Questions tagged [neural-architecture-search]

For questions related to the concept of neural (network) architecture search (NAS), which is a way of automating the design (that is, the hyper-parameters) of a neural network. NAS is related to neuroevolution, given that neuroevolution can be used to perform NAS, but neuroevolution is not the only way of performing NAS. For example, reinforcement learning can also be used to perform NAS.

Filter by
Sorted by
Tagged with
5
votes
3answers
147 views

How is neural architecture search performed?

I have come across something that IBM offers called neural Architecture search. You feed it a data set and it outputs an initial neural Architecture that you can train. How is neural architecture ...
3
votes
2answers
88 views

Is it possible to train a neural network with 3 inputs and 12 outputs?

The selection of experimental data includes a set of vectors of different dimensions. The input is a 3-dimensional vector, and the output is a 12-dimensional vector. The sample size is 120 pairs of ...
3
votes
1answer
23 views

Which hyperparameter does Neural Architecture search (NAS) use?

i have read a lot about NAS but I still do not understand one concept: When setting up a neural network, hyperparameters need to set up, like for example the learning rate, dropout rate, batch size, ...
3
votes
1answer
82 views

How does RL based neural architecture search work?

I have read through many of the papers and articles linked in this thread but I haven't been able to find an answer to my question. I have built some small RL networks and I understand how REINFORCE ...
3
votes
0answers
17 views

Which hyper-parameters are considered in neural architecture search?

I want to understand automatic Neural Architecture Search (NAS). I read already multiple papers, but I cannot figure out what the actual search space of NAS is / how are classical hyper-parameters ...
2
votes
0answers
20 views

How do I determine the best neural network architecture for a problem with 3 inputs and 12 outputs?

This post continues the topic in the following post: Is it possible to train a neural network with 3 inputs and 12 outputs?. I conducted several experiments in MATLAB and selected those neural ...
1
vote
1answer
33 views

Convolutional filters: create new ones

I'm studying a Master's Degree in Artificial Intelligence an my final work is about Convolutional Neuronal Networks. I was looking for information about filters (or kernel) at the convolutional ...
1
vote
0answers
8 views

Regional specialization in neural networks (especially for language processing)?

What is the status of the research on regional specialization of the artificial neural networks? Biology knows that such specialization exists in the brain and it is very important for the functioning ...
1
vote
0answers
14 views

Number of weights in historical to cutting edge deployment of deep networks [closed]

In cutting edge deployment of deep networks for different architectures (such as $CNN$, $QRNN$ etc) what is the historical trend of current limits of trainability possible computationally? By this I ...
0
votes
1answer
54 views

Can neural networks modify their own weights without back-propagation and gradient descent?

Can neural networks modify their own weights without back-propagation and gradient descent?