# Tag Info

4

You're right about the basic arrangement of the inputs, but there are a number of differences: Artificial neural networks typically use exemplar data as inputs for the purpose of training, or adjusting the weights of its internal connections, to accurately classify them within a certain error range. The network is then applied to unknown data to classify ...

4

I think you should redirect your focus. Learn and play with ML, and only when compute becomes the main bottleneck for your learning, invest in hardware. I've recently engaged into a ML project for which I 've assembled a machine with gtx1080, installed gui-less ubuntu, configured ssh, drivers etc, and than spend 3 months on data collection. And the dataset ...

4

There is nothing stopping you, you can setup Dense Neural Networks to have any size inputs or outputs (simple proof is to imagine a single layer NN with no activation is just a linear transform and given input dim $n$ and output dim $m$, it's just a matrix of $n$ x $m$, trivially this works though with any number of hidden layers) The better question is ...

3

You can synthetically increase the number of samples. For example with augmentation or unsupervised adaption (Self-training). With augmentation you grant the system way more robustness so i would really recommend this. For example this github. The problem with such small database sizes is that your test-set is also very small and you cannot test properly if ...

3

It is possible, but is a pretty terrible idea. There are a few options. One is to not use the GA as a direct classifier, but instead use a GA to learn the parameters of another classification model like a neural network. The basic idea of a GA is that it (very roughly speaking) forms a black-box method for searching an arbitrary space for solutions that ...

2

As the question has been left unanswered, for future readers of the questions: The documentation you link gives the answer to your question. Given the fact you have a pre-trained model as you say: YPred = classify(netTransfer,testDigitData); where netTansfer is the pre-trained model and testDigitData is your test image that you want to predict the label. ...

2

You must understand that a genetic algorithm is an optimization algorithm. You can't feed it e-mails and make it classify spam. A genetic algorithm is used to train a model to classify spam. That something could be neural networks. What you need is a genetic algorithm that optimizes neural networks neuroevolution, which might roughly work as follows Start ...

2

Yes, you can use confusion matrix as a performance metric for a classifier where the output of the classifier is class labels. If your classifier output is a likelihood floating point value for each of the classes, then you have to use some scheme of converting the likelihoods to a class label. For example, use softmax function for one hot encoding. So, ...

2

Finding lines in an image often leads to the Hough line transform. Many libraries implement it, including OpenCV. Getting the lines should answer subsequent questions (and it doesn't, please consider having one question per post, and some other sites on StackExchange may be better suited than AI.SE). Alternative approaches based on Machine Learning may also ...

2

Deep learning based image segmentation is basically pixel-wise image classification. So instead of predicting a $C$ dimensional vector $\vec{x}$ where $C$ corresponds to the number of class labels, you predict a tensor $x\in\mathbb{R}^{h\times w \times C}$ of the same height and width dimensions as your input image, and with $C$ channels which correspond to ...

2

If you are just starting out with Deep Learning, then a laptop with GTX 1060 is enough. I am using a GTX 1060 myself and I find it adequate for many of my personal projects, training large datasets and participating in most (not all) Kaggle competitions as well. But you say that you want to do research work as well. In that case, you may want to contact ...

2

(This question is could be considered off-topic or opinion-based, but I will answer it by providing facts that could hinder the adoption of MATLAB by AI researchers). There are 2 main reasons why MATLAB may not be the "best" programming language/environment for research (in AI and other areas too) It's closed source (i.e. it's more difficult to ...

1

Similar to other answers, I don't know Matlab that well but you could try the following steps to debug your problem. Make sure you can overfit to a single instance from your dataset, pull out a single image with a good amount of true positives in it. Duplicate that images B times (where B = Batch Size) and then try to train your network with only that small ...

1

In theory, yes, using synthetic data generation. This involves applying transformations to the original images to generate new 'unique' images. Some standard techniques include rotating, flipping, stretching, zooming or brightening. Obviously not all of these make sense depending on the data. In your problem, zooming, stretching and brightening could be used ...

1

The perceptron convergence theorem states that any architecture will lead to a correlation between the data. Yes, you can!

1

You need to have access to the 696th hour (or successive hours), otherwise, you cannot test your model. An alternative would be, for example, to train your model on the first 693 hours, validate it on the 694th hour, and test it on the 695th hour.

1

From your question, it appears that you would like to use other features in your data to predict one of the features. I am not sure I understood your question clearly, but anyways, either, you would be using the feature you want to predict as the output of the network. Also, if you want to use the output of the network and other features to predict the new ...

1

I suggest you first consider your coordinate systems. There are two. Field Coordinate Axis Field boundary corners are in field coordinates (for example): { (-50.0, -35.0, 0), (50.0, -35.0, 0), (-50.0, -35.0, 0), (50.0, -35.0, 0) }, all values in meters. At any moment in time the camera in the robot: is at (x, y, z) and oriented relative to north by angle ...

1

I assume that you are familiar with homogeneous transformations and the meaning of global and local coordinate frames. If not, global frame is the fixed frame; a reference frame for your whole problem, such as the starting position of your robot. Local frame should be placed anywhere on your robot, preferably in the middle-point of the virtual line (called &...

1

Yes, it is a very common practice to use some RNN when your input data is a sequence. Besides, your network has some shape issue if your input data is 2D. You should, at least flatten your input data to a vector to be able to forward propagate to the dense layer, but instead of this use some kind of RNN. To the best of my knowledge, that dropout value doesn'...

1

I think that this may be too difficult for only a few weeks of work. There are a few reasons why and although all of the reasons are themselves learning opportunities, it may cost you more time than you have. First off, Robots are hard to work with. Ask anyone who has worked with robots and they will say that have broken their heart at least once. This is ...

Only top voted, non community-wiki answers of a minimum length are eligible