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.
4,791
questions
0
votes
0
answers
10
views
Accelerated learning when wrapping layers in a class
I am implementing a VGG-like network using Pytorch 1.13.1 (python=3.7.12) for image classification on the CINIC-10 dataset. The following two implementations turn out to have very different training ...
- 1
0
votes
1
answer
26
views
Understanding correlation - Machine Learning
I am experimenting a project on identifying cancer or not - Binary classification
The dataset has many columns. Here, I added correlation values between few input columns and the target column[cancer/...
- 21
0
votes
0
answers
20
views
Multi-output Classification?
I have a dataset consisting of 1 X (Textual Data) and 5 different y (Topics of each text) and each y can take values from 0 to 5. I need to develop a deep learning model to take text and predict all y....
0
votes
0
answers
14
views
Subjectivity Classification with BERT and Word2Vec
I am new to NLP and working on a final-year project to classify if a sentence is written from objective or subjective point of view, using BERT with Word2Vec.
The datasets I found for this project are ...
0
votes
0
answers
7
views
loss: NaN when training ucr timeseries set
I'm trying to change the input of this model,
https://keras.io/examples/timeseries/timeseries_classification_from_scratch/
the model architecture is as follow:
...
- 1
0
votes
0
answers
16
views
Fast Fourier Transform in computer vision
Can someone explain me how does FFT works in computer vision, please. I know something about FFT as an algorithm of competitive programming but I can't understand how it perform an image in computer ...
- 101
0
votes
0
answers
31
views
Weighting and loss function for multi-dimensional output on ECG neural network in Tensorflow
I am working on a DNN that is training on ecg data with a shape of [None,1,2500] and output shape of [None,12,19] where 19 is a ...
1
vote
1
answer
10
views
0
votes
0
answers
24
views
Differential equations, real time measurements of variables, and ML
TL;DR: We measure variable $x$ every $10$ minutes, solve a differential equation $\frac{\mathrm{d}y}{\mathrm{d}t}$ where $y=f(x)$. We are interested in the time it takes for the cumulative value of $y$...
0
votes
0
answers
11
views
Siamese Neural network inputs
A currently task involves the classification of bacteria as antibiotic susceptible and antibiotic resistant.
I have 4 data sets: treated resistant, treated susceptible, untreated resistant and ...
0
votes
0
answers
8
views
In "Show, attend and tell", why do the attention weights get multiplied with the features to form the context vector?
The attention weights are formed through the last hidden state of the LSTM and the feature map from some kind of image encoder (in my case resnet so the features are in the form of 14x14x2048). They ...
- 101
0
votes
1
answer
29
views
ReLu layer in CNN (RGB Image)
I am able to get convoluted values from RGB Image lets say for each channel.
So I have red channel with values: -100,8,96,1056,-632,2,3....
Now what I do is that I ...
- 103
0
votes
0
answers
19
views
ValueError: Input 0 of layer sequential_3 is incompatible with the layer: expected ndim=5, found ndim=3. Full shape received: (None, 1, 200)
I m confused about the input shape for the convLstm model !
I need some help for a classification problem. I would be very grateful if anyone could help me. So, the dataset is in the form of Drug ...
- 1
0
votes
1
answer
48
views
Can feature engineering avoid overfitting?
Can feature engineering avoid overfitting? If yes, are there any relevant papers that state this?
- 21
0
votes
0
answers
14
views
Reporting and/or evaluation of metrics in deep learning
While I was trying to write a custom training script, I encountered the following doubt.
I see that the loss is evaluated at the end of every forward pass (i.e., a step or with a particular batch of ...
0
votes
0
answers
9
views
Which loss function is used on Whisper model?
I read the article on Whisper model:
Robust Speech Recognition via Large-Scale Weak Supervision
They didn't write which loss function did they used ?
It seem that they trained the model as ...
- 363
0
votes
0
answers
9
views
Creating a neural network for classification that take each embedded word in each sentence as input
(The title was difficult to phrase - please suggest another title if you can)
I have a classification problem with 60 classes, and some (very) short sentences (bank transactions). Most of the ...
- 440
0
votes
0
answers
15
views
Main Features of Convolutional Neural Network
The design of CNN architectures in recent years focuses on how to implement attention mechanism, features an aggregation (sum, addition, and multiplication), as well as receptive field enhancement.
...
- 231
0
votes
0
answers
10
views
why by adding additional information as number of sequence on dataset can avoid overfitting
I am developing a regression model to analyze walking styles. The dataset I am using to build the model is from 2 different sources, let's call them dataset A and dataset B. Dataset A has a shape of (...
- 21
0
votes
3
answers
50
views
+100
In-batch Random Negative Sampling
I'm trying to train a recommender model using In-batch Random Negative Sampling as described in the following paper: https://arxiv.org/pdf/2102.06156.pdf. I'm having a bit of difficulty wrapping my ...
- 1
0
votes
0
answers
10
views
Can invariance in CNNs hamper semantic segmentation?
As far as I understand, invariance is a property that is desirable for the CNN-based models. It helps us detect various objects even in different scale, position, rotation, etc. depending upon the ...
0
votes
2
answers
40
views
Laptop for machine learning jobs
I am buying a new laptop for data science and web development jobs.
Which combination is better:
i9 (12900H) & NVIDIA T600 4GB
or i7 (12800H) & NVIDIA RTX1000A 4GB?
Both run on a DELL ...
- 1
0
votes
0
answers
16
views
How to make a DL price prediction model aware of market fluctuations [closed]
here's a pretty general question, so i do not expect to get precise answers. Instead i hope to read ideas and suggestions.
I have a deployied proprietary Deep Learning model that make retail price ...
- 101
0
votes
0
answers
18
views
Need help with improving validation loss and model overfitting/underfitting
I am using Ensemble PyTorch to train a voting classifier. My dataset includes around 60k records. I trained a Neural Network with Cross-entropy loss. Below is my model architecture
...
- 1
0
votes
0
answers
30
views
Tensorflow regression model appears to not learn anything
I have a data set containing press releases from publicly traded companies in one column. Then I have the net return impact on the of the company who published the press release stock price. For ...
0
votes
0
answers
10
views
Can I use zero-padded input and output layers in a 1D convnet to predict an element of interest from a variable-length input sequence?
I have developed a small encoding algorithm that accepts a time series of n = 750 samples and m = 1 feature from a scientific instrument, and encodes/transforms it into a new ordered sequence with an ...
- 133
0
votes
0
answers
16
views
Teaching the model on more than one dataframe/dataset
I am trying to write a thesis on oil pipe leakage detection. The aim is to predict the size and location of the leak. My problem is that I can only run single simulations using a software called OLGA ...
0
votes
1
answer
17
views
Are there any pre-trained non english model of deepspeech?
I want to try deepspeech model.
I founded only english pre-trained model
Are there any other pre-trained not english model of ...
- 363
0
votes
0
answers
17
views
why CNN the model can't predict 0
I have two datasets: force plate data and plantar pressure data. The force plate data consists of 6 data points, while the plantar pressure data consists of 90 data points. Both datasets have a ...
- 21
1
vote
1
answer
27
views
How does BERT work for Aspect-Based sentiment analysis?
I have recently used a package to perform Aspect-Based Sentiment Analysis (ABSA) through a BERT model.
Briefly, the model takes two inputs:
words that constitute the aspects
a sentence on which we ...
0
votes
0
answers
12
views
2
votes
2
answers
25
views
Should I open abbreviations/acronyms in the text data, when training transformer model?
I am currently training a transformer model on text data. Is it a good practise to open abbreviations/acronyms in the text data? I did not dins any tips or recommendations about it on internet.
- 183
0
votes
1
answer
23
views
Is deep learning high initial validation accuracy a sign of problem?
I have a image classification model with 8400 images of class A and 1800 images of class B. I have used validation_split=0.2 with subsets of ...
- 111
1
vote
2
answers
42
views
What does the output of an encoder in encoder-decoder model represent?
So in most blogs or books touching upon the topic of encoder-decoder architectures the authors usually say that the last hidden state(s) of the encoder is passed as input to the decoder and the ...
- 113
0
votes
0
answers
5
views
help with comparison between the prediction of a bayesian neural network and an analytical model
i am in a weird situation where i have a bayesian neural network used for regression and a polynomial model $f(a,b,c,d) that depends on 4 parameters and that is fitted through monte carlo methods.
i ...
- 101
1
vote
1
answer
26
views
What to do if my dataset have only One instance for class in classification?
I am working on a benchmark dataset for text classification. The dataset has about 300 classes, and approximately 50 of these classes have a single instance. In a paper that used fine-tuning BERT, the ...
0
votes
1
answer
11
views
CWRU Bearing fault
I am new to ML. I have been asked to use a pre-trained GRU model for detecting a bearing fault in CWRU. is pre-trained model another name for transfer learned model?
0
votes
0
answers
9
views
How to calibrate autoregressive model?
TL;DR What metric, and how to calibrate autoregressive language (deep learning) model?
Background
Usually there are several popular approach to calibrate a non-autoregressive model such as isotonic ...
- 101
0
votes
0
answers
11
views
How to shape the input for Temporal Convolutional Networks
Consider a normal time series coming from stock prices, assume for simplicity it's several thousand data points. So basically I have a time series of prices $\{x_i\}_{i=0}^n$ of $n$ data points.
I ...
- 101
0
votes
1
answer
48
views
What are the advantages of autoregressive over seq2seq?
Why are recent dialog agents, such as ChatGPT, BlenderBot3, and Sparrow, based on the decoder architecture instead of the encoder-decoder architecture?
I know the difference between the attention of ...
- 3
0
votes
0
answers
19
views
CNN model well trained but can't predict real data
I'm developing a CNN regression model for gait analysis. It seems the model is well trained, with low val_loss and low loss. However, the model does not work well to predict real data. In this ...
- 21
0
votes
0
answers
34
views
I can't figure out why even when training the seq2seq chatbot neural network, it doesn't give adequate answers
When training with 50 thousand pairs of questions and loss 0.2 accuracy 0.9 it does not give adequate answers
...
- 1
0
votes
0
answers
7
views
When using wav2vec2 inference, does the quantitation being used?
According to wav2vec model:
it seems that quantitation only used on training phase (in order to train the transformer layer to quantitative the data to use small number of discrete values).
So my ...
- 363
0
votes
0
answers
12
views
Which is a better tool to build on Azure, SAP or Oracle
I'm trying to understand each platform's pros and cons to help decide how we build out your ERP solution.
I'm new to the cloud, so please bare with me.
We will use this for D.B for ML first, then A.L.
...
- 1
2
votes
2
answers
87
views
Group unstructured chat logs into conversations
I am new to ML/AI/NLP and am interested in tackling the following problem. I have a database of chat logs from a Discord server. The database contains the following labeled data: ...
- 21
0
votes
0
answers
12
views
CNN sharing weights in feature map
what do they mean when they say all
neurons in a channel share weights with one another? Do they mean that in a chanel or a featue map the weights are the same ?
0
votes
1
answer
26
views
Why is cross entropy loss averaged and not used directly as a sum during model training(such as in neural networks)
Why is the cross entropy loss for all training examples(or the training examples in a batch) averaged over size of the training set(or batch size) ?
Why is it not just summed and used ?
0
votes
0
answers
7
views
Is there a Graph Neural Network that learns from its neighboring labels (and features)?
I built a heterogeneous graph on a citation graph with a Heterogeneous Graph Convolutional Neural Network in PyTorch and DGL. The graph structure looks like this: (author, writes, paper), (paper, ...
- 1
0
votes
0
answers
13
views
Input shape for a keras custom layer
How does one find the input shape for a custom keras layer? Say I have a layer which accepts a list of 2D tensors as an input [a, b, c...] where only ...
- 1
0
votes
0
answers
13
views
Explain the outputs of Bidirectional LSTM . There are 5 output , which of them are hidden state and cell state respectively?
I am trying to use bidirectional LSTM as encoder in my translation model.
I set return_sequence=True and return_state=True and I ...
