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
8 views

Train a model when input can contain a smaller options output with the correct output

I have service order lines to charge customers, each line needs to be set to an actual product. If the customer had only one product, so all lines are set to that product. But, if the there are many ...
1
vote
0answers
12 views

Modeling events with an intermediate stage

For a lot of prediction problems, there's an intermediate stage which must occur for the target event to occur. For example, to graduate from college, one must first be accepted. For an internet ad to ...
0
votes
0answers
8 views

Tune SIRD Model Parameters using a Neural Network

I want to use a neural network to predict the number of new cases of COVID-19. For the same, I have decided to use an SIRD (Susceptible-Infected-Recovered-Deceased) Model, which is parameterized by ...
0
votes
0answers
7 views

Neural Network Architecture for Mixed Frequency Data

I have accelerometer and gyroscope data generated at 119 Hz. I have magnetometer data generated at 20 Hz. I would like to build 2D-CNN based on this data. One solution is that decreasing the freq. of ...
1
vote
0answers
17 views

How should I think when I want to compare mu and sigma for different images in VAE?

I'm searching for a way to compare mu and sigma values of the encoder network's output of variational autoencoders. In detail, imagine I trained my VAE on the MNIST digits dataset using the official ...
1
vote
0answers
23 views

What kind of ML approach is more suitable for detecting event related signal changes?

First of all please if there is a better way to phrase my question let me know. It will help with search. ( This part : "detecting event related signal changes" ) Here you can see 4 black ...
1
vote
0answers
21 views

How to predict data from sequence of sequences of variable size?

input data ...
1
vote
0answers
22 views

Which model is used for document extraction (CamScanner, Microsoft Lens etc)

I want to start a small project where I'd create a model(s) that would extract document from a picture and rescale it, something like CamScanner or Microsoft Lens apps do. I've gathered a small ...
0
votes
1answer
23 views

Not sure how I can get class labels from Neural Network predictions. Would this be an acceptable alternative to the old method

I am currently working with a dataset that has over 300 variables and a target variable with 10 different classes. My goal is to use said variables and produce a prediction for the target variable. ...
1
vote
1answer
46 views

SMOTE for multi-class balance changes the shape of my dataset

So I have a dataset of shape (430,17), that consists of 13 classes (imbalanced) and 17 features. The end goal is to create a NN which btw works when I import the imblanced dataset, however when i try ...
0
votes
0answers
10 views

Multivariant LSTM with labels per sequence

I'm very new to RNN and the ML space in general. Please excuse my lack of vocabulary and domain knowledge. I'm trying to classify requests as to whether if it's spam. The labels are per-user-based. ...
0
votes
0answers
12 views

How to create 2D visualization of loss for weights in PyTorch model?

I am looking to create visualization of this type for PyTorch ResNet model to see trajectories of optimization. Could anyone provide me code sample for that?
0
votes
0answers
15 views

One to many LSTM vs feed forward

Let us say I have three output variables I would like to predict $y_1, y_2, y_3$ where $y_1$ could have an high correlation with $y_2$ and $y_2$ with $y_3$. We have one input variable $x_1$. How does ...
0
votes
2answers
29 views

Activation and Loss Function not chosen correctly when use Neural Network

I have three classes for my text dataset before. These are my classes: 0 = Cat 1 = Not Both 2 = Dog Then I use this code: ...
0
votes
0answers
6 views

Implement NestedCV into Neural Networks

I have a regression task for which I am using ML models. My input features are 64. I implement NestedCV to get best ML models and hyperparameters. I have recently learned Neural Networks and want to ...
0
votes
0answers
7 views

How to overcome extremely variable model performance?

I am training an LSTM and the model performance seems to range from near perfect to dreadful by visual inspection of predicted values - it seems by random initialisation simply retraining the model ...
0
votes
1answer
18 views

Connection between GANs and adversarial learning

Is there a connection between: "Adversarial Learning" (AL) and "Generative Adversarial Networks" (GANs)? Is it valid to say that GANs employ AL?
4
votes
2answers
221 views

How to determine if my data split is appropriate for my data size?

I currently have a model that has a pretty large dataset (50ishMB) and was performing pretty well with a 80:20 split. However, when I tried changing it up to a 50:50 split, the model performed 28% ...
0
votes
0answers
35 views

Reinforcement learning policy gradient derivation

I was reading a document about Reinforcement Learning policy gradient http://web.stanford.edu/class/cs234/CS234Win2019/slides/lnotes8.pdf when I encountered this expression $ \nabla_{\theta} \mathbb{...
1
vote
1answer
25 views

Help starting ML project in pythin(novice)

I am starting a machine learning project (for fun!), but I am not sure where to start from... I am fairly new to ML so any hints are appreciated. I have a relatively large data-set where each input is ...
1
vote
1answer
27 views

Exact Predictions for Regression problems in Machine Learning

I am working on shipment days delivery problem , where i want to predict shipment days (continuous variable target) I have tries both Neural Network and Random Forest regressors ,i got very low error ...
0
votes
0answers
14 views

Custom layers in Keras -- custom weights

I am trying to understand how to build custom layers in Keras and I went through a couple examples: here and here. The syntax is, of course, similar, but in non of the cases it is addressed why ...
1
vote
0answers
18 views

Comparing machine learning algorithms on features selected by a neural network

I'm reading a paper where they use a neural network to select 9 features from tabular input data with 20 features. And then, this is what feels weird to me, they run several machine learning ...
0
votes
0answers
12 views

Best Javascript Modules for creating Neural Networks

After checking out this similar post for python: Best python library for neural networks, I was curious if the community had recommendations for JavaScipt modules for creating neural networks. I am ...
0
votes
0answers
22 views

How to use Mean squared error as the loss function on CIFAR 10

I have tried using MSE on Resnet50 for the CIFAR10, no matter how I change the output layer like dense(1, relu)/dense(1, sigmoid). The model failed to converge in the training. What is the correct way ...
0
votes
0answers
26 views

Imbalanced NLP text classification

I'm trying to solve a multi-class text classification task with 3 classes. I have an initial pretty balanced but small dataset. When I start to mine additional data I can't always find a lot of new ...
1
vote
1answer
44 views

Does validation_split in tf.keras.preprocessing.image_dataset_from_directory result in Data Leakage?

For a binary image classification problem (CNN using tf.keras). My image data is separated into folders (train, validation, test) each with subfolders for two balanced classes. Borrowing code from ...
1
vote
1answer
17 views

Questions of understanding - Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

I'm currently analysing the paper Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation (Post, Vilar 2018): https://arxiv.org/abs/1804.06609 I have ...
0
votes
0answers
24 views

Siamese netwroks - how to choose loss function?

I have read several articles about siamese netwroks, and I understand that there are 3 different types of loss functions: ...
0
votes
3answers
19 views

Creating numeric word representation of input sentences resulting in MemoryError

I am trying to use CountVectorizer to obtain word numerical word representation of data which is essentialy list of 160000 English sentences: ...
1
vote
1answer
34 views

Points to remember when embarking on an organization-wide turn to AI solutions

In our organization, we are currently in the phase of building up team, skills to automate and implement AI based solutions. So, we are very early in this AI journey. Right now, we are also working on ...
0
votes
0answers
19 views

How can I reduce overfitting in CNN model for image classification, even after data augmentation?

its my first time posting here. I'm trying to build a CNN model that identifies fruits from a dataset of apples, bananas, mixed fruits, and oranges. So far, one of the things I have done to prevent ...
1
vote
0answers
29 views

Why can't a multi-layer linear neural network fit this linear function data?

I am learning to implement a neural network with gradient descent, and encountered this problem, please. Using the target function ...
0
votes
2answers
61 views

Is reinforcement learning analogous to stochastic gradient descent?

Not in a strict mathematical formulation sense but, would there be there any key overlapping principals for the two optimisation approaches? For example, how does $$\{x_i, y_i, \mathrm{grad}_i \}$$ (...
2
votes
1answer
56 views

Standardization vs min-max scaling

In the book Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow 2nd Edition by Aurélien Géron, the author quoting: Unlike min-max scaling, standardization does not bind values to a ...
0
votes
0answers
41 views

When should I use neural networks?

I am struggling with this exercise. The objective is "to build a recommendation system that predicts the next video" viewed by a user, given the data provided. So, the dataset consists in ...
0
votes
0answers
21 views

My LSTM is struck with local minima

My LSTM Accuracy is low and is the same even if I go for higher epochs. I tried varying the optimizer/changing the batch size, but it still remains the same. My data: sequence length is 300, so its ...
2
votes
0answers
14 views

Derive backpropagation for PreLU

I want to derive the back propagation functions for the Parametric Relu activation function which is defined as follows: $$ h_a(x) = \text{max}(ax, x) $$ I want to derive $ \frac{\partial L}{\partial ...
1
vote
0answers
17 views

Should I use Pad Sequence when using Word Vectors?

I have an unbalanced text data set. I want to use word vectors to embed words. When I use pad sequence? Before or after the word vector? I tried it, after the word vector I used pad sequence but my ...
0
votes
0answers
27 views

My neural net plots stop working when I add 20 and 50 neurons in the hidden layer, does anyone know what the problem is?

I just have four basic neural net plots, each one has a different number of neurons in the hidden layer. The first has 3 neurons, the second 10, the third 20, and the fourth 50. The issue is the plots ...
0
votes
0answers
10 views

Applying LSTM or Deep Neural Algorithm for Mobile sensor

I am doing a project on mobile sensor Data ,I haven't used neural networks before on this type of data The data is 20750 subsamples extracted from the 1945 collected samples provided in a single .csv ...
0
votes
1answer
59 views

What does keras.backend.clip do?

I am trying to create a custom loss function and when looking at other examples of loss functions online, I found this example: ...
1
vote
0answers
25 views

Would it make sense to have an output layer connected to other output layers in a NN?

I'm working with data that has multiple variables which could be predicted, nonetheless I need to predict just one that is directly correlated to all of the others. Would it make sense to have a NN ...
1
vote
0answers
15 views

Neural network predicting on similar inputs with many features

I am training a deep RL agent (DQN) on states with 333 components that usually are very similar between themselves. The actions predicted by the agent, which is nothing but the max operator applied to ...
1
vote
1answer
34 views

How to solve a non classification problem with multiple plausible reults?(Tensorflow)

I'm fairly new to ML and now that I digged through tutorials and documentations I wanted to create a model myself now. The problem: I am a carpenter and back then in shool we had a problem where we ...
1
vote
2answers
151 views

How to obtain vector representation of phrases using the embedding layer and do PCA with it

I am trying to understand from both a conceptual and a Python code point of view, how to represent phrases that are present in a corpus (that is used to train a neural network to classify phrases) as ...
0
votes
0answers
9 views

What is the reason of this behavior of training loss in CONV auto-encoders?

I don't get Training Loss is steady up to the 7th epochs
0
votes
0answers
7 views

Masked Autoencoder Structure

In the following structure when we use MADE due to the constrains for making masked autoencoder, it seems some inputs do not have any connection to the next layer and also there is output which does ...
0
votes
0answers
15 views

First-differencing non-stationary time series when fitting neural networks

I am trying out different types of neural networks for time-series forecasting and I have not been able to find a satisfying answer online about whether or not non-stationary series should be first-...

1
2
3 4 5
80