I'm fairly beginner in the world of machine learning and am trying to make some predictions on fantasy sport performance in baseball on any given night. Given the sequential nature of the data, recurrent neural networks seemed liked a good starting point.
I understand the basic principles of rnn but what isn't clear to mean is how to incorporate multiple time series' from different individuals into a single model. For instance, we have performance for 2000 players across each of their career and hence have 2000 distinct time series. In order to make use of rnn, would I have to build models for each player separately, or is it possible/better to pass a player's ID into the model as a feature?
If the latter is possible, I'm still unsure about how this would mechanically work, because players have different time series lengths, and we would have many time series observations for a particular point in time.
Some references/examples/advice would be very helpful.
Related
I'm fairly new to the world of NNs so it could be that my question is extremely stupid, so sorry in advance:
I'm working on a predictive autoscaler, trying to predict the workload of different, unknown, applications using only historic workload data about this application.
One of my predictors is a LSTM RNN. To make the RNN predict the values in question, I have to define the timestep - that is the amount of Lags I feed in to the RNN to predict the future value (I hope I used the right terms here). Alot of tutorials and literature seems to set the timestep to a value that seems pretty random to me. My Question can be divided in two subquestions:
1. Given I don't know the Timeseries during implementation: Is there any way to compute this value other than trying different values and comparing the confidence of the prediction?
2. How does the Value influence the assumptions the RNN learns about that time series?
I sadly lack of any intuition on what this value influences. To make an example of my confusion:
Given I have a Time Series with a yearly seasonality, but I decide that I will only feed in the data of a week to make the next prediction: Is the Network able to learn this yearly seasonality? Part of me says no because it can't learn that the partial correlation between the timestamp in question and the lag 365 days ago is very high, because it does not have that data, right? Or does it because it has seen the data from a year ago while training and learned that fairly similar pattern and simply applies it now (which is more likely to be right I guess)?
Is my assumption right, that taking too many timestamps into the equation overfits the network?
Can you please help me get a vague understanding of what this parameter influences in the great scheme of things and what properties of a time series should influence my choice of that value?
Thank you so much and stay healthy :)
I study ML and I see that most of the time the focus of the algorithms is run time and not accuracy. Reducing features, taking sample from the data set, using approximation and so on.
Im not sure why its the focus since once I trained my model I dont need to train it anymore if my accuracy is high enough and for that if it will take me 1 hours or 10 days to train my model it does not really matter because I do it only 1 time and my goal is to predict as better as I can my outcomes (minimum loss).
If I train a model to differ between cats and dogs I want it to be the most accurate it can be and not the fasted since once I trained this model I dont need to train any more models.
I can understand why models that depends on fasting changing data need this focus of speed but for general training models I dont understand why the focus is on speed.
Speed is relative term. Accuracy is also relative depending on the difficulty of the task. Currently the goal is to achieve human-like performance for application at reasonable costs because this will replace human labor and cut costs.
From what I have seen in reading papers, people usually focus on accuracy first to produce something that works. Then do ablation studies - studies where pieces of the models are removed or modified - to achieve the same performance in less time or memory requirements.
The field is very experimentally validated. There really isn't much of a theory that states why CNN work so well other than that it can model any function given non-linear activations functions. (https://en.wikipedia.org/wiki/Universal_approximation_theorem) There have been some recent efforts to explain why it works well. One I recall is MobileNetV2: Inverted Residuals and Linear Bottlenecks. The explaination of embedding data into a low dimensional space without losing information might be worth reading.
I recently came across this link for learning tensorflow object detection
https://www.youtube.com/watch?v=Rgpfk6eYxJA&t=993s
However I have few doubts and want suggestion on how to proceed.
1) How should I train different objects using the same model( I mean what should my data set contain if I want to train cats,dogs as objects.
2) and once I have trained it for dogs and then continue training on cars will the model detect dogs?
Your dataset should contain a large variety of examples for every object (class) you wish to detect. It sounds like you're misunderstanding the training process by assuming that you train it on each class of objects in sequence, this is incorrect. When you train the model you will be taking a random batch of samples (maybe 64 for example) across all classes.
Training simultaneously on all or many of the classes makes sense, you have one model that has to perform equally well on all classes. So when you train the model you compute the error of the parameters with respect to a random selection of classes and average the error to come up with each update step, yielding a model that performs well across classes.
Notice that it's quite common to run into class imbalance issues. If you have only a few samples of cats, and millions of samples of dogs you will disproportionately penalize the network for misclassifying dogs as cats and the network will simply always predict dog to hedge its bet. Ideally, you will have a roughly equal balance of data per class, if not, there are books and tutorials galore on the strategies to deal with this.
I have a use case where I have around 100 images each of 10000 unique items. I have 10 items with me which are all from the 10000 set and I know which 10 items too but only at the time of testing on live data. I have to now match the 10 items with their names. What would be an efficient way to recognise these items? I have full control of training environment background and the testing environment background. If I make one model of all 10000 items, will it scale? Or should I make 10000 different models and run the 10 items on the 10 models I have pretrained.
Your question is regarding something called "one-vs-all classification" you can do a google search for that, the first hit is a video lecture by Andrew Ng that's almost certainly worth watching.
The question has been long studied and in a plethora of contexts. The answer to your question does very much depend on what model you use. But I'll assume that, if you're doing image classification, you are using convolutional neural networks, because, after all, they're state of the art for most such image classification tasks.
In the context of convolutional networks, there is something called "Multi task learning" that you should read up on. Boiled down to a single sentence, the concept is that the more you ask the network to learn the better it is at the individual tasks. So, in this case, you're almost certain to perform better training 1 model on 10,000 classes than 10,000 classes each performing a one-vs-all classification scheme.
Take for example the 1,000 class Imagenet dataset, and CIFAR-10's 10 class dataset. It has been demonstrated in numerous papers that first training against Imagenet's 1,000 class dataset, and then simply replacing the last layer with a 10 class output and re-training on CIFAR-10's dataset will produce a better result than just training on CIFAR-10's dataset alone. There are admittedly multiple reasons for this result, Imagenet is a larger dataset. But the richness of class labels, multi-task learning, in the Imagenet dataset is certainly among the reasons for this result.
So that was a long winded way of saying, use one model with 10,000 classes.
An aside:
If you want to get really, really interesting, and jump into the realm of research level thinking, you might consider a 1-hot vector of 10,000 classes rather sparse and start thinking about whether you could reduce the dimensionality of your output layer using an embedding. An embedding would be a dense vector, let's say size 100 as a good starting point. Now class labels turn into clusters of points in your 100 dimensional space. I bet your network will perform even better under these conditions.
If this little aside didn't make sense, it's completely safe to ignore it, your 10,000 class output is fine. But if it did peek your interest look up information on Word2Vec, and read this really nice post on how face recognition is achieved using embeddings: https://medium.com/#ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-learning-c3cffc121d78. You might also consider using an Auto Encoder to generate an embedding for the images (though I favor triplet embeddings as typically used in face recognition myself).
I have faced some problem when I needed to solve Regression Task and use as minimum instances as possible. When I tried to use Xgboost I had to feed 4 instances to get the reasonable result. But Multilayer Perceptron tuned to overcoming Regression problems has to take 20 instances, tried to change amount of neurons&layers but the answer is still 20 .Is it possible to do something to make Neural Network solve Resgression tasks with from 2 to 4 instances? if yes - explain please what should I do to succeed in it? Maybe there is some correlation between how much instances are needed to train and get reasonable results from Perceptron and how features are valuable inside dataset?
Thanks in advance for any help
With small numbers of samples, there are likely better methods to apply, Xgaboost definitely comes to mind as a method that does quite well at avoiding overfitting.
Neural networks tend to work well with larger numbers of samples. They often over fit to small datasets and underperform other algorithms.
There is, however, an active area of research in semi-supervised techniques using neural networks with large datasets of unlabeled data and small datasets of labeled samples.
Here's a paper to start you down that path, search on 'semi supervised learning'.
http://vdel.me.cmu.edu/publications/2011cgev/paper.pdf
Another area of interest to reduce overfitting in smaller datasets is in multi-task learning.
http://ruder.io/multi-task/
Multi task learning requires the network to achieve multiple target goals for a given input. Adding more requirements tends to reduce the space of solutions that the network can converge on and often achieves better results because of it. To say that differently: when multiple objectives are defined, the parameters necessary to do well at one task are often beneficial for the other task and vice versa.
Lastly, another area of open research is GANs and how they might be used in semi-supervised learning. No papers pop to the forefront of my mind on the subject just now, so I'll leave this mention as a footnote.