Questions tagged [neural-network]

Artificial neural networks (ANN), are composed of 'neurons' - programming constructs that mimic the properties of biological neurons. A set of weighted connections between the neurons allows information to propagate through the network to solve artificial intelligence problems without the network designer having had a model of a real system.

Filter by
Sorted by
Tagged with
0
votes
0answers
10 views

Non-constant/variable input data matrix length

Which neural network type could be used for input data matrix M (presented in the picture), where k dimension is constant, and n dimension is variable? A sequence of rows in n dimension does not have ...
0
votes
1answer
24 views

How to pass variable length data as feature to a neural network?

I am working on building a model to classify the type of touch the user makes (Long Press, Left Swipe, Right swipe, and so on). I have data with features that characterize the user's touch, like ...
2
votes
0answers
22 views

Building machine learning models whilst penalizing them for complexity

I come from a predictive modelling background, where it's common to use differential equations to model physical or chemical or biological processes. Commonly to avoid overfitting people use AIC and ...
0
votes
1answer
38 views

Custom layer for Simple Exponential Smoothing

I am writing a test custom layer which implements the Simple Exponential Smoothing algorithm. The problem: when I train it, the alpha (smoothing) coefficient always converges to value 1. This means ...
1
vote
0answers
41 views

Predicting probabilities in Neural Networks

I have 1000 number of inputs in a sample each ranging between 0-1 as shown: ...
0
votes
1answer
22 views

How to use new dataset on a pretrained neural network model?

I have built a dataset that I would like to pass to a pretrained model in oder to perform some predictions. I am looking for some steps/processes to guide me in this. Should I fine tune?If so what ...
0
votes
0answers
16 views

Model comparison: how to explain worse (lower) dice scores but better (lower) Hausdorff distances

I have two segmentation models (U-Net-like architectures): an original model, and an experimental model. I use the dice score and 95% Hausdorff distance to evaluate their performance. Using the first ...
0
votes
0answers
22 views

Inverting a matrix using a convolutional neural network

Just for a fun exercise, I am trying to invert a matrix, say size 28x28 (or even 5x5) with a neural network. The way I approached this (quite naively) is as follows: I built a fully convolutional ...
1
vote
0answers
18 views

Text generation with deep neural network?

For my master's project, I have to build a deep learning model for text generation: the model learns on a set of sentences, then it generates new sentences based on those from which it learned. I ...
0
votes
0answers
14 views

How to modify this training function in order to print the aggregation of models

I have 3 VGG: VGGA, VGGB and VGG*, trained with the following training function: ...
-1
votes
1answer
31 views

Max-pooling layer

I started to learn about NN and I am following lecture CS231n. I wanted to know if we have input that is 5x5 and we do max pooling with filter that is 2x2. Is this possible? I tried in python and I ...
0
votes
0answers
11 views

Which kind of technique is used for classifying a graph datastructure?

I have a 3D surface from which I extract certain spatial parameters like extremas and their locations (a.k.a coordinates), which then I convert into a bipartite graph with distance between them as ...
0
votes
0answers
10 views

Attention mechanism: Why apply multiple different transformations to obtain query, key, value

I have two questions about the structure of attention modules: Since I work with imagery I will be talking about using convolutions on feature maps in order to obtain attention maps. If we have a set ...
1
vote
0answers
12 views

Unable to train neural network for prediction

My data consists of a time series of values $\pm1$ and I am trying to apply a RBF NN as a function approximator. Essentially, the NN will take as input one data sample and predict the next sample (...
0
votes
1answer
26 views

Why is l1 regularization rarely used comparing to l2 regularization in Deep Learning?

l1 regularization increases sparsity, so unimportant weights are decreased closer to 0. In Deep Learning models, the input usually consists of thousands or millions of features/pixels, and the network ...
3
votes
1answer
119 views

Train-test split and augmentation strategy for small dataset for video classification problem

I have a small data set of videos of approximately 100 videos for each class for a binary classification problem. This results in a total of 200 videos. I am applying two types of augmentations on the ...
0
votes
1answer
32 views

How Are Kernel Weights Trained in 1-D CNN's with Multi-dimensional Input?

I have far from a perfect understanding of how 1-D convolution neural networks learn, but I think I understand how the kernel operates on 1-D input data. How does 1-D convolution work with multi-...
0
votes
0answers
9 views

Why are the values of my Y predicted the same and R-Squared Negative in SupervisedDBNRegression, Neural Networks

My model is not outputting the results I expected. I don't quite know my way around ANN. After learning how to use SupervisedDBNClassification from https://github.com/albertbup/deep-belief-network I ...
0
votes
0answers
21 views

How to calculate Efficientnet's compound scaling

I would like to use compound scaling to tweak my own model, but I am confused about how to utilize the $d=\alpha^\phi,w=\beta^\phi,r=\gamma^\phi$ in compound scaling and how to compute the specified ...
1
vote
1answer
41 views

Autoencoder not learning walk forward image transformation

I have a series of 15 frames with (60 rows x 50 columns). Over the course of those 15 frames, the moon moves from the top left to the bottom right. Data = https://github.com/aiqc/AIQC/tree/main/...
0
votes
1answer
14 views

Image autoencoder w/o thousands of dense neurons? prevent large model

I am trying to get around producing large models. If my desired output is a 120x100 image, then do I need a 120*100=12,000 neuron dense layer preceding it? ...
2
votes
1answer
85 views

Is it possible to use a Neural Network to interpolate data?

I am completely new to Artificial intelligence and Neural Networks. I am currently working on a plasma physics simulation project which requires a very high resolution data set. We currently have the ...
0
votes
2answers
44 views

Different results after each training of Keras/TensorFlow model

I have the following Keras/TensorFlow code: ...
0
votes
0answers
31 views

Regression trees for extrapolating time series data

This is a regression problem that involves predicting the price of e.g. aluminum, oil, strawberries. I have hourly and half hourly data for the weather and up to 10 different socioeconomic variables (...
0
votes
1answer
77 views

time series anomaly detection

I want to ask for time series anomaly detection we can apply tnn on multiple features or not? I used transformer for sentiment analysis where I have to provide a sentence and it predicts its output as ...
0
votes
1answer
21 views

Extra feature on test set

Suppose I convert categorical data into dummy variables with get_dummies and I get these columns in the training dataset: x_A x_B x_C 0 1 0 0 0 1 1 1 0 But in ...
1
vote
1answer
23 views

What methods are there for predicting a signal?

I have a large dataset of signals (composed of time series). All time series describe the same process, but each series has a different duration (number of points). Based on these time series, I want ...
0
votes
1answer
19 views

Can anyone interpret this Recurrent Network Encoder-Decoder question?

I'm trying to earn some extra credit, so the professor won't elaborate further on what's being asked in this question: The dataset that we're given is a line-by-line file of protein sequences (...
0
votes
0answers
8 views

regressor column might have different length

I'm attempting to use a neural network to do some time series forecasting. The goal is to forecast price and I have a fewer regressors to help along like fuel prices and number of sick people among ...
1
vote
0answers
18 views

Question about a reading

So I'm trying to do multivariate time series prediction and a google search led me to this article: https://bookdown.org/singh_pratap_tejendra/intro_time_series_r/neural-networks-in-time-series-...
0
votes
1answer
239 views

Validation Accuracy Not Changing

As the title states, my validation accuracy isn't changing when I try to train my model. I've built an NVIDIA model using tensorflow.keras in python. I have absolutely no idea what's causing the issue....
0
votes
0answers
14 views

times series prediction with several regressors( using R)

Absolute beginner here. I'm trying to use a neural network to predict price of a product that's being shipped while using temperature, deaths during a pandemic, rain volume, and a column of 0 and 1's (...
1
vote
1answer
43 views

Is there a general rule for how many layers a NN should be based on the number of inputs?

I have a neural network that takes 1935 inputs, so I'm wondering if there is a general rule for how many layers the network should be. Should the number of neurons be descending by a certain amount?
0
votes
3answers
67 views

Which neural network is better?

MNIST dataset with 60 000 training samples and 10 000 test samples. Neural network #1. Accuracy on the training set: 99.53%. Accuracy on the test set: 99.31%. Neural network #2. Accuracy on the ...
1
vote
1answer
27 views

Examples of uses of neural networks where you can rigorously define desired properties of the solution?

Neural networks are often used to solve problems where we can't rigorously define what properties the desired solution should have, e.g. you can't define what a "picture of a cat" is and so ...
1
vote
1answer
46 views

Force neural network to only product positive values

I have a custom neural network that has been written from scratch in python and also a dataset where negative target/response values are impossible, however my model sometimes produces negatives ...
1
vote
0answers
38 views

Which Neural Network or Gradient Boosting framework is the simplest for Custom Loss Functions?

I need to implement a custom loss function. The function is relatively simple: $$-\sum \limits_{i=1}^m [O_{1,i} \cdot y_i-1] \ \cdot \ \operatorname{ReLu}(O_{1,i} \cdot \hat{y_i} - 1)$$ With $O$ being ...
3
votes
3answers
174 views

Retraining with the same data returns different accuracies

I am using TensorFlow to train a simple neural network (3 sequential dense layers). The problem is that the accuracy changes a lot every time I retrain it from scratch. I understand that, since the ...
0
votes
1answer
308 views

Combining heterogeneous numerical and text features

We want to solve a regression problem of the form "given two objects $x$ and $y$, predict their score (think about it as a similarity) $w(x,y)$". We have 2 types of features: For each ...
1
vote
0answers
22 views

Neural network weight initialization

I was working on recreating the Convolutional Neural Network Le-Net 5. I was getting around 96.5% accuracy on the training set. This was not near the 99.2% the network was meant to be operating at. ...
0
votes
0answers
25 views

Recurrent models for asynchronous / mixed frequency time series

What are some of the RNN/LSTM models for handling mixed frequency/asynchronous time series data, such as macroeconomics, financial, precipitation, etc.? So far I have found phased lstm from a similar ...
3
votes
0answers
26 views

How to train a neural network where computing the loss requires multiple object values?

I want to train a function that given metadata about an image produces hyper-parameters for an algorithm which operates on the image. My understanding is (please forgive me I'm a novice here) a neural ...
0
votes
0answers
12 views

"Saliency map" of perceptron?

I am using keras currently, and I want to see which inputs the model is "looking at". It would be like a saliency map, but my model is a simple two-layered perceptron for classification, so ...
0
votes
1answer
18 views

Do grouped convolutions actually improve learning?

My Understanding of Grouped Convolutions Let say we have some data with the dimensions [100,100,32] (lets ignore batch size and assume channels last) and we want to ...
1
vote
1answer
58 views

Vanishing gradient problem even after existence of ReLu function?

Let's say I have a deep neural network with 50 hidden layers and at each neuron of hidden layer the ReLu activation function is used. My question is Is it possible for vanishing gradient problem to ...
0
votes
1answer
50 views

Early stopping with class weights / sample weights

I'm performing a classification of imbalanced multiclass data using a Neural Network in the TensorFlow framework. Therefore, I'm applying class weights. I would like to apply early stopping to reduce ...
2
votes
2answers
86 views

KL-divergence to compare ML models

Let us say we have to neural network architectures, A and B and we train $x$ times each of them. Based on the $x$ retrainings, we can calculate $x$ prediction errors for each model, and plot its ...
0
votes
0answers
35 views

text classification - does number of features matters?

I'm working on a multi-class text classification project that aims to assign a "new bug" to his "final group assignee" To do that I was able to extract ~17000 samples and divided ...
0
votes
1answer
21 views

Question regarding training data in word2vec - skip-gram

I have a very simple question regarding the training data in word2vec. In the skip-gram implementation, the training data (if I understand it correctly) is generated as pairs of words like it's shown ...
0
votes
0answers
25 views

Don't understand Channels in Covolutional Layers [duplicate]

I'm struggling to understand the concept of 'Channels'. What does a channel mean in the context of an image. I understand that a grey scale image only has 1 channel, and a RGB has 3, but then I see ...

1 2 3
4
5
79