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
0 answers
11 views

There is less inputs received while giving the exact number of inputs required

I am testing an encoder decoder lstm model . the training phase went well but the testing phase after building the testing model is giving me an error while trying to input to the decoder layer , here'...
user avatar
0 votes
1 answer
22 views

What is the difference between adding words to a tokenizer and training a tokenizer?

The title says it all. I was researching this question but couldn't find something useful. What is the difference between adding words to a tokenizer and training a tokenizer?
user avatar
  • 71
1 vote
1 answer
18 views

How do we derive our loss function from the gradient objective?

I've been dwelling through RL theory and practice and one particular part I find hard to properly understand is the relation between the practical loss function and ...
user avatar
1 vote
1 answer
29 views

Fine tuning Convolutional Neural Network with a learnable first layer

I have a classification task using grayscale images and I want to leverage from pretrained networks. There are a lot of resources out there presenting how to fine tune large neural nets like resnet, ...
user avatar
0 votes
0 answers
32 views

Training a model with ArcFace layer according to code by 4uiiurz1 compatible with TensorFlow Keras

I am trying to train a model with the ArcFace code taken from https://github.com/4uiiurz1/keras-arcface in which I took the ArcFace layer and added it to the model. I created a small dataset of 4 ...
user avatar
1 vote
1 answer
75 views

What is the best machine learning technique to fuse two spatial data sets?

I have two data sets, containing points geometry (X,Y) and a recorded car exhaust parameter (let's say, RP value), of an area of ...
user avatar
0 votes
0 answers
7 views

Assuming a nearly perfect NN exists for any data, and Training MSE is approx Val MSE, is a more complex model required?

Assuming that there always exists a function/NN that can perfectly model the data, I apply a neural network/random forest or ... etc. to data. If my model has a training and validation MSE/loss that ...
user avatar
  • 71
0 votes
0 answers
11 views

How to generate multiple captions from an image captioning model in Keras/Tensorflow

I am practicing one of the popular image captioning keras model (LINK IS HERE). Basically this model takes Flickr8k dataset where each image has 5 captions. ...
user avatar
  • 1
2 votes
1 answer
17 views

Mixed language OCR

I'm solving a table data recognition task And the huge problem is the recognition of mixed language pictures. I'm using tesseract for OCR, but it fails to recognize both languages simultaneously. Here ...
user avatar
  • 21
0 votes
0 answers
9 views

Rapid MSE decrease in one (or less) epoch. Then seeming never ending but glacial decrease in MSE

What does this mean? That my neural network can get to a good MSE very quickly suggests maybe I have too complex a model. (I think?) But that the MSE/R2 is ok, hardly great, and also seems to improve, ...
user avatar
  • 71
0 votes
0 answers
8 views

How to feed temporal image data to a 3D CNN?

I am using TensorFlow and Keras to build a 3D CNN, where the 3rd dimension is time. I have a dataset which contains evolving images with time (51 frames were taken). For testing, I took 10 simulations....
user avatar
  • 1
0 votes
0 answers
13 views

How to use batches for training in Sequence-to-Sequence models?

I am working on a seq-to-seq Image Captioning model, with Vision Transformer as the encoder and a LSTM based model as a decoder. The output from the encoder is given as the hidden state and cell state ...
user avatar
0 votes
0 answers
5 views

Different Kernel Initializers in my prediction layer with Transfer Learning could affect performance?

So I have this model right here and the task is to classify 3 labels.: ...
user avatar
0 votes
0 answers
2 views

Does ResNet takes less training and testing time compared to squeezeNet?

It is being said that ResNet manages to overcome vanishing gradient problem thereby making the training faster. So, does it means ResNet requires less training and testing time? Also does training and ...
user avatar
  • 1
0 votes
0 answers
29 views

NLP Text Classification Model with defined context / intent

This is more of a guideline question rather than a technical query. I am looking to create a classification model that classifies documents based on a specific list of strings. However, as it turns ...
user avatar
  • 101
0 votes
0 answers
7 views

Is GAN better than DBNs?

I understand that they are different models and work differently, but they are both generative models and can both be used to do feature learning and classification. Is GAN most of the time better ...
user avatar
  • 1
0 votes
1 answer
15 views

Named Entity Recognition using Spacy V3 with imbalance entities

Will the spacy V3 model get affected by imbalanced entities? I have got a dataset annotated in spacy format and if I look into my custom entities the rations are different for different entities. For ...
user avatar
  • 103
0 votes
0 answers
21 views

Marginal Probability Distribution of Feature space - meaning

I'm reading some literature on Transfer Learning in NLP, and this is one of the definitions that I came across in Pan & Yang (2010) Here is another definition from Sebastian Ruder which is a ...
user avatar
0 votes
0 answers
12 views

Why are we training Segment Embedding in BERT?

In BERT we have segment embeddings that are used for "Segment Embeddings with shape (1, n, 768) which are vector representations to help BERT distinguish between paired input sequences." Yes,...
user avatar
  • 71
1 vote
0 answers
21 views

Deep learning model to predict the actual input values

I have some observed parameters to be used as input to the deep learning model. This problem comes from the wireless field where we transmit $x$. The channel $h$ is random in nature. The received ...
user avatar
  • 11
0 votes
1 answer
21 views

Training deep neural networks with ReLU output layer for verification

Most algorithms for verification of deep neural network require ReLU activation functions in each layer (e.g. Reluplex). I have a binary classification task with classes 0 and 1. The main problem I ...
user avatar
0 votes
0 answers
16 views

How does CLS token having meaning of the sentence in BERT

As my understanding CLS token is a representation of the whole text (sentence1 and sentence2), which means that model got trained in such a way that the CLS token is having the probability of "if ...
user avatar
  • 71
0 votes
0 answers
13 views

Can I distill knowledge across different neural network frameworks?

I'm interested in using knowledge distillation to compress a large deep learning model to a smaller size so it will run on an embedded device. I've found a number of open source examples for the ...
user avatar
  • 244
0 votes
0 answers
15 views

job roles hierarchy formation literature

I have a csv file with job titles, descriptions and skills associated with each job title. These titles and skills span multiple domains (IT, HR, Banking, Healthcare and many more). I am interested in ...
user avatar
0 votes
0 answers
15 views

What causes the loss to be nan and accuracy to not improve?

I am training a Bi-Directional LSTM model as follows, to predict the probability of a binary class based on a handful of observed time series. The model is as follows: ...
user avatar
  • 1
1 vote
1 answer
53 views

How special tokens in BERT-Transformers work?

I was trying to understand how tokens work and all I understood is that tokens are the representation of the input in a more meaningful way (data preparation for the "encoder of transformer" ...
user avatar
  • 71
0 votes
0 answers
8 views

How to build a multi caption image generator model?

I want to build a multi caption image model. This model should be able to produce (5-8) captions from an image. I have searched about it but there are only single caption generator image models. I ...
user avatar
  • 1
0 votes
1 answer
28 views

DQN not learning anything - Reinforcement Learning

I am trying to train a DQN to play the 8puzzle game. I have implemented a batched gameboards, so I am not using ReplayMemory. Here's training process: ...
user avatar
  • 1
0 votes
0 answers
13 views

Circular data model for wind direction

Say I have a matrix of 10 X 10 of vectors in 3D, where the dimensions include height of the specific point, speed in m/s, and angle in degrees. The test cases I have are matrices of 10 X 10, where the ...
user avatar
2 votes
1 answer
55 views

Low validation accuracy when not using shuffled datasets

First I tried creating the training/testing datasets using sklearn train_test_split function like the following, ...
user avatar
  • 123
0 votes
0 answers
11 views

Which layers are doing image segmentation on AutoEncoders/U-NET?

While I was researching for transfer learning, I saw that people are replacing encoders with VGG-16 weights and only training the decoder part of the network. But in some representations (like This) ...
user avatar
  • 71
0 votes
0 answers
24 views

Masking pixels for a CNN

I'm trying to implement a CNN with RGB and depth images. But my depth images are a little sparse. So I would like to mask out those neighborhoods in the RGB image where the depth neighbors are empty. ...
user avatar
1 vote
1 answer
32 views

Which representation of CNN feature maps is correct?

When I extract my features from my CNN, it doesn't look like this: And those pictures are not just representation. From this article it can be seen that these features are actual extracted features ...
user avatar
  • 71
0 votes
0 answers
7 views

Discrepancy between hyperband best models and identically manually made models

When I do a keras hyperband hyperparameter search, and obtain the best models from a search over e.g. 30 max_epochs and 10 hyperband iterations, and the search is complete, the hyperband tuner https://...
user avatar
  • 71
0 votes
0 answers
32 views

The observation returned by the `reset()` method is not contained with the observation space

i'm strugling to understand how custom observation_space should be coded and how there isn't so much info about some topics i have to ask here if for example i have to return a observation with an ...
user avatar
1 vote
2 answers
46 views

Formal conditions on mappings that can NOT be learned from data

I am new to machine learning and would appreciate some help on the following question. I have observed the literature is focused on algorithms, how one learning does better compared to others for a ...
user avatar
0 votes
2 answers
81 views

How to Predict Probabilty that the Customer will buy specific Product?

We have data consist of previous transaction history consisting of Date,Order-id, Product-id, Product name, ordered or not. We need to predict a specific product probability for all the customers that ...
user avatar
  • 36
1 vote
2 answers
24 views

In Gradient descent, Why the gradient of cost function do not have to be normalized into unit vector

From my background, I understand that the purpose of having a learning rate (α) is to normalize the magnitude of gradient (▽J), so the step size can properly converge the local minima Since α is ...
user avatar
  • 11
0 votes
0 answers
10 views

not able to show evaluation metrics for object detection on MSCOCO like dataset using FASTAI

I want to show evaluation metrics for coco object detection,I have saved my learner in .pth file and I have data in variable data(databunch type fastai) , I have the code from the notebook finding ...
user avatar
1 vote
0 answers
31 views

Why is a neural network not doing better than multivariate linear regressions?

I am making neural networks of multiple targets, all using same training data. For some of these targets, multivariate linear regressions do a very good job, i.e. a strong linear relation exists ...
user avatar
  • 71
1 vote
1 answer
19 views

Understand the reason of embedding and the size inside it in Pytorch

I'm very new to pytorch - taking a course in udemy. There is something I find hard to understand and would like to get explaination about, in a bit simpler words than what I can find in the ...
user avatar
  • 349
0 votes
1 answer
21 views

how to handle soft weight constraints in neural network

Let us assume that there is a feedforward neural network with two layers. and weights of each layer are constrained such that sum of the weights is a constant value in each layer and their values are ...
user avatar
0 votes
0 answers
10 views

Style Transfer - how to choose the cnn layers?

I read this tutorial. In that tutorial they choosed: conv layer #4 for content_layers conv layers: 1, 2, 3, 4, 5 for ...
user avatar
0 votes
1 answer
15 views

tensorflow beginner demo, is that possible to train a int-num counter?

I'm new to tensorflow and deep-learning, I wish to get a general concept by a beginner's demo, i.e. training a (int-)number counter, to indicate the most repeated number in a set (if the most repeated ...
user avatar
8 votes
2 answers
844 views

MLOps for beginner

I am 1 year old in ML and have been using jupyter notebook to build static models all these days, do some analysis and present my results to the bosses as it was all POC. Now, we would like to scale ...
user avatar
  • 2,275
0 votes
0 answers
6 views

I do not understand normalization and standardization

in my ML Course at Uni, a big topic was normalization and standardization, but still - I don't really get why we do that. More specifically, I'm working on a (fairly complex) CNN to predict missing ...
user avatar
1 vote
1 answer
20 views

In LSTM why h_t output twice?

According the LSTM design: The hidden state (ht) is output twice (1 and 2 in the picture). If they are the same, why we need them twice ? Is there a different use for each one of them ? According to ...
user avatar
0 votes
0 answers
15 views

nn.NLLLoss() gives negative result - what it's mean?

I saw code which use nn.NLLLoss() (negative log likelihood loss). I looked on the results and some loss results (result of ...
user avatar
0 votes
0 answers
22 views

Best Neural Networks for Models with If Statements

If I am trying to use a neural network to learn/improve/replace part of an existing computer model, and that has if statements in it which seemingly make it more difficult to predict than other parts ...
user avatar
  • 71
0 votes
0 answers
9 views

does constant input add information in training a neural network?

I am working on an image denoising task. My noise pattern is generated from a 3rd degree polynomial function of images. I have multiple sets of 4 images (called tables) to generate different noise ...
user avatar

1
2
3 4 5
92