Questions tagged [deep-learning]

a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.

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

News articles clustering for ESG and others

Can anyone suggest method to do classify ESG categories. News contains very huge noise so doing direct clustering not working to classify the esg or not in a news. Any idea on this?
0
votes
0answers
9 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 ...
0
votes
1answer
23 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 ...
1
vote
1answer
15 views

How can I convert text data to CoNLL format?

This is the same question that I posted on stackoverflow, but I wondered stackexchange would be appropriate for this question. I would like to convert text data to CoNLL format. words.txt ...
0
votes
1answer
16 views

Predictions for classes on which the DNN was not trained yet - is that possible?

my data is of multi-class, multi-label type, and I plan to have 100 output classes in total. My input X to the model is audio data, my ...
0
votes
0answers
8 views

How to calculate Efficientnet's compound scaling

I want to use compound scaling to tweek my own model, but I'm confused of how to utilize the $d=\alpha^\phi,w=\beta^\phi,r=\gamma^\phi$ in compound scaling and how to compute the specified grid search ...
0
votes
0answers
14 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. As my input data I have a 60x50 image. As my ...
1
vote
1answer
11 views

What is the logic behind recommended normalization parameters in PyTorch?

On the PyTorch documentation for torchvision.models, it is states that images have to be loaded in a range of [0,1] and then normalized using ...
0
votes
1answer
13 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? ...
0
votes
0answers
29 views

Why it is said that cross entropy has no minimum value?

I have been reading Deep Learning book by Ian Goodfellow, et al. ,and in chapter 6 (pages 179-180), the following point is mentioned: One unusual property of the cross-entropy cost used to perform ...
0
votes
1answer
16 views

Batch normalization for multiple datasets?

I am working on a task of generating synthetic data to help the training of my model. This means that the training is performed on synthetic + real data, and tested on real data. I was told that batch ...
0
votes
0answers
9 views

can i do object detection on pretrained classification model…?

so i built a natural disaster classification model using transfer learning Renet50(tensor flow) got 98% accuracy and now instead of just classifying natural disaster lets say a cyclone appeared in ...
0
votes
1answer
25 views

ML algorithm for high dimensional time series forecasting

I'm trying to make a forecasting model for goods prices in an economy (trying to forecast inflation). Dataset: has 300 goods prices % monthly variations for last 6 years. And also added $n$ ...
0
votes
0answers
5 views

Relation between random walk, DeepWalk and Neighbour Aggregation in GNN?

What is the relation between random walk, DeepWalk and Neighbour Aggregation in GNN? Please provide compare and contrast for all these 3 pairs. Thank you.
0
votes
1answer
23 views

time series anomaly detection

I want to ask in time series anomaly detection we can apply transformer architecture on multiple features or not? I used a transformer for sentiment analysis where I have to provide a sentence and it ...
2
votes
1answer
16 views

LSTM returns the same results for different inputs

Hey everyone, I am working on a LSTM network in TensorFlow that predicts the values of the price-index of different product-categories in a month, based on those same values of the 12 months before. ...
1
vote
2answers
42 views

Combining CNNs for image classification

I would like to take the output of an intermediate layer of a CNN (layer G) and feed it to an intermediate layer of a wider CNN (layer H) to complete the inference. Challenge: The two layers G, H have ...
0
votes
1answer
28 views

Deep Learning Model to predict sum of Sequences based on flag value

I am trying to Predict Sum of the Sequence based on flag but my model is not able to converge. for each time stamp, include the first element in sum if second number is 1 in Sequence. Example ...
0
votes
0answers
8 views

How to define similarity between nodes in original graph?

While there has been a lot of talk in how to define the similarity between nodes in the embedding space, but I don't seem to come across any talking about defining the similarity between nodes in the ...
0
votes
0answers
10 views

Predicting categories from data having no targets

I have training data that just contains transaction history of a store which includes user id of the customer, the product purchased and the cost of the purchase. There are repeated transactions from ...
1
vote
0answers
17 views

Deep Learning book - trying to understand Bernoulli formulas

In the section 6.2.2.2 Sigmoid Units for Bernoulli Output Distributions of The Deep Learning Book there is a section: (z is defined as $z=w^Th+b$ and $\hat{y}=\...
0
votes
1answer
17 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 ...
0
votes
0answers
13 views

Systematically finding a CNN architecture?

I am trying to train a classifier from 25k images and 7k classes. Seems like my model overfits just after 3 epochs. I have tried to reduce the model complexity and increase the weight decay but still, ...
0
votes
1answer
25 views

How do you research and list up thinkable encoders and decoders when you build NLP models?

I'm a beginner in NLP and deep learning fields, and have stacked with the phase how research and list up available and substitutional encoders and decoders. For example, I read a thesis that ...
0
votes
1answer
28 views

Underfitting issue

I have a small datset (530 images) trained on a simple CNN called AquaSight. This is the architecture. I had an underfitting problem, 75% accuracy and 0.6 loss. How can I solve the underfitting ...
0
votes
0answers
27 views

Sensitivity analysis in time series forecasting

Given a data set consisting of features time signals $X=[x_1,\dots, x_n]$ and one target time series $y$, I would like to study the sensitivity of $y$ with each of the $x$'s. What I think: Compute ...
0
votes
0answers
12 views

Is reinforcement learning suitable for the Dial-a-Ride problem?

Is reinforcement learning suitable for this problem or will it perform poorly against classical algorithms? "The Dial-a-Ride Problem (DARP) consists of designing vehicle routes and schedules for ...
0
votes
0answers
15 views

Extracting features from bounding boxes of CornerNet

I am using the CornerNet model. I want to extract features from specific bounding boxes that have been detected. Unlike Faster RCNN,...
0
votes
1answer
36 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?
1
vote
1answer
24 views

How can the ReLU function lead to convergence?

The gradient descent algorithm is based on the fact that the gradient decreases as we move towards the optimum point. However, in the activations by the ReLU ...
0
votes
1answer
16 views

how to correct mislabeled data in training, validation and test set

In an image classification task, I know there are mislabeled data. should I remove/correct them in all training / validation / test set ? I saw this article https://arxiv.org/pdf/2103.14749.pdf but I ...
1
vote
0answers
15 views

Prediction method when the time series is not sequential?

I have multivariate time series data consisting of monthly sales of contraceptives at various delivery sites in a certain country, between January 2016 and June 2019. The data looks as follows: The ...
0
votes
0answers
11 views

Doubt with Imagedata generator

I have a total of 500 images in one class. And below are my parameters passed for image argumentation from image data generator,now I am confused with the amount of images produced in total. I have ...
1
vote
1answer
34 views

tf-idf for sentence level features

Many papers mention comparing sentences using the tf-idf metric, e.g. Paper. They state: The first one is based on tf-idf where the value of the the corresponding dimension in the vector ...
0
votes
1answer
15 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
32 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
0answers
12 views

Does Fast-R-CNN model take into account the context?

Does Fast-R-CNN model take into account the local context and global context of objects in an image ? If it doesn't, is there any other models that does that and which is efficient in small object ...
2
votes
1answer
67 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
1answer
29 views

Self-Attention Summation and Loss of Information

In self-attention, the attention for a word is calculated as: $$ A(q, K, V) = \sum_{i} \frac{exp(q.k^{<i>})}{\sum_{j} exp(q.k^{<j>})}v^{<i>} $$ My question is why we sum over the ...
0
votes
0answers
9 views

Deep Learning for One-Class Classification

I have Big Data that is textual in nature, and I have found some useful ressources for one-class classification using SVM and other models. What I'm struggling to find is how to train a model using ...
0
votes
0answers
22 views

Getting Word Embeddings for Sentences using long-former model?

I am new to Huggingface and have few basic queries. This post might be helpful to others as well who are starting to use longformer model from huggingface. Objective: Create Sentence/document ...
0
votes
0answers
14 views

Assisting image classifier with additional subjective expert knowledge without training data

This is a cross-posting from a different perspective of a question asked here: Converting weighted value to probability . For a disease classification problem, I trained a deep learning model to ...
0
votes
0answers
18 views

Comparing results of different image splicing methods on a part of the CASIA 2.0 dataset

So I am working on an image splicing detection algorithm using ResNet-50 model. I am using the CASIA 2.0 dataset which consists of 7491 Authentic images and 5123 Fake images. However out of the fake ...
0
votes
1answer
16 views

Does a rotational convolutional filter exist in neural networks?

Traditionally, a convolutional filter is one where you take a matrix of numbers, multiply it with a subset of the data, and then sum it up. Then you move the filter left to right and top to bottom in ...
0
votes
1answer
24 views

train without having target column

I have data from a year (many years but let's say one year for clarity). Data has columns like Temperature, Humidity etc. I want to train a model from October to March, in order to see if from April-...
0
votes
0answers
12 views

Checking if an image has an noise in it or not using psnr signal value

I basically want to check if an original image has noise in it or not. To do this, I came up with an approach where the original image is filtered first like using Gaussian filter. And then I ...
0
votes
1answer
36 views

Cuda for PyTorch and Cuda for Tensorflow

I want to install PyTorch and for that I visited PyTorch official website, and they give me a command to install it with Cuda: ...
0
votes
1answer
25 views

Noise free image dataset [closed]

Presently, I am working on image denoising using CNNs. I am curious where I can find a noise-free image dataset? I am looking for real-world images but not the dataset that belongs to MNIST.
0
votes
1answer
20 views

What is the standard output of the GloVe algorithm?

When I look at the loss function of the GloVe algorithm for generating word vectors, I see that $w$ and $\tilde{w}$ are symmetric: $$ J=\sum_{i,j=1}^Vf(X_{ij})(w_i^T\tilde{w}_j+b_i+b_j-logX_{ij})^2 $$...
0
votes
0answers
23 views

How can I design a search space for this simple problem?

My goal is to predict the convolutional layer execution time and I am trying to build a dataset for predicting execution time. The following parameters are used as an input to the regression model to ...

1
2 3 4 5
81