easy way of doing things. It falls down if you're doing hard realtime or very high performance things.
This is where you can learn the basics:
http://www.gamedev.net/reference/start_here/
Nearly all of the games are programmed in real time architecture and the computer capabilities(and the coding of course :)) determine the frame rate.
Game programming is a really complex job including object modeling, scripting, math calculations, fast and nice rendering algorithms and some other stuff like pixel shaders.
So i would recommend you to check out available engines in the first place.(just google "free game engine")
Basic logic is to create an infinite loop (while(true){}) and the loop should:
Listen for the callbacks - you get the keyb, mouse and system messages here.
Do the physics due to the time passed till the previous frame and user inputs.
Render the new frame (gdi, derictX or openGL)
Have fun
Basically, there are 2 different approaches that allow you to add animation to a game:
Frame-based Animation: easier to understand and implement but has some serious disadvantages. Think about it this way: imagine your game runs at 60FPS and it takes 2 seconds to draw a ball that goes from one side of the screen to the other. In other words, the game needs 120 frames to move the ball along the screen. If you run this game on a slow computer that's only able to render 30FPS, it means that after 2 seconds the ball will be at the middle of the screen. So the problem of this approach is that rendering (drawing the objects) and simulation (updating the positions of the objects) are done by the same function.
Time-based Animation: a sophisticated approach that separates the simulation code from the rendering code. The amount of FPS the computer can render will not influence the amount of movement (animation) that has to be done in 2 seconds.
Steven Lambert wrote a fantastic article about these techniques, as well as 3rd approach that solves a few problems with Time-based Animation.
Some time ago I wrote a C++/Qt application to demonstrate all these approaches and you can find a video of the prototype running here:
Source code is available on Github.
Searching for time-based movement will give you better results.
Basically, you either have a timer loop or an event triggered on a regular clock, depending on your language. If it's a loop, you check the time and only react every 1/60th of a second or so.
Some sites
http://www.cppgameprogramming.com/
Ruby game programming
PyGame
Flight Simulation is one of the more complex examples of real-time simulations. The understanding of fluid dynamics, control systems, and numerical methods can be overwhelming.
As an introduction to the subject of flight simulation, I recommend Build Your Own Flight Sim in C++. It is out of print, but seems to be available used. This book is from 1996, and is horribly dated. It assumes a DOS environment. However, it provides a good overview of the topics, covers numerical integration, basic flight mechanics and control systems. The code examples are simplistic, reasonably complete, and do not assume the more common toolsets used for graphics today. As with most things, I think it is easier to learn the subject with a more basic reference.
A more advanced text (college senior, first year graduate school) is Principles of Flight Simulation provides excellent coverage of the breadth of topics involved in making a flight simulation. This book would make an excellent reference for anyone seriously interested in flight simulation as an engineering task, or for more realistic game development.