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
10 views

Loss & accuracy curves from learning rate range test interpretation

I am working on a project doing experiments with the Learning Rate Range Test (See "A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and ...
1
vote
0answers
10 views

Deep autoencoder: validation loss doesn't change

I'm trying to understand autoencoders and reproduced some code from Keras documentation: ...
2
votes
2answers
89 views

Best approach for text classification of phrases with little syntactic difference

So I have the task of classifying sentences based on their level of 'change talk' shown. Change talk is a psychology term used in counseling sessions to express how much the client wants to change ...
0
votes
0answers
17 views

ValueError: Input 0 of layer dense_123 is incompatible with the layer: expected axis -1 of input shape to have value 20 but received input with shape

I was trying to use keras to build a fully connected neural network to predict the winner of men 100m race. For simplicity sake, my data $X$ consists of 6 races (so number of training data = 6), each ...
1
vote
0answers
18 views

Identify areas within a shape/polygon with Vision / ML

Given a shape, in the format of a binary image, I would like to detect and subdivide it to new areas. Below is an attached example of such a shape and the expected outcome where each new area is ...
2
votes
1answer
14 views

Phrase/Token labeling

Looking for suggestions on how to define the following NLP problem and different ways in which it can be modeled to leverage machine learning. I believe there are multiple ways to model this problem. ...
1
vote
0answers
16 views

Why concatenating these layers, why applying masks over and over to partial convoluted image?

I have to ask some questions about one topic. In this sentence of Nvidia's article they are saying: "The last partial convolution layer’s input will contain the concatenation of the original ...
1
vote
0answers
15 views

How to feed the model with a stack of images instead of one by one?

I built a 2D model, but the dataset contains a group of images from different viewpoints for each patient, so the input should be a stack of images for each patient. I have compressed each group of ...
1
vote
0answers
42 views

Deep Learning with Time Series Data (containing Log Returns)

I am curious about how I would begin to approach this problem. I am working with a time series multi-indexed data frame (consisting of precomputed log returns) of various stocks. In this dataframe, ...
0
votes
0answers
25 views

Improving accuracy of 2D CNN with time series classification

After somewhat extensive optimization of hyperparameters, my test accuracy remains at around 70 %. I have tried techniques to augment time series but they only make things worse. Unlike image ...
0
votes
1answer
25 views

How to improve regression neural network?

I am new to deep learning and data science and trying to increase my knowledge by working on some hackathons. Currently, the hackathon project I am working on has the task to predict the closing price ...
0
votes
0answers
26 views

Reinforcement Learning, wont learn and bad in test set

I'm study and try to understand better the reinforcement learning branch; In this case I want to learn the agent to make a reward; I've tried with: A2C DQN PPO2 but the agent in test env make ever ...
1
vote
1answer
21 views

Developing a deep learning hybrid architecture for a particular problem is a highly complicated task [closed]

I am currently conducting research on application of deep learning (sensor signal recognition). I spent about a year and a half sifting through the literature and discovered some research patterns. To ...
1
vote
0answers
10 views

RMSprop in weight update - what if vertical slopes small and horizontal slopes large?

I have a question regarding the intuition behind RMSprop, As shown in the lecture video of Deep Learning Specialization by Andrew Ng, RMSprop helps to reduce the oscillation (the values of the ...
1
vote
0answers
28 views

Monte Carlo Markov Chain

I was trying to figure out what is a Monte Carlo Markov Chain. From what I understand it is a way of computing an approximation of a probability distribution, which cannot compute exactly. So we ...
0
votes
1answer
19 views

What does Keras image generators do with input images samplewise_std_normalization= True?

I have trained a a convolutional network samplewise_std_normalization=True. Now I want to check my model in real-time using Opencv. Therefore I would like to perform the same preprocessing on the ...
0
votes
0answers
16 views

Tutorial fruits and vegetables segmentation and classification with python

There is a great number of tutorials for fruit and vegetable classification with python. But the neural network is trained to classify a single fruit. What if there are several fruits in the same ...
2
votes
0answers
10 views

Why GP posterior variance is the worst-case error?(exact proof)

I am reading this paper, which explains the connecting idea Gaussian Process and Kernel methods in detail. I am impressed by the insightful explanation in this paper, but am stuck on one part in ...
0
votes
0answers
14 views

How to improve my deep LSTM model for time series?

I want to train a deep model for my time series power consumption dataset. I have created a model consist of CNN, BILSTM, Encoder-Decoder, and dense layers. here is my model: ...
0
votes
0answers
12 views

Does there exist a "content transfer" like a neural style transfer?

Normally, a neural style operation works by taking a content image and a style image. A third image is optimized to have the same content as the content image and the same style as the style image by ...
0
votes
0answers
6 views

Sequential batch processing vs parallel batch processing?

In deep learning based model training, in general batch of inputs are passed. For example for training a deep learning model with [512] dimensional input feature vector, say for batch size= 4, we ...
2
votes
0answers
25 views

Where Does the Normal Glorot Initialization Come from?

The famous Glorot initialization is described first in the paper Understanding the difficulty of training deep feedforward neural networks. In this paper, they derive the following uniform ...
1
vote
1answer
20 views

How do I represent audio file in a format that can be saved in dataset and then can be used in modelling?

i used the following code to read my audio file from scipy.io import wavfile samplerate, data = wavfile.read("the path of my audio") but when i tried to ...
0
votes
0answers
12 views

What kinds of changes can I attempt on my object detector .config file to improve the detection accuracy?

I have trained an object detection model with 2 classes, around 7500 images, and approx. 10,000 annotations per class. I was able to fine-tune Faster R-CNN with ResNet (V1) from the Tensorflow Object ...
0
votes
1answer
25 views

Excluding data via confidence score: Is it a good idea?

Let's say I have a model which has a binary classification task (Two classes of 0 and 1) and therefore, it outputs a number between 0 and 1, if it is greater than 0.5 we consider it to be class 1 and ...
0
votes
0answers
15 views

One single-batch training on Huggingface Bert model "ruins" the model

For some reason, I need to do further (2nd-stage) pre-training on Huggingface Bert model, and I find my training outcome is very bad. After debugging for hours, surprisingly, I find even training one ...
0
votes
0answers
18 views

loss function for simultaneous prediction of multiple OHE vectors

Hi I am trying to figure out how to set up the loss function for a model where the outputs are 3 one hot encoded vectors which are predicted simultaneously. This is a fully connected feed-forward ...
2
votes
0answers
28 views

Few shot learning and object detector

I have a dataset with a lot of classes (~10000+) but few examples by classes (~15-). I want to classify these classes, but there are some specificities. My examples provide from a video stream. ...
0
votes
0answers
15 views

How to create custom stochastic layer in tensorflow 2.0?

Recently, I have been looking into Stochastic neural networks and would like to try creating one; however, I am not sure where to start. I have experience in Python and have been learning TensorFlow ...
0
votes
0answers
16 views

Usage of ML models and DL models for text data

I am newbie to NLP , I was going through the some of the Kaggle notebooks then I got little bit confused. some of them are using ML models text classification and text regression problems and for ...
2
votes
0answers
20 views

Why does my validation loss increase, but validation accuracy perfectly matches training accuracy?

I am building a simple 1D convolutional neural network in Keras. Here is the model: ...
1
vote
0answers
18 views

Lovasz Softmax loss explanation

I would like to use Lovasz softmax for foreground background semantic segmentation because of its ability to improve segmentation with Jaccard index according to paper. I got the idea that its a ...
1
vote
1answer
29 views

Lung segmentation by Kmeans contains white border

I'm new to image processing, I'm trying to segment lung CT images by Kmeans by the following: ...
2
votes
0answers
15 views

How to use NER and POS for model input?

I am building a model for contract information extraction, where NER and POS could serve relevant information. I am trying with Keras (and XGBoost). My question would be what are the techniques to use ...
1
vote
0answers
27 views

How to read video dataset in tensorflow/keras?

I'm trying to develop simple 3D-CNN network for the task of video classification. I'm having 6 categories with 100 videos for each category. How can I pre-process this data and feed to the model? And ...
1
vote
1answer
153 views

All machine learning models are giving the same accuracy

I have a small dataset (2000 rows) and am testing different algorithms for binary classification. The data set is very small but I do not have the option of increasing the dataset. I have tested a ...
0
votes
0answers
30 views

Training Loss increases, but Validation Loss decreases

I am finetuning a T5 transformer model on a sequence to sequence task. My program outputs the training and validation loss every 500 optimization steps. However, when I first started training the ...
2
votes
1answer
36 views

How to measure the accuracy of an NLP paraphrasing model?

I using the HuggingFace library to do sentence paraphrasing (given an input sentence, the model outputs a paraphrase). How am I supposed to compare the results of two separate models (one trained with ...
2
votes
0answers
39 views

Freelancing in Data Science [closed]

I would like to dive into freelancing in data science but I don't know how to do it, which site I can consult.
1
vote
1answer
45 views

Concatenate two tensors of different shape

I have two tensors: ...
0
votes
0answers
14 views

calculating score for the sentiment

I am working on the sentiment project. I have used the BERT model. Now I need to generate a score for the sentiment of each sentence. I don't have any idea what would be the potential approach to do ...
0
votes
0answers
4 views

Transfer learning on images with higher dynamic range

Is it possible to fine-tune a CNN-based model previously trained on images with 8 bits depth [0 ~ 2^8] to fit a 16 bits depth [0 ~ 2^16] images? if there is any research paper that confirm that, it ...
0
votes
0answers
35 views

Q value is estimated under state V value and action A value for DDQN

How Q value is estimated under state V value and action A value. Given the below DDQN algorithm, the deep network is divided into two parts on the end layer, including state value function V(s) which ...
1
vote
1answer
21 views

Calculation of cross entropy

I want to calculate the cross-entropy(q,p) for the following discrete distributions: p = [0.1, 0.3, 0.6] q = [0.0, 0.5, 0.5] and using the numpy library: ...
0
votes
0answers
18 views

How to estimate Coal Level in a Coal Train

I want to estimate coal level in each of the bogies in a moving coal Train. I want to get the percentage of how much it is filled. Can anyone please suggest me how should I proceed?
0
votes
0answers
33 views

Imaging multivariate time series for 2D CNN classification

I have multivariate time series data in the shape of (batches, timesteps, features). So, for 10 samples with 20 timesteps and 4 features, my dataset shape is (10,20,4). I have been using this data for ...
0
votes
1answer
15 views

What are some deep learning models use in timeseries forecasting that include context from covariates?

I was going through the literature for time-series forecasting using DL and all the methods I read about only use the variable of interest at previous timesteps to predict the same variable at time ...
3
votes
1answer
69 views

Convolutional neural network low performance

Problem description I'm doing Signal Modulation Classification using a Convolutional Neural Network, but performances are very low (around 15% accuracy) and I can't find out why. Data Dataset is ...

1 2 3
4
5
84