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
5 views

Should the data be shuffled on a translation dataset

As reference to Why should the data be shuffled for machine learning tasks I was curious if this is the case for neural-machine-translation. I would like to analyze why I think this is the case for ...
0
votes
0answers
6 views

Multi-output classifier using Tensorflow/Keras on tabular data

I have been tasked with combining a several classifier models we have into one model using deep learning (or something else). The reason for this is that, in future, it would be difficult to maintain ...
0
votes
0answers
6 views

Is it possible to train a object detection network with fixed topology for a variable amount of classes?

Let's assume we have a neural network detecting objects (e.g. YOLO). The network topology is built to detect 10 different object classes. But for now I don't know, which objects I potentially want to ...
0
votes
0answers
6 views

Training with auxialiary output layer in MXNet: initializer required for another label variable

I want to test a network with auxillary classifier (example: https://stackoverflow.com/questions/39352108/does-the-inception-model-have-two-softmax-outputs ). I am trying to create a simple net with ...
0
votes
0answers
10 views

Tensorflow: how to interpret Tensorboard profile? How to increase efficiency according to it?

I use Tesla K80 for training a DNN model built with Tensorflow 2.0. I want to speed up the training. I have already used tf.data.Dataset input pipeline. I'm not using TFRecords files though. From my ...
0
votes
1answer
12 views

Epochs or Loss Convergence

I was training a Deep Neural Network using transfer learning and the loss value as of now is close to 1.7. I am using a dataset of 31,000 images and I do apply data augmentation techniques to help the ...
2
votes
1answer
37 views

Explanation behind the calculation of accuracy in deep learning model

I am trying to model an image segmentation problem using convolutional neural network. I came across code in Github which I am not able to understand the meaning of following lines of codes for ...
2
votes
0answers
17 views

What are the good parameter ranges for BERT hyperparameters while finetuning it on very small datasets

I need to finetune BERT model (from huggingface repository) on a sentence classification task. However, my dataset is really small. I have 12K sentences and only 10% of them are from positive classes. ...
0
votes
0answers
17 views

what should I do if my Neural network model stuck on high value loss?

I'm using neural nets in my projects. It's a regression problem where i have 3 features and I'm trying to predict one continuous value. I noticed that my neural net start learning good but after 10 ...
0
votes
0answers
23 views

Help required for medical imaging research | Deep Learning Project

I am a cs student currently working on Brain tumour segmentation using cascading of two U-Net research project. I have researched over the internet about the cascading of CNN but I found nothing about ...
0
votes
1answer
23 views

Using categorical_crossentropy for binary classification

Is it ok to use categorical_crossentropy for binary classification or is it better to use binary_crossentropy
0
votes
0answers
7 views

Does Feeding Edge detected images to the CNNs make sense?

Are edge detected images fed to the CNN based architectures like VGG16, etc? I know that CNNs are able to detect features like Edges, lines, contours, etc but what will happen if one feeds edge ...
0
votes
0answers
6 views

How many output channels does a resnet50 feature extractor have?

The feature extractor would be all layers until the last 2, i believe, that have the Pooling and FC layer. Based on my understanding, and these diagrams ( https://i.stack.imgur.com/gI4zT.png ), the ...
0
votes
0answers
10 views

NL2SQL, for real industrial application, what strategy to locate the exact table?

The datasets like WikiSQL is that the table corresponding to question is given. But in real industrial application, we have 100+ tables for 1 new question. Thank you!
0
votes
0answers
11 views

my cifar10 kaggle result around 10% is there something wrong with my pytorch code/?

I'm quite new to pytorch so I want check is there something wrong I got final submission code score around 10% here is my code ...
0
votes
1answer
28 views

Are there some research papers about text-to-set generation?

I have googled but find no results. Text-to-(word)set generation or sequence-to-(token)set generation. For example, input a text and then output the tags for this text: ...
0
votes
1answer
56 views

Tensorflow model works for classification but not for regression (all predictions equal the output layer bias)

I'm trying to build a model for FX prediction. It's giving some promising results for classifying each period as buy/sell/neutral. When used as a classifier, actual returns are converted to 0, 1, or ...
0
votes
1answer
29 views

Deep learning model gives random results

First I am new to machine learning if it is an obvious question, I am sorry. ...
1
vote
3answers
32 views

group the similar words

array(['Ruby on Rails', 'Ruby', 'AWS DynamoDB', 'Python', 'MySQL', 'Swift', 'Android', 'iOS', 'JavaScript', 'React Native', 'ReactJS', 'TypeScript', 'Vue.js', 'Webpack', 'Amazon Web ...
1
vote
0answers
18 views

Where can I find datasets suitable for an undergraduate research project? [closed]

I have tried Kaggle but couldn’t find anything suitable. Basically I want to do a machine learning or deep learning project. Ideally it would have something to do with computer forensics or security. ...
1
vote
0answers
21 views

SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors

I am writing Encoder-Decoder architecture with Bahdanau Attention using tf.keras with TensorFlow 2.0. Below is my code This is working with TensorFlow 1.15 but getting the error in 2.0. you can check ...
0
votes
0answers
7 views

Plotting Graph by Implementing Python [closed]

I have a question about The Polynominal Regression and python. I was wondering how to plot this data given below into graph of Polynominal Regression by using the python. How to do that ? I am facing ...
2
votes
3answers
31 views

Can someone explain what batch size is doing in convolutional NNs?

I've noticed that the performance of my models vary quite a bit as a function of the batch size, both in terms of the time to converge and (possibly) the amount of overfitting.I thought batch size was ...
0
votes
2answers
38 views

Can some one please explain AI, Machine learning and Deep learning? [closed]

Can anybody Differentiate between AI, Machine-learning, and Deep-learning? Please Share if you have Detailed Material. Thanks in Advance.
0
votes
1answer
25 views

Help with deep learning for motorbike inspection

First of all, I am very new in machine learning and data science, so I am really sorry if my question is completely stupid. I am doing an internship in machine vision, and people of my office want me ...
2
votes
0answers
9 views

How to estimate the marginal distribution of a class with respect to one predictor in a classification task?

I have a dataset with a binary dependent variable $y \in \{0,1\}$ and a set of predictors $x1,x2,..,t$. Here, $t$ is the time in minutes (in 24 hrs, that is $t \in (0,1440)$). I want to estimate the ...
1
vote
1answer
18 views

In Deep Learning, how many kinds of Attention exist? And what is the history of Attention models? [closed]

How many definitions of attention are commonly employed for Deep Learning tasks? That's what I've encountered up to now: Self-attention Bahdanau Luong Multi-Head (used in Transformers) Could you ...
1
vote
1answer
17 views

Trained CNN individually on multiple images to classify them, how can I now classify a related “set” of these images that correspond to one object?

I have a N object classification examples, each example consisting of a set M individual images of the object at different angles. I've trained M CNNs with the dataset of one particular image angle ...
0
votes
0answers
14 views

How to consider different size of input for “Graph Conv Network”

I'm a student who just start study deep learning. I hope to practice with simple project using Graph Convolution Network. The question is that "How can I handle with different size of input graph ...
1
vote
1answer
19 views

Any good Implementations of Bi-LSTM bahdanau attention in Keras?

From past few weeks I'm trying to learn sequence to sequence machine translation modelling but I couldn't find any good examples/tutorials with bahdanau attention implemented. I did come across a ton ...
1
vote
1answer
27 views

When to use deep learning for java as opposed to python

I have been asked to explore options to build deep learning based applications using java, so i happend to browse a website called dl4j (https://deeplearning4j.org) which has got implemantations of ...
0
votes
0answers
24 views

EMOJIS Help me find an architecture

I want to build a deep learning algorithm that places emojis in a pretty long text, please don't ask me why I just want to do it. Where should I start? I've read that recurrent neural networks are ...
0
votes
1answer
30 views

Why would batch normalization allows us to use higher learning rate in the neural network?

I am doing some study about the BatchNormalization: https://towardsdatascience.com/batch-normalization-8a2e585775c9 In the article, it says: ...
1
vote
0answers
13 views

Discriminator of a Conditional GAN with continuous labels

OK, let's say we have well-labeled images with non-discrete labels such as brightness or size or something and we want to generate images based on it. If it were done with a discrete label it could ...
1
vote
1answer
58 views

Steps on how to use autoencoders to reduce dimensions

I have a dataset that contains text columns. I have used tf-idf to convert those text columns to numerical columns. I want to reduce the dimension of the dataset since tf-idf creates a multitude of ...
1
vote
1answer
12 views

Can a convention convolution neural network train correctly with different training image size and ratio?

For example the task of transformation, the model consist convolutional layer and pooling layer only, take input of image, and output a feature map (loss MSE, trying to produce feature map that ...
0
votes
1answer
23 views

How to gauge the Complexity of Pre trained Neural Networks?

What does one mean when they are talking about the simplicity of the networks? Does it mean that the shallower the networks the simpler they are, or does it mean that lesser the number of trainable ...
1
vote
0answers
13 views

Which non heuristic based approach would be best for document segmentation? [closed]

Due to my lack of knowledge in deep learning and neural network I need help picking the best approach to tackle a challenge. I have a dataset with list of words where each word has 4 attributes (x, ...
1
vote
0answers
14 views

Why not use loss value for stopping the training in Siamese Networks?

I was building the training pipeline for a siamese network for one-shot learning. Everybody on the internet uses accuracy rather than loss for stopping training. Why use one-shot accuracy over loss ...
1
vote
0answers
10 views

Training a model for Single Image Super Reoslution

I'm trying to implement the Attention-based approach for SISR paper. However, during something odd happens. The MAE for the first output of the model is very small. But as the training progresses, the ...
0
votes
0answers
12 views

Was the ImageNet challenge organized in 2018 and 2019?

Does anybody know if the ImageNet challenge was organized in 2018 and 2019? If so, what were the results/winning algoritms? If not, why? I could not find any references on the ImageNet website and on ...
0
votes
1answer
17 views

Why seq2seq models are superior to simple LSTMs?

It is common knowledge in the field of Deep Learning that the most powerful Recurrent architecture is the sequence-to-sequence, or seq2seq, for pretty much any task (to time series forecasts, to ...
1
vote
0answers
23 views

Detect blur image using ssdmobilenet and tensorflowlite

I have clear images of cards vs blurry images of card. My task is to capture photo when the image is not blurry, as you can see from the description I need this code to run in real time on android ...
1
vote
1answer
21 views

How to use Inception v3 in Tensorflow

I am trying to import Inception v3 in TensorFlow. I wish to apply it after reading this tutorial on object detection.
0
votes
0answers
7 views

should I re-initialize my optimizer and my scheduler before I try to fine tune my neural network on the different dataset?

I am doing NLP, and I have this block of Transformer body that was already trained on dataset A. Now I am interested in fine tuning this same Transformer on a new dataset B. In my Python code, should ...
2
votes
2answers
66 views

why an advanced LSTM model produce the same results as a simpler one?

I have implemented the model proposed in this article which is a text classification model that uses sentence representation rather than only word representation to classify texts. ...
2
votes
0answers
11 views

Model not learning when using transfer learning

I am working on a personal project on image classification (two classes) and am trying to see how the MobileNet v2 structure would perform. While training the training accuracy is already quite high ...
0
votes
0answers
14 views

Design of Deep Learning Architecture?

How is a deep learning architecture designed? Can somebody explain in-detail, steps involved for designing a deep learning architecture?
0
votes
0answers
21 views

Customize loss function for Music Generation LSTM (?)

I have to carry out a Music Generation project for a Deep Learning course I have this semester and I am using Pytorch. The dataset is songs in midi format and I use the python library mido to extract ...
0
votes
0answers
14 views

Do I need to train a separate DeepFake model for every input person?

I would like to create a deep fake model of a specific person (we will call him Steve). I would then like to be able to upload a video of any random person and swap their face with Steve's. So far I ...