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?
Related
I hear the terms stability/instability thrown around a lot when reading up on Deep Q Networks. I understand that stability is improved with the addition of a target network and replay buffer but I fail to understand exactly what it's refering to.
What would the loss graph look like for an instable vs stable neural network?
What does it mean when a neural network converges/diverges?
Stability, also known as algorithmic stability, is a notion in
computational learning theory of how a machine learning algorithm is
perturbed by small changes to its inputs. A stable learning algorithm
is one for which the prediction does not change much when the training
data is modified slightly.
Here Stability means suppose you have 1000 training data that you use to train the model and it performs well. So in terms of model stability if you train the same model with 900 training data the model should still perform well , thats why it is also called as algorithmic stability.
As For the loss Graph if the model is stable the loss graph probably should be same for both size of training data (1000 & 900). And different in case of unstable model.
As in Machine learning we want to minimize loss so when we say a model converges we mean to say that the model's loss value is within acceptable margin and the model is at that stage where no additional training would improve the model.
Divergence is a non-symmetric metrics which is used to measure the difference between continuous value. For example you want to calculate difference between 2 graphs you would use Divergence instead of traditional symmetric metrics like Distance.
I am classifying a client's clients. However, the data is fluid and the clusters can change every day.
Running new clusters daily to update user clusters is difficult because Kmeans is inconsistent in labeling clusters.
If we cluster, and then train the data say with a Neural networks or XGBoost and moving forward simply predict the clusters. Does this make sense or is it a good way to do things?
Yeah, it does make sense, it's just a regular classification task at that point. You should have enough data assigned to clusters though before moving on to neural network.
On the other hand, why don't you predict clusters for new points instead of updating them (you can see separate methods for fit and predict in sklearn's docs, though it depends on technology you are using)? Remember, that neural network will only be as good as it's input (K-Means clusters) and it's predictions will probably be similiar to K-Means.
Furthermore, NNs are more complicated and harder to train, maybe those shouldn't be you first choice.
You could check the idea of fuzzy clustering as well, as the data is fluid it might be a better fit for your case. Maybe autoencoders, as a method of obtaining latent variables, might be of use as well.
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 a dataset of about a 100 numeric values. I have set the learning rate of my neural network to 0.0001. I have successfully trained it on the dataset for over 1 million times. But my question is that what is the effect of very low learning rates in the neural networks ?
Low learning rate mainly implies slow convergence: you're moving down the loss function with smaller steps (the step size is the learning rate).
If your function is convex this is not a problem, you will wait more but you'll reach a good solution.
If, as in the case of deep neural networks, your function is not convex than a low learning rate could lead to the reaching of a "good" optimum that's not the best one (getting stuck in a local minimum, without making steps as big as required to jump out of it).
That's why there are different optimization algorithms that are adaptive: such algorithm, like ADAM, RMSProp, ... have different learning rates for each weight in the network (every single learning rate starts from the same value). In this way, the optimization algorithm can work on every single parameter independently with the aim of finding a better solution (and letting the chose of the initial learning rate less critical)
As far as I understand, neural networks aren't good at classifying 'unknowns', i.e. items that do not belong to a learned class. But how do face detection/recognition approaches usually determine that no face is detected/recognised in a region? Is the predicted probability somehow thresholded?
Summary
It is true that neural networks are inherently not good at classifying 'unknowns' because they tend to overfit to the data that they have been trained on, if the underlying structure of the neural network is complex enough. However, there are multiple ways to go about reducing the affects of overfitting. For example, one technique that is used for this is called dropout. Another example can be batch normalization. Despite these techniques, the best way to reduce the affects of overfitting is to use more data.
For the facial recognition example that you have given above, it is common that the models that have been trained have 'seen' a huge amount of data. This means that there are very few 'unknowns' and even if there are, the neural network has learned how to tell if there are facial features present or not. This is because certain structures of neural networks are really good at telling if there is a pattern of features present in the input data. This helps the neural networks to learn if the image that is being input has certain features/patterns in it or not. If the these features are found then the input data is classified as face otherwise it is not.