A message from our CEO about the future of Stack Overflow and Stack Exchange. Read now.
6

You could say that NAS fits into the domain of Meta Learning or Meta Machine learning. I've pulled the NAS papers from my notes, this is a collection of papers/lectures that I personally found very interesting. It's sorted in rough chronological descending order, and *** means influential / must read. Quoc V. Le and Barret Zoph are to good authors on the ...


2

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 ...


2

I'd suggest you better understand edge detectors such as Robert or Sobel operators first to understand better how convolution operation on images extract features by constant value kernels. Would personally recommend Gonzales and Woods for this, as it gives a pure mathematical explanation to how and why these features are extracted. Essentially the ...


2

Great question! It's not clearly stated (it's not stated at all on wikipedia), but after a bit of searching, I found an answer here about a third of the way down the page: The best performing architecture observed during the training of the controller is taken, and a grid search is performed over some basic hyperparameters such as learning rate and weight ...


2

Artificial neural networks (ANNs) do not modify their own weights! Humans create algorithms that modify the weights or architecture of ANNs. Having said that, you can change the weights of ANNs using other methods other than gradient descent combined with back-propagation, such as Hebbian learning, evolutionary algorithms or reinforcement learning.


1

(I will repeat a few details that you're already aware of, so that other users can also understand the context). In the Neural Architecture Search (NAS) paper (that I mention in my answer to the question you link to in your question), the agent is the controller (see also this question Is there any difference between a control and an action in reinforcement ...


1

Here are two review articles: Elsken, Metzen, Hutter: Neural Architecture Search: A Survey (2019), Journal of Machine Learning Research 20, 1-21 He, Zhao, Chu: AutoML: A Survey of the State-of-the-Art (2019)


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