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.

651 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
82 views

Vector normalization by a neural network

I'm wondering if there is a NN that can achieve the following task: Output a unit vector that is parallel to the input vector. i.e., input a vector $\mathbf{v}\in\mathbb{R}^d$, output $\mathbf{v}/\|\...
3
votes
1answer
87 views

What sort of Neural Network is best suited to predicting a future purchase?

I have previously implemented a Neural Network with Back-Propagation that was able to learn Tic-tac-toe and could go pretty well at Connect-4. Now I'm trying to do a NN that can make a prediction. ...
3
votes
0answers
24 views

Handwritten digits recognition during the process of writing

I know how to train a NN for recognizing handwritten digits (e.g. using the MNIST database). I'm wondering how to accomplish the same "online", which is during the process of writing e.g. I'm writing ...
3
votes
0answers
52 views

Feasibility of using machine learning to obtain self-consistent solutions

I am a physicist and I don't have much background on machine learning or deep learning except taking a couple of courses on statistics. In physics, we often simulate a model by means of two-way ...
3
votes
0answers
72 views

Does Retina-net's focal loss accomplish its goal?

Taking out the weighting factor we can define focal loss as $$FL(p) = -(1-p)^\gamma log(p) $$ Where $p$ is the target probability. The idea being that single stage object detectors have a huge ...
3
votes
0answers
61 views

Designing state representation for board game

I am trying to write self-play RL (NN + MCTS http://web.stanford.edu/~surag/posts/alphazero.html) to "solve" a board game. However, I got stuck in designing boardgame same (input layer for NN). 1) ...
3
votes
0answers
76 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-...
3
votes
0answers
28 views

How do we ensure that training GANs will fall in the desirable Nash equilibrium?

One Nash equilibrium of every GANs model has is when the generator creates perfect samples indistinguishable from the training data and the discriminator just output 1 with probability 1/2. And I ...
3
votes
0answers
30 views

Models of reward (possibly mimicking dopamine) in artificial neural networks?

How one can model physiological reward mechanisms occuring in the brain using artificial neural networks? E.g. are there efforts to use the notion of dopamine or similar substances in the artificial ...
3
votes
0answers
35 views

Is there any formal test for linear separability of 2-class data?

SVM is designed for two-class classification problem. If the data is not linear-separable, a kernel function is used. I want to know if there is exists any method that will indicate if the data is ...
3
votes
0answers
63 views

Is there any GUI for per-neuron editing

I couldn't find GUI for precise "artificial neural-network alike" structures, which could supports neuron naming, synapse naming, import of external functions or code fragments and debugging. It would ...
3
votes
0answers
88 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 ...
3
votes
0answers
28 views

Batch PTA stopping condition

I am reviewing my Neural Network lectures and I have a doubt: My book's (Haykin) batch PTA describes a cost function which is defined over the set of the misclassified inputs. I have always been ...
3
votes
0answers
50 views

Using a “is_padding” attribute in your padding instead of simply zero vectors

Typical Feed Forward Neural Networks require a fixed sized input and output. So when you have variable sized input, it seems to be common practice to pad the input with zero vectors. Why does it not ...
3
votes
0answers
336 views

How to encode Azul game state as NN input

Question to NN practicioners. I'd like to encode Azul board game state as an input to NN, let's focus on 2-player variant for a while. There are 5 round "Factories" on the table (7 on picture, ignore ...
3
votes
0answers
82 views

Variable sized input-Multi Label Classification with Neural Network

I have a data input vector ( No Image classification) which size varys from 2 to 7 entrys. Every one of them belongs to a class Out of 7. So I have a variable Input size and a variable Output size. ...
3
votes
0answers
39 views

How do we calculate the hidden units values in a (restricted) Boltzmann machine?

Now, Boltzmann machines are energy-based undirected networks, meaning there are no forward computations. Instead, for each input configuration $x$, a scalar energy is calculated to asses this ...
3
votes
0answers
161 views

What is the relation between the definition of learnability of Vapnik and Gold and learnability of neural networks?

Gold showed that a language can be learned only if it contains a finite set of sentences. We know that deep neural networks can implement any function. Does this contradict the Gold's result? What ...
3
votes
0answers
166 views

Training RNN's on text: Can you use an ASCII encoding just as well as a one-hot character encoding?

I've mostly seen (e.g. in The Unreasonable Effectiveness of Recurrent Neural Networks) that when training RNN on text for something like language modeling, the text is usually featurized character-by-...
3
votes
0answers
127 views

How can I calculate the number of matrix additions, multiplications and divisions in AlexNet?

I'm a first-year student in machine learning and I really recently started to immerse myself. I need to calculate number of: matrix additions matrix multiplications matrix divisions which are ...
3
votes
0answers
95 views

How is the distribution of the state related to the distribution of the units in Boltzmann machines?

I'm trying to understand Boltzmann machines. Tutorials explain it with two formulas. Logistic function for the probability of single units: $$p(unit=1)=\frac{1}{1+e^{-\sum_{x}wx } }$$ and, when the ...
3
votes
2answers
92 views

What is the advantage of using cross entropy loss & softmax?

I am trying to do the standard MNIST dataset image recognition test with a standard feed forward NN, but my network failed pretty badly. Now I have debugged it quite a lot and found & fixed some ...
3
votes
1answer
241 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 ...
2
votes
0answers
17 views

Understanding neural network achitectures in policy gradient reinforcement learning for continuous state and action space

I am trying to train a neural network using reinforcement learning / policy gradient methods. The states, i.e. the inputs, as well as the actions I am trying to sample are vectors with each element ...
2
votes
0answers
45 views

Why are “Transformers” called this way?

What is the reason behind the name "Transformers", for Multi Head Self-Attention-based neural networks from Attention is All You Need? I have been googling this question for a long time, and ...
2
votes
0answers
22 views

What is the appropriate way of passing a list of integers that represents the environment to a neural network's dense layer?

I'm training an RL agent using the DQN algorithm to do a specific task. The environment is represented by a list of $10$ integer numbers from $0$ to $20$. An example would be $[5, 15, 8, 8, 0, \dots]$....
2
votes
0answers
52 views

Why should the weight updates be proportional to input?

I'm reading the book Grokking Deep Learning. Regarding weight updates during training, it has the following code and explanation: ...
2
votes
0answers
21 views

how to handle highly imbalanced multilabel classification?

I am working on a multilabel classification in which I am having 206 labels. When I saw the percentage of the number of 1's in each label they are way less than 0.1% for each label. The maximum ...
2
votes
0answers
35 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. ...
2
votes
1answer
43 views

Comparing a large/general CNN to a smaller more specialized one?

I am still somewhat a novice in the ML world, but I had a strange idea about CNNs and wanted to ask if this would be a valid way to check the robustness of a general CNN that classifies certain images....
2
votes
1answer
45 views

Is batch learning with gradient descent equivalent to “rehearsal” in incremental learning?

I am learning about incremental learning and read that rehearsal learning is retraining with old data. In essence, isn't this the exact same thing as batch learning (with stochastic gradient descent)? ...
2
votes
0answers
29 views

Handling a Large Discrete Action Space in Deep Q Learning

I am attempting to solve a timetabling problem using deep Q learning. It could be thought of as a resource allocation problem to obtain some certificate of 'optimality'. However, how to define and ...
2
votes
1answer
78 views

What is the weight matrix in self-attention?

I've been looking into self-attention lately, and in the articles that I've been seeing, they all talk about "weights" in attention. My understanding is that the weights in self-attention ...
2
votes
0answers
69 views

Doing backpropagation in an Tensorflow.js Neural Network

I have a neural network (which I am making from scratch). In order to make the neural network "learn" I need to conduct back-propagation. Using the code at the below how would I conduct back-...
2
votes
1answer
40 views

How do RNN's for sentiment classification deal with different sentence lengths?

I have been doing a course which teaches you about Deep Neural Networks, during one of the exercises I was made to make an RNN for sentiment classification which I did, but I did not understand how an ...
2
votes
0answers
58 views

How can I find a specific word in an audio file?

I'm trying to train and use a neural network to detect a specific word in an audio file. The input of the neural network is an audio of 2-3 seconds duration, and the neural network must determine ...
2
votes
0answers
54 views

What is the reason for mode collapse in GAN as opposed to WGAN?

In this article I am reading: $D_{KL}$ gives us inifity when two distributions are disjoint. The value of $D_{JS}$ has sudden jump, not differentiable at $\theta=0$. Only Wasserstein metric provides ...
2
votes
0answers
47 views

What is meant by “arranging the final features of CNN in a grid” and how to do it?

In the paper What You Get Is What You See: A Visual Markup Decompiler, the authors have proposed a method to extract the features from the CNN and then arrange those extracted features in a grid to ...
2
votes
0answers
40 views

Why does learning rate reduce train-test generalization gap?

In this blog post: http://www.argmin.net/2016/04/18/bottoming-out/ Prof Recht shows two plots: He says one of the reasons the plot below has a lower train-test gap is because that model was trained ...
2
votes
0answers
42 views

Inaccurate masks with Mask-RCNN: Stairs effect and sudden stops

I've been using matterport's Mask R-CNN to train on a custom dataset. However, there seem to be some parameters that i failed to correctly define because on practically all of the images, the bottom ...
2
votes
0answers
69 views

Should batch normalisation be applied before or after ReLU?

I know that there has been some discussion about this (e.g. here and here), but I can't seem to find consensus. The crucial thing that I haven't seen mentioned in these discussions is that applying ...
2
votes
0answers
40 views

Can you use transformer models to do autocomplete tasks?

I've researched online and seen many papers on the use of RNNs (like LSTMs or GRUs) to autocomplete for, say, a search engine, character by character. Which makes sense since it inherently predicts ...
2
votes
0answers
30 views

Why is ANFIS important in general?

I am actually working with the iris dataset from sklearn and try to understand the ANFIS-Package for python. But that does not really matter! I have a more general question. During thinking about ...
2
votes
0answers
22 views

What is the difference between fuzzy neural networks and adaptive neuro fuzzy inference systems?

I have, like you see, just a general question about the combination of fuzziness and neural networks. I understood it as follows Fuzzy neural networks as a hybrid system: the neural network helps me ...
2
votes
0answers
48 views

How to calculate the data noise variance for a prediction interval?

I have a neural network that connects $N$ input variables to $M$ output variables (qoi). By default, neural networks just give out point estimations. Now, I want to plot some of the quantity of ...
2
votes
0answers
50 views

What work has been done with Poisson-style regression via neural networks with exponential activation function?

The first neural net I wrote was a classifier. After that, I learned that neural nets can be used for regression tasks, even quantile regression. It has become clear to me that the usual games with ...
2
votes
0answers
28 views

Merge two different CNN models into one

I have 2 different models with each model doing a separate function and have been trained with different weights. Is there any way I can merge these two models to get a single model. If it can be ...
2
votes
1answer
72 views

Can you explain me this CNN architecture?

I am starting to get my head around convolutional neural networks, and I have been working with the CIFAR-10 dataset and some research papers that used it. In one of these papers, they mention a ...
2
votes
0answers
66 views

Which activation functions should I use for polynomial regression?

I am a beginner in machine learning and neural networks. I have only used neural networks for classification problems. My aim is to modify it so that it can work for polynomial regression as well. In ...
2
votes
0answers
129 views

How to select good inputs and fitness function to achive good results with NEAT for Icy Tower bot

I'm trying to make a bot to the famous "Icy Tower" game. I rebuilt the game using pygame and I'm trying to build the bot using Python-NEAT. Every generation a population of 70 characters ...

1
2
3 4 5
14