Questions tagged [neural-networks]

For questions about a artificial networks, such as MLPs, CNNs, RNNs, LSTM, and GRU networks, their variants or any other AI system components that qualify as a neural networks in that they are, in part, inspired by biological neural networks.

796 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
13 votes
0 answers
297 views

What is the number of neurons required to approximate a polynomial of degree n?

I learned about the universal approximation theorem from this guide. It states that a network even with a single hidden layer can approximate any function within some bound, given a sufficient number ...
user avatar
  • 673
9 votes
0 answers
172 views

Why is my GAN more unstable with bigger networks?

I am working with generative adversarial networks (GANs) and one of my aims at the moment is to reproduce samples in two dimensions that are distributed according to a circle (see animation). When ...
user avatar
  • 134
9 votes
2 answers
374 views

Back-of-the-envelope machine learning (specifically neural networks) calculations

There is a popular story regarding the back-of-the-envelope calculation performed by a British physicist named G. I. Taylor. He used dimensional analysis to estimate the power released by the ...
user avatar
  • 281
9 votes
0 answers
770 views

Are Cellular Neural Networks one type of Neural Networks?

I am researching Cellular Neural Networks and have already read Chua's two articles (1988). In cellular neural networks, a cell is only in relation with its neighbors. So it is easy to use them for ...
user avatar
  • 273
7 votes
1 answer
92 views

What is the impact of using multiple BMUs for self-organizing maps?

Here's a sort of a conceptual question. I was implementing a SOM algorithm to better understand its variations and parameters. I got curious about one bit: the BMU (best matching unit == the neuron ...
user avatar
7 votes
1 answer
113 views

How does the network know which objects to track in the paper "Label-Free Supervision of Neural Networks with Physics and Domain Knowledge"?

I was reading the paper Label-Free Supervision of Neural Networks with Physics and Domain Knowledge, published at AAAI 2017, which won the best paper award. I understand the math and it makes sense. ...
user avatar
7 votes
0 answers
354 views

Why don't people use nonlinear activation functions after projecting the query key value in attention?

Why don't people use nonlinear activation functions after projecting the query key value in attention? It seems like doing this would lead to much-needed nonlinearity, otherwise, we're just doing ...
user avatar
  • 530
7 votes
1 answer
223 views

Why do layered neural nets struggle with continous data?

In this article here, the writer claims that a new type of neural net is required to deal with data that is both continuous, and also sparsely sampled. It was my understanding that this was the ...
user avatar
  • 171
6 votes
0 answers
100 views

How can a neural network distinguish a rotated 6 and 9 digits?

Rotated MNIST is a popular dataset for benchmarking models equivariant to rotations on $\mathbb{R}^2$, described by $SO(2)$ group or its discrete subgroups like $\mathbb{Z}^{n}$: Group equivariant ...
user avatar
6 votes
0 answers
101 views

How do neural network topologies affect GPU/TPU acceleration?

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
user avatar
5 votes
0 answers
60 views

It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems?

It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems? If we take, for example, the travelling salesman problem (or the dominating set problem). Let's say ...
user avatar
  • 171
5 votes
0 answers
96 views

Why is there a Uniform and Normal version of He / Xavier initialization in DL libraries?

Two of the most popular initialization schemes for neural network weights today are Xavier and He. Both methods propose random weight initialization with a variance dependent on the number of input ...
user avatar
  • 600
5 votes
1 answer
117 views

How to classify human actions?

I'm quite new to machine learning (I followed the Coursera course of Andrew Ng and now starting deeplearning.ai courses). I want to classify human actions real-time like: Left-arm bended Arm above ...
user avatar
5 votes
1 answer
173 views

How do big companies, like Facebook, model individuals and their interaction?

As a layman in AI, I want to get an idea of how big data players, like Facebook, model individuals (of which they have so many data). There are two scenarios I can imagine: Neural networks build ...
user avatar
4 votes
1 answer
141 views

Which neural network can I use to solve this constrained optimisation problem?

Let $\mathcal{S}$ be the training data set, where each input $u^i \in \mathcal{S}$ has $d$ features. I want to design an ANN so that the cost function below is minimized (the sum of the square of ...
user avatar
4 votes
0 answers
57 views

Can the quality of randomness in neural network initialization affect model fitting?

This is a topic I have been arguing about for some time now with my colleagues, maybe you could also voice your opinion about it. Artificial neural networks use random weight initialization within a ...
user avatar
4 votes
0 answers
71 views

Visualizing the Loss Landscape of Neural Nets: Meaning of the word 'filter'?

I found myself scratching my head when I read the following phrase in the paper Visualizing the Loss Landscape of Neural Nets: To remove this scaling effect, we plot loss functions using filter-wise ...
user avatar
  • 41
4 votes
0 answers
85 views

Why does sigmoid saturation prevent signal flow through the neuron?

As per these slides on page 35: Sigmoids saturate and kill gradients. when the neuron's activation saturates at either tail of 0 or 1, the gradient at these regions is almost zero. the gradient and ...
user avatar
  • 183
4 votes
0 answers
104 views

Why are most commonly used activation functions continuous?

I have come to notice that the most commonly used activation functions are continuous. Is there any specific reason behind this? Results such as this paper have worked on training networks with ...
user avatar
  • 505
4 votes
0 answers
75 views

When do two identical neural networks have uncorrelated errors?

In Chapter 9, section 9.1.6, Raul Rojas describes how committees of networks can reduce the prediction error by training N identical neural networks and averaging the results. If $f_i$ are the ...
user avatar
4 votes
0 answers
53 views

When is using weight regularization bad?

Regularization of weights (e.g. L1 or L2) keeps them small and standardized, which can help reduce data overfitting. From this article, regularization sounds favorable in many cases, but is it always ...
user avatar
  • 673
4 votes
0 answers
125 views

Has the logistic map ever been used as an activation function?

I find the logistic map absolutely fascinating. Both in itself (because I love fractal) and because it is observed in nature (see: https://www.youtube.com/watch?v=ovJcsL7vyrk). I'm wondering if anyone ...
user avatar
  • 163
4 votes
0 answers
35 views

How do weights changes handles during back-propagation when there are unknown labels

I have a question about how weights are updated during back-propagation for some of my samples that have unknown labels (please note, unknown, not missing). The reason they are unknown is because this ...
user avatar
4 votes
0 answers
60 views

Is it a good idea to first train a spiking neural network and then convert it to a conventional neural network?

In many papers about artificial spiking neural networks (SNNs), the performance of them is not up to par with traditional ANNs. I have read how some people have converted ANNs to SNNs using various ...
user avatar
  • 309
4 votes
0 answers
106 views

Is there a mathematical formula that describes the learning curve in neural networks?

In training a neural network, you often see the curve showing how fast the neural network is getting better. It usually grows very fast then slows down to almost horizontal. Is there a mathematical ...
user avatar
  • 2,084
4 votes
1 answer
433 views

What are the differences between Bytenet and Wavenet?

I recently read Bytenet and Wavenet and I was curious why the first model is not as popular as the second. From my understanding, Bytenet can be seen as a seq2seq model where the encoder and the ...
user avatar
  • 1,098
4 votes
0 answers
103 views

Why isn't the evolutionary Turing machine mainstream?

Given that recurrent neural networks are equivalent to a Turing machine, then why isn't the evolutionary Turing machine, e.g. described in the paper Evolution of evolution: Self-constructing ...
user avatar
  • 331
4 votes
0 answers
435 views

What is the difference between GAT and GaAN?

I was looking at two papers Graph Attention Networks (GAT) by Petar Veličković and GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs by Jiani Zhang. I'm trying to ...
user avatar
  • 1,098
4 votes
0 answers
107 views

What are stable ways of doing online machine learning?

I am trying to deploy a machine learning solution online into an application for a client. One thing they requested is that the solution must be able to learn online because the problem may be non-...
user avatar
  • 403
4 votes
0 answers
98 views

How do the relative number of cells between neighboring stacked LSTM layers affect the network's behavior?

It seems that stacking LSTM layers can be beneficial for some problem settings in order to learn higher levels of abstraction of temporal relationships in the data. There is already some discussion on ...
user avatar
4 votes
0 answers
43 views

Can there be applications of byzantine neural networks on quantum computers?

This question came after I connected 2 pieces of information : I recently listened to The Byzantine Generals’ Problem, Poisoning, and Distributed Machine Learning with El Mahdi El Mhamdi (Beneficial ...
user avatar
4 votes
0 answers
163 views

What characteristics make it difficult for a Neural Network to approximate a function?

What are the characteristics which make a function difficult for the Neural Network to approximate? Intuitively, one might think uneven functions might be difficult to approximate, but uneven ...
user avatar
4 votes
0 answers
1k views

Which other loss functions for hierarchical multi-label classification could I use?

I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels like multilayer perceptron (MLP) branch ...
user avatar
  • 133
4 votes
2 answers
2k views

How to perform gradient checking in a neural network with batch normalization?

I have implemented a neural network (NN) using python and numpy only for learning purposes. I have already coded learning rate, momentum, and L1/L2 regularization and checked the implementation with ...
user avatar
4 votes
4 answers
771 views

Use Machine/Deep Learning to Guess a String

I want to be able to input a block of text and then have it guess a string within a predefined range (i.e. a string that starts with three letters and ends with five numbers like "XXX12345", etc). ...
user avatar
4 votes
0 answers
3k views

Is this a good way to represent Connect 4 to a Neural Network?

I'm attempting to make a bot for the Connect 4 competition on http://riddles.io My bot isn't horrible, like it's getting up the ladder, but it cannot compete with the winning bots. I'm using a ...
user avatar
4 votes
0 answers
897 views

Can neural networks be used to study (elementary) number theoretic problems?

Can neural networks be used to study (elementary) number theoretic problems? What are examples where this has been done in the past? Or is there on the contrary an understanding that neural networks ...
user avatar
3 votes
0 answers
112 views

What is a neural network compatibility function?

Typically, a neural network parameterized by weights $\mathbf{W}$ is a function from an input $x$ to an output $y$. The network has an associated compatibility function $\Psi(y; x, \mathbf{W}) \...
user avatar
  • 179
3 votes
0 answers
72 views

Are there neural networks with (hard) constraints on the weights?

I don't know too much about Deep Learning, so my question might be silly. However, I was wondering whether there are NN architectures with some hard constraints on the weights of some layers. For ...
user avatar
  • 163
3 votes
0 answers
72 views

Which algorithms are used to locate objects in a 3d space?

I can see mobile apps that can locate a 3D object on a surface with a mobile camera and you can turn around that object. What is the name of the algorithm(s) that is used for that purpose? Or, is ...
user avatar
  • 247
3 votes
0 answers
53 views

How are partial derivatives calculated in a computational graph?

I am trying to understand how are partial derivatives calculated in a computational graph. I understand reasoning behind computational graphs and I am bold enough to say I understand how they work, at ...
user avatar
  • 131
3 votes
0 answers
57 views

How does the paper implement NEAT without a global set tracking Innovations?

I have been reading this paper on NEAT and trying to implement the algorithm in C#. For the most part, I understand everything in the paper however, there are 2 things I don't understand that confuse ...
user avatar
3 votes
0 answers
189 views

Loss function to minimize the distance between sets

Are there references or links to examples about loss functions "Distance Metrics" which could be used to minimize the distance between two sets for a neural network. More precisely, this ...
user avatar
  • 131
3 votes
0 answers
162 views

How do I implement the cross-entropy-method for a RL environment with a continuous action space?

I found many tutorials and posts on how to solve RL environments with discrete action spaces using the cross entropy method (e.g., in this blog post for the OpenAI Gym frozen lake environment). ...
user avatar
  • 143
3 votes
1 answer
139 views

What is asymmetric relaxation backpropagation?

In Chapter 8, section 8.5.2, Raul Rojas describes how the weights for a layer of a neural network can be calculated using a pseudoinverse of the sigmoid function in the nodes, he explains this is an ...
user avatar
3 votes
0 answers
73 views

Image classification - Need method to classify "unknown" objects as "trash" (3D objects)

We have an image classifier that was built using CNN with faster R-CNN and Yolov5. It is designated to run on 3D objects. All of those objects have similar "features" structure, but the ...
user avatar
3 votes
0 answers
51 views

How efficient is SCAWI weight initialization method?

I'm currently in the middle of a project (for my thesis) constructing a deep neural network. Since I'm still in the research part, I'm trying to find various ways and techniques to initialize weights. ...
user avatar
  • 41
3 votes
0 answers
56 views

How does backpropagation work in LSTMs?

After reading a lot of articles (for instance, this one Understanding LSTM Networks), I know that the long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture used in ...
user avatar
  • 1,193
3 votes
0 answers
97 views

Understanding the TensorFlow implementation of the policy gradient method

I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow. I think I got almost everything. The only thing that still bothers me is the loss function ...
user avatar
  • 31
3 votes
0 answers
192 views

Understanding the results of "Visualizing and Understanding Convolutional Networks"

I am trying to understand the results of the paper Visualizing and Understanding Convolutional Networks, in particular the following image: What are these 3x3 blocks and their 9 cells representing? ...
user avatar

1
2 3 4 5
16