Most Popular
1500 questions
5
votes
1 answer
Which machine learning approach should I use to estimate how many products a research group should have to improve its category?
Currently, in my country, there is a system in which certain groups of researchers upload information on products of scientific interest, such as research articles, books, patents, software, among others. Depending on the number of products, the…
LP0
- 83
- 4
5
votes
1 answer
Which functions can be activation functions?
What are the required characteristics of an activation function (in a neural network)? Which functions can be activation functions?
For example, which of the functions below can be used as an activation function?
$$f(x) = \frac{2}{\pi}…
mBabaee
- 51
- 2
5
votes
2 answers
Are Bayesian networks important to learn in 2018?
I study AI by myself with the book "Artificial Intelligence: A Modern Approach". I've just finished the chapters about the Bayesian network and probabilities, and I found them very interesting. Now, I want to implement different algorithms and test…
kaizokun
- 173
- 5
5
votes
2 answers
What is feature embedding in the context of convolutional neural networks?
What are feature embeddings in the context of convolutional neural networks? Is it related to bottleneck features or feature vectors?
Kaustubh
- 51
- 1
- 4
5
votes
2 answers
Can translational invariance of CNNs be unwanted if object is likely in certain positions?
Various texts on using CNNs for object detection in images talk about how their translation invariance is a good thing. Which makes sense for tasks where the object could be anywhere in the image. Let's say detecting a kitten in household…
simplename
- 151
- 3
5
votes
3 answers
Does the model learn from the average of all the data points in the mini-batch?
I used the example at - https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_DataManagement/tensorflow_dataset_api.py - to create my own classification model. I used different data but the basic outline of datasets was used.…
Emile Engelbrecht
- 51
- 2
5
votes
1 answer
How to handle varying types and length of inputs in a feedforward neural network?
After learning the basics of neural networks and coding one working with the MNIST dataset, I wanted to go to the next step by making one which is able to play a game. I wanted to make it work on a game like slither.io. So, in order to be able to…
AntonKad
- 53
- 4
5
votes
1 answer
Why is breadth-first search only optimal when the cost solution is a non-decreasing function?
I am learning about searching strategies in AI and I was reading that breadth-first search is only optimal when the cost solution is a non-decreasing function? I am not really sure what this refers to since decreasing search cost should be our goal.…
xava
- 423
- 1
- 4
- 10
5
votes
2 answers
Is it possible to build an AI that learns humanity, morally?
It is a new era and people are trying to evolve more in science and technology. Artificial Intelligent is one of the ways to achieve this. We have seen lots of examples for AI sequences or a simple "communication AI" that are able to think by…
Scarlet62442
- 53
- 3
5
votes
1 answer
Over- and underestimations of the lowest and highest values in LSTM network
I'm training an LSTM network with multiple inputs and several LSTM layers in order to set up a time series gap filling procedure. The LSTM is trained bidirectionally with "tanh" activation on the outputs of the LSTM, and one Dense layer with…
Kristof
- 61
- 2
5
votes
1 answer
How can genetic programming be used in the context of auto-encoders?
I am trying to understand how genetic programming can be used in the context of auto-encoders. Currently, I am going through 2 papers
Training Feedforward Neural Networks Using Genetic Algorithms (a classific one)
Training Deep Autoencoder via…
Gabriele
- 243
- 1
- 9
5
votes
1 answer
How can neural networks that extract many features be fooled by adversarial images?
I have been reading a bit about networks where deep layers able to deal with a bunch of features (be it edges, colours, whatever).
I am wondering: how can possibly a network based on this 'specialised' layers be fooled by adversarial images?…
magnolia1
- 51
- 1
5
votes
3 answers
What is the most time-consuming part of training deep networks?
Deep networks notoriously take a long time to train.
What is the most time-consuming aspect of training them? Is it the matrix multiplications? Is it the forward pass? Is it some component of the backward pass?
echo
- 693
- 1
- 6
- 12
5
votes
1 answer
Several questions regarding the NEAT algorithm
I've recently read the paper Evolving Neural Networks through Augmenting Topologies which introduces NEAT. I am now trying to prototype it myself in JavaScript. However, I stumbled across a few questions I can't answer.
What is the definition of…
Nigk
- 63
- 1
- 6
5
votes
1 answer
How does backpropagation work on a custom loss function whose components have magnitudes of different orders?
I want to use a custom loss function which is a weighted combination of l1 and DSSIM losses. The DSSIM loss is limited between 0 and 0.5 where as the l1 loss can be orders of magnitude greater and is so in my case. How does backpropagation work in…
user12754
- 107
- 3