In TensorFlow's Computational Model, is it possible to implement general machine learning algorithms? https://www.tensorflow.org/
All the projects on TensorFlow I have seen in GitHub implement some kind of Neural Network model. Given TensorFlow is an improvement over the DAG (it's not acyclic any more), I was wondering if some inherent shortcoming makes it unsuitable for general machine learning model?
In TensorFlow's Computational Model, is it possible to implement general machine learning algorithms?
 A: This is a bit of a necropost, but if you are still interested, here is a set of general tensorflow tutorials that explain how to run things in tensorflow. It includes examples of doing linear and nearest neighbor regressions, so it should help with your original question.
https://github.com/aymericdamien/TensorFlow-Examples
In addition, here is the original tensorflow tutorial for doing differential equations in tensorflow. Gives you an idea of the flexibility of the tensorflow computation graph.
https://www.tensorflow.org/versions/r0.9/tutorials/pdes/index.html
A: With TensorFlow you can implement any machine learning algorithm that relies on gradient descent and backpropagation (chain rule) or can be restated as such. That includes logistic regression, support vector machines and many others. But I wouldn't know how to implement random forest in TensorFlow.
A: A few of numpy operations are mirrored in TensorFlow, so if you can implement it in numpy, porting to TensorFlow can be straightforward. For instance, here's an example of K-means clustering: https://stackoverflow.com/questions/33621643/how-would-i-implement-k-means-with-tensorflow
