New answers tagged

1 vote
Accepted

Why are SVMs / Softmax classifiers considered linear while neural networks are non-linear?

I was confused because the images look similar even though in reality the problems the 2 images are solving are completely different: The first image shows a linear classifier assigning scores for ...
user avatar
  • 121
1 vote

Why are embeddings added, not concatenated?

First of all, I think it is very hard to properly reason about these things, but there are a few points that might justify using sum instead of concatenation. For example, concatenation would have the ...
user avatar
  • 306
0 votes

Hidden layer size <= input size?

There isn't a rule of thumb, and in fact, expanding the input dimension is a somewhat common approach that is being used in some cases. For example, you can think of a NN that learns the function of ...
user avatar
0 votes

Make an NN utilize other NNs as part of its decision process

In tensorflow models can be their own layers as part of a larger architecture. (If you want to see an example you can check out a notebook I have here and here) Specifically what you are trying to do ...
user avatar
  • 81
0 votes

Visualizing the loss landscape in deep NN to compare optimization methods

How about: speed of convergence stability/variance w.r.t to the initial random seed (or other sources of variance like learning rate) presence/number of saddle points in your loss landscape
user avatar
0 votes

What is the advantage of adding CNN to LSTM for forecasting sequential data?

If your data are 2D + time then you might want to use something like ConvLSTM. If you only care about 1D + time then you don't need to add CNN to LSTM you only use one or the other. In terms of pros ...
user avatar
  • 121
0 votes
Accepted

How to justify the chosen neural architecture?

This is a very general question, so I'll just point to a reference that should be a good starting point. Deep Learning for Encrypted Traffic Classification: An Overview seems to contain exactly what ...
user avatar
1 vote

How to use a trained neural network to find optimal function inputs?

You can try to optimize the 4 input parameters to maximize or minimize the output of the neural network with a mathematical optimizer. The scipy.optimize package has some methods you can use. It is ...
user avatar
  • 111
0 votes

How to configure a neural network to selectively change only certain characters in a string?

You could wrap each RNN cell in a custom module that is an identity for consonants (output = input when the input is a consonant) and predicts the macronization of vowels (it outputs the result from ...
user avatar
2 votes

How to identify and diferentiate several edge lines of an object?

I don't think that more advanced AI would necessarily produce more consistent results. Check something as simple as the Prewitt operator, which is pretty damn good at edge detection. I would suggest ...
user avatar
0 votes

What exactly is the AI explainability problem?

It has much more to do with the inference of new data points than the training of deep neural networks(DNNs). Because DNNs learn complicated non-linear relations between your input variables and your ...
user avatar
3 votes
Accepted

Why are only neural networks (and not SVMs, for example) used for reinforcement learning?

The biggest problem with SVMs, random forests, gradient boosting and others for reinforcement learning (RL) is that they are not able to learn online, adjusting for new data as it arrives, and equally ...
user avatar
  • 23.8k
1 vote
Accepted

Why aren't neural networks contractions?

why neural networks aren't considered contractions, as Geoffrey J. Gordon says in his paper. I am not sure how strongly you mean aren't considered, if you mean it in a strong sense or weak sense. ...
user avatar
  • 81
1 vote
Accepted

Do I need to create one or many neural networks to play Risk?

What a fantastic problem! Also, welcome to AI. The challenge, and it isn't terrible, is that you have to build an NN that can ingest the problem. How do you pose the problem to the learner? Here is ...
user avatar
0 votes

How does backpropagation know which weights to change?

@serali is correct, there are many resources to describe this process. I'm going to talk about it in a very general way. Disclaimer: this is a work in progress, it is not yet complete. Question: How ...
user avatar
0 votes

YearPrediction dataset for a regression task: is it possible to evaluate a fair comparison between standard loss and a quadratic one?

The way to evaluate any supervised learning result is to pick a metric - a scoring system for the results. Ideally this metric captures key details of what properties you care about for the trained ...
user avatar
  • 23.8k
3 votes

How can a convnet learn with a 3x3 output layer?

I'm going to assume that what you posted is the output of something like model.summary() from TensorFlow/Keras. With that assumption, (None, 3, 3, 64) is the output shape. We can ignore the None, as ...
user avatar
  • 31
0 votes

Shifting training data

tl;dr Yes. Question: Can I train starting with a trained network instead of from a newly initialized network. Answer: You can, and should, save network weights when it is done training. You can also ...
user avatar

Top 50 recent answers are included