When doing reinforcement learning, I have to start training from the beginning each time. It costs lots of time. Is there any solution on starting training from the previous training results? Thanks.
If you are doing reinforcement learning based on episodes, you can save the networks you have trained to a file every X episodes. When you are running the script, you can check if that file exists, and load it instead of starting with an empty network.
How you can do this depends on which programming language you're using.
If you are using Python, you can save your data, state table and neural network weights using the Pickle or JSON modules.
Related
I have a large set of Training data which consists of various texts. They should be the input for my neural network. I have no output, or I don't know what to put as output.
Anyway, after the learning phase I want the neural network to create new texts based on the training data.
I read about this like „I made a bot watch 1000 hours of xy and asked it to write a new xy“.
Now my question is, what kind of machine learning is this? I am not looking for instructions on how to write it, but just a hint on how to find some keywords or tutorials. My Google searches so far were useless.
Your problem can usually be solved by an Encoder-Decoder architecture. This architecture would learn a set of latent vectors from your input, then try to output in whatever form you want. This architecture can be built with RNN, LSTM or CNN. Nowadays, attention-based models like transformers are more common among the big names. If you want to do text generation, you can start by reading about Generative Adversarial Networks (GANs).
Does it overfit if I build a machine learning model where it use the output from another machine learning model while both models are trained on the same data?
Basically I was wondering if I can use the KNN prediction result as an input for a deep neural network model while both of the models are trained on the very same data.
Nesting machine learning models is possible. For example, neuronal networks can be seen as multiple nested perceptrons (see https://en.wikipedia.org/wiki/Perceptron).
However you are right - nesting machine learning models increase the VC-dimension (https://en.wikipedia.org/wiki/VC_dimension) of your complete machine learning system and thus the risk of overfitting.
In practice cross-validation is often used in order to reduce the risk of overfitting.
Edit:
#MatiasValdenegro +1 for pointing towards a point I do not specify very clearly in my answer. Pure cross-validation can indeed only be used in order to detect overfitting.
However when we training certain machine learning systems like neuronal networks, it is possible to use some sort of cross-validation in order to reduce the risk of overfitting. In order to do so, we simply discard e.g. 10% of the training data for training. Then after each training round, the trained machine learning system is evaluated on the discarded training data. Once the trained neuronal network is getting worse on the discarded part, the training algorithm stops. This is for example done by the python pybrain (http://pybrain.org/) library.
I have tried with KDD dataset on my neural net and now I want to extend using ISCX dataset. Some part of this dataset contains the HTTP DOS attacks labelled represents replica of real time network traffic but I couldn't figure out how can I convert them into Neural inputs(numeric) to train and test my neural net which would classify these intrusion vectors..
Appreciated for Any pointers..
I didn't work with this data set, but if you have sufficient information about features and values of each feature, you can create .arff file quickly and then use WEKA very easy.
Although you can use many applications but some user-friendly applications such as GUI of WEKA has the capability of working with discrete and non numerical features very easy. and can help you to start working with your data set as fast as possible.
I have a neural network that performs a classification task, and it works fairly well when the training set is large enough.
However, I'm looking for a way to train the NN with one labelled example at a time.
That is, I intercept data, one example at a time, and I need to update my NN weights. I'm not allowed to store the data for future, batch training purposes.
I have a feed-forward NN built(following Stanford's ML course on Coursera) in octave. I can run back-prop on the NN using each new example, but that approach unreliably converges, and takes a significant amount of time.
Are there any other more efficient algorithms for online learning out there in the context of Neural Networks?
I noticed Matlab's adapt() function seems to do just this. The documentation doesn't specify what it's doing behind the scene. Is it just one iteration of back-prop?
If I have a video dataset of a specific action , how could I use them to train a classifier that could be used later to classify this action.
The question is very generic. In general, there is no foul proof way of training a classifier that will work for everything. It highly depends on the data you are working with.
Here is the 'generic' pipeline:
extract features from the video
label your features (positive for the action you are looking for; negative otherwise)
split your data into 2 (or 3) sets. One for training, one for testing and the other optionally for validation
train a classifier on the labeled examples (e.g. SVM, Neural Network, Nearest Neighbor ...)
validate the results on the validation data, if that is appropriate for the algorithm
test on data you haven't used for training.
You can start with some machine learning tools here http://www.cs.waikato.ac.nz/ml/weka/
Make sure you never touch the test data for any other purposes than testing
Good luck
Almost 10 years later, here's an updated answer.
Set up a camera and collect raw video data
Save it somewhere in form of single frames. Do this yourself locally or using a cloud bucket or use a service like Sieve API. Helpful repo linked here.
Export from Sieve or cloud bucket to get data labeled. Do this yourself or using some service like Scale Rapid.
Split your dataset into train, test, and validation.
Train a classifier on the labeled samples. Use transfer learning over some existing model and fine-tune just the last few layers.
Run your model over the test set after each training epoch and save the one with the best test set performance.
Evaluate your model at the end using the validation set.
There are many repos that can help you get started: https://github.com/weiaicunzai/awesome-image-classification
The two things that can help you ensure best results include 1. high quality labeled data and 2. a diverse, curated dataset. That's what Sieve can help with!