Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

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 sorts of Probabilistic Graphical Models.

0
votes
0answers
6 views

YOLO algorithm - understanding training data

I am taking "Convolutional Neural Networks" on Coursera and it is taught by Andrew Ng. I am in week 3 and confused about YOLO algorithm. I checked the course forums on coursera but I am still not ...
-1
votes
1answer
11 views

Best framework to detect Emotion

I am slightly greater than a beginner to Data Science. Currently I am trying to build an emotion detection API which will detect emotional state from a short video. I have planned to do it with fast....
0
votes
0answers
5 views

With two deep learning models, how do I perform Bayesian Model Averaging for better prediction on a test set?

Given two deep learning models that can predict on a test set, what I want to do is use BMA (Bayesian Model Averaging) to average the models to better predict? What exactly is the procedure for this?...
0
votes
0answers
14 views

LSTM predictions only above or below mean value

I have an interesting problem with the predictions of my keras LSTM model. The goal of my model is to predict the changes in high and low prices for a selected FX rate pair based on the following ...
0
votes
0answers
5 views

Whats the Difference between probabilistic programming such as pyro and Belief networks?

I heard about ubers pyro and stumbled upon this Wikipedia Artikel As I understand a bayesian network is the same as a belief netLink to datascience StackExchange post Does someone know how these are ...
1
vote
0answers
16 views

AttributeError: module 'torch.distributed' has no attribute 'init_process_group' [on hold]

AttributeError: module 'torch.distributed' has no attribute 'init_process_group' Still getting this error after installing latest pytorch-nightly and other stuff, when I tried to run the imagenet ...
3
votes
0answers
14 views

Do CNNs benefit from HDR images?

I have images with 12 bits per color channel which I use for several detection networks (YOLO, RetinaNet, etc.). Can I expect any precision difference between 12 bpp and 8 bpp as network input? Or is ...
0
votes
0answers
8 views

Hierarchical multi classification using Neural networks

I have a data set(non text) of 40 features which has 4 main classes and 2 sub classes. Assume, the 4 classes are AB, C, D and E. AB is further divided into class A and class B as sub classes. I want ...
1
vote
1answer
11 views

RBF neural network python library/implementation

I want to use a Radial Basis Function Neural Network for my thesis. Is there any library that implements it? And in the negative case, which is the best library to implement it?
0
votes
1answer
12 views

Feature Scaling and normalization in cross-validation set

I have a question that normally, when we are making a training set and a final test set, we would compute the mean and standard deviation for preprocessing using the training data and use it to ...
0
votes
1answer
37 views

Possible reasons for word2vec learning context words as most similar rather than words in similar contexts

I am observing my word2vec model learning context words as most similar rather than words in similar contexts. I don't understand why it (word2vec in general, not my model in particular) can behave ...
0
votes
1answer
30 views

Unsupervised learning from images

I want to design a model that can detect the different feature in the images, let's consider we have ~100000 images of cows. when I give this images to the model it has to identify different parts of ...
0
votes
0answers
24 views

Which machine learning/deep learning model can I apply to a mix on textual, categorical and numerical data for a binary classification

I have a project based on tweets wherein I am trying to build a binary classifier, I am aware that I can use a contextual LSTM model which takes the metadata of a tweet as an auxiliary input within ...
0
votes
0answers
17 views

Should I concatenate one-hot vectors and real vectors as input feature?

I have a set of input features consisting of the following for each row of data: real vectors (1x128 dimensions, between [1,1000000000] ) one-hot vectors ( 1x168 dimensions, i.e. 7 days 24 hours ) ...
0
votes
1answer
11 views

In Reinforcement Learning can I randomly assign next_states from the state space to my agent while creating transition set?

In Reinforcement Learning, while creating transition samples (state, action, next_state, reward), where: Agent: The learning agent Environment: The trainer The environment gives two feedback to the ...
0
votes
0answers
9 views

Why does my custom categorical cross-entropy explode with Keras while not with TensorFlow?

I'm trying to train various Keras models on Pascal VOC 2012 dataset. The particularity of this dataset is that there is a particular class used to label "ambiguous" regions. These pixels are meant to ...
1
vote
2answers
22 views

Continous bag of words claimed to be unsupervised, how is it working?

I'm following these two lectures on CBOW and skip-gram word2vec models. The first is lec 12 and the next lec 13 of a deep learning series https://www.youtube.com/watch?v=syWB-YMYZvI https://www....
1
vote
1answer
11 views

sentiment analysis for multiple entry in one text

I must do sentiment analysis on a set of financial news from s&p500 for given entities (organization names), but the problem is that each news (rows in my dataset) may have more than one entity ...
0
votes
0answers
15 views

How is Universal Sentence Encoder trained using Deep Averaging Network (DAN)?

In the paper of Universal Sentence Encoder (USE), the author mentions it to be trained using transfer learning in an unsupervised manner in two forms: 1. Using Deep Averaging Network (DAN) 2. Using ...
0
votes
0answers
6 views

What is the best tensor data format from saving in python and loading in c++

I hope to use Caffe c++ backend to conduct my new model training on a large embedding corpus data. As I am using python numpy to do the basic preprocessing and ...
0
votes
0answers
5 views

Hierachical Softmax Example In Deep Learning Book

I was learning neural network using the book "Deep Learning" by Ian Goodfellow, Yoshua Bengio and Aaron Courville. Section 12.4.3.2 has an example to show the computation cost improvement from ...
0
votes
1answer
22 views

Input and output Dimension of LSTM RNN

I am fairly new to RNNs and Im having trouble setting up the desired output from RNN using Keras library. Each datapoint in my dataset consist of a pattern of labels and timestamp of occurrence of ...
0
votes
0answers
6 views

Predict the StateOnTime and StateOffTime for each appliance

Explanatin: 1. There are 5 appliances in "applanceName colomn". each appliance(Fan, LED, Srtip, Tube,Bulb) has some observations with StateOnTime and StateOffTime. 2. In StateOnTime there are 2 or 3 ...
0
votes
1answer
26 views

Using categorial_crossentropy to train a model in keras

I'm a novice in machine learning. I was following this Keras blog to train image classifier using Keras. Though this blog only demonstrates how to train only two classes using binary_crossentropy, I ...
2
votes
1answer
15 views

Why ELMo's word embedding can represent the word better than glove?

I have read the code of ELMo: https://github.com/allenai/bilm-tf Based on my understanding, ELMo first init an word embedding matrix A for all the word and then ...
1
vote
0answers
11 views

How do I implement an attention mechanism for convolutional neural network in Keras?

I have a convolutional neural network in Keras on which I'd like to add an attention mechanism? Has anyone done this? It seems Keras doesn't have an in-built attention mechanism and the ones I've ...
1
vote
0answers
14 views

Import the same interval of previous week into the deep model

In a dataset, the data are the average of vehicles speed in the points (cells) of a map. I am trying to build a prediction model. While the inputs are the average of vehicles speed of all points in ...
0
votes
0answers
19 views

backpropagation problem from university of Toronto midterm

Here is the question: Consider a 1-layer neural net with three input units, 1 output unit, no hidden units and no bias terms. Suppose that the output unit uses a sigmoid activation function, i.e., y =...
0
votes
1answer
27 views

Where can I find a good machine learning research team /university Lab for a PhD in CS?

I am aiming to do a PhD in Machine Learning and in Germany since I have a Masters in ML already I wanted to know what are the best options to aim for ? Thank you
0
votes
1answer
12 views

Query regarding (.output_shape) parameters used in CNN model

I am applying CNN model on my dataset for predictions. After reshaping the dimensions, the input_shape of my model1 becomes: model1.input_shape: (None, 1, 3, 4) then i apply CNN ist input layer ...
0
votes
1answer
15 views

Combining different features as input to Neural Network

I use two different sources of information as input to my neural model. The model takes a word as input and produces a 1/0 output. I represent each word by using its word embedding (1024 dimensional ...
0
votes
0answers
8 views

Convert generator to DirectoryIterator in Keras

I created a multi input deep learning model, and a lot of functions I could not use it because the testgenerator (in the code) is a generator not a DirectoryIterator. ...
1
vote
0answers
11 views

Transformer architecture not working on toy problem

My transformer is not working on a toy problem. Toy problem Input : Sequence of random integer, one-hot-encoded. Example : ...
0
votes
1answer
28 views

How can I increase the number of iterations per epoch in MATLAB?

I am training a deep learning network using MATLAB and would like to increase the number of iterations per epoch. Using trainingOptions ...
1
vote
0answers
6 views

Confused about transpose convolution and tensor shapes in tensorflow GAN tuturial

https://github.com/tensorflow/tensorflow/blob/r1.11/tensorflow/contrib/eager/python/examples/generative_examples/dcgan.ipynb class Generator(tf.keras.Model): def init(self): super(Generator, ...
1
vote
1answer
23 views

What is non-decomposable and/or non-differentiable loss function?

I have been reading some deep learning literature and came up with these concepts of non-decomposable and non-differentiable loss functions. My question is are these same thing? if not how are they ...
0
votes
0answers
9 views

Conditional DCGAN mystery collapses [closed]

I forked DCGAN and modified it to generate conditional celebA faces. Currently this is my implementation, but my network collapses every time. Here are my results after 20 epochs. Note that only the ...
0
votes
2answers
33 views

Deep Learning Network decreasing in accuracy

In order to familiarize myself with semantic segmentation and convolutional neural networks I am going through this tutorial by MathWorks: Semantic Segmentation Using Deep Learning I did not use the ...
2
votes
1answer
26 views

How does Pooling Layer in CNN introduce invariance to other transformations besides translation

Here is a quote from deeplearningbook which I am trying to process. I am not sure what do they mean by this quote, can someone help me understand please? Pooling over spatial regions produces ...
0
votes
2answers
35 views

Building predictive model with low correlated data [on hold]

I have been working on a project with low features and only few entry fields ( 4 to be exact ). All the data in the dataset is barely correlated to each other. Is there some organized way or ...
2
votes
1answer
18 views

Batch normalization vs batch size

I have noticed that my performance of VGG 16 network gets better if I increase the batch size from $64$ to $256$. I have also observed that, using batch size $64$, ...
0
votes
1answer
20 views

How to use Statistical Learning theory in real analysis

I begin the post trying to say that i don't know if this post is in compliance to community rules, so pardon me for any abuse. I studied back at the university statistical learning theory. I studied ...
1
vote
1answer
23 views

Is Loss not a good indication of performance?

Im trying to segment 3D volumes using a 3D uNet network. Ive reached a stage where I am getting very good validation loss using CrossEntropy and ...
1
vote
1answer
20 views

What brings the performance difference in Deep Learning with different data augmentation strategies?

I am studying the performance of deep learning models toward abnormality detection in chest X-rays. Due to sparsity of data, I augment the data using different augmentation strategies including: ...
0
votes
0answers
10 views

Sequence tokenization and pretrained embedding layers

Sequence tokenization and pretrained embedding initialization - say you have a unique (but not huge) corpus of texts, and you also load a pretrained embedding vector (for example GloVe-100d). What's ...
-1
votes
2answers
33 views

How good will a neural network perform on an unusual data? [closed]

I want to make a simulation based on neural network that will estimate the situation label(not a discrete value) based on state values. Suppose I have data with 40 features/columns and one ...
0
votes
0answers
11 views

Questions about Backpropagation Through Time for Gated Recurrent Unit?

I'm trying to implement it myself so I can understand it more. I ended up deriving the gradients myself. So my understanding is that if $t=T$ is the terminal time index, and suppose you have forward ...
0
votes
0answers
10 views

patched based training of fully convolutional neural network

I have a doubt regarding patch based training. I know it is suggested in supervised learning of classifiers for example, but could the same been said also for fully convolutional autoencoders? If I ...
0
votes
2answers
43 views

Machine learning algorithm for Low dimension input to high dimension output

I am plaining on training a network for body generation, i.e. given some specific measurement,(5 features) the output will be the a set of vertices representing the obj of the bodies. I am wondering ...
0
votes
0answers
16 views

How to dual encode two sentences to show similarity score

I've been trying to grasp the concept of Google's semantic experiences. By using it, I'm planning to implement a semantic query tool. With universal sentence encoder I can first pre-encode all ...