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
2
votes
1answer
140 views

Understanding Youtube recommender (candidate generation step)

I'm trying to understand https://storage.googleapis.com/pub-tools-public-publication-data/pdf/45530.pdf Their candidate generation step outputs topn items via softmax (with negative sampling) at ...
1
vote
3answers
25 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 ...
0
votes
1answer
85 views

CNN image to image translation: multiple image inputs to one image output

I am interested in training a CNN to take in inputs where each input is a set of low-resolution images and each ground truth is a single high-resolution image. The ground truth high-resolution image ...
0
votes
2answers
80 views

what is the difference between euclidean distance and RMSE?

I'm searching for a loss function that fits my Project. Actually I have two question but they are in the same direction. I take a look at the definition of the root mean squared error and the ...
0
votes
0answers
16 views

Meta learning - what exactly support set means?

In the defining of meta learning two set of data is sampled from original dataset : support set - S and mini batch - B. If mini batch is the one on which learner is trained, then what exactly is ...
0
votes
1answer
29 views

Does adding of many FC layers during re-training increase the model size ? Are there any ways to optimize the size of model?

I am re-training a pretrained model VGG16. In the last layers, im using two FC layers of size 2048 each, with dropout=0.5. When i saved the model, The size of the model was found to be 2 GB (which ...
1
vote
0answers
15 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
7 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
1answer
41 views

How to detect if a person is interacting (as in touching) some object in an image?

I am currently working on a human interaction problem, which tries to identify if a person touched a predefined object. Current Approach: I am using open-pose to estimate the pose of the person then ...
4
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 ...
98
votes
6answers
80k views

When to use GRU over LSTM?

The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates). Why do we make use of GRU ...
0
votes
1answer
122 views

what is correct way to perform normalization on data in Auto encoder?

working on anomaly detection problem. i'm using auto-encoder to denoise given input. I trained network with normal data(anomaly free). so model predict normal state of given input. Normalization of ...
2
votes
1answer
544 views

Is GEMM used in Tensorflow, Theano, Pytorch

I know that Caffe uses GEneral Matrix to Matrix Multiplication (GEMM) which is part of Basic Linear Algebra Subprograms (BLAS) library for performing convolution operations. Where a convolution is ...
0
votes
0answers
6 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
2answers
65 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
3answers
543 views

Detect the time at which deviation occurs in time series data

I working on multivariate time series data. I have sensor data generated by a machine every time it is operated. Data set consists of machine_ID(machines of same model), hours_ operated, measurements ...
2
votes
2answers
35 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.
2
votes
2answers
84 views

optimal combination of hyper parameters and model selection

This is a general question which often comes up when tuning deep learning and machine learning algorithms such as recurrent neural network, multilayer perceptron or SVM etc. When we tune the hyper ...
2
votes
0answers
7 views

Checkerboard artifacts output using a FCN8

I am using FCN8 to do texture segmentation. However, my output is always this weird checkboard. I read that it might be related with my NN architecture or weights initialization and I would like to ...
0
votes
1answer
182 views

How can I detect anomalies/outliers in my online streaming data on a real-time basis?

Say, I've a huge set of data(infinite in size) consisting of alternating sine wave and step pulses one after the other. What I want from my model is to parse the data sequence wise or point wise and ...
2
votes
1answer
43 views

How can I know the name of the features selected by a Deep Belief Network?

I want to use DBN to reduce the 41 features of nslkdd dataset after transforming nominal data to numeric the number of features increases from 41 to 121 . I used 3 RBMs (121-50-10) now I want to know ...
0
votes
1answer
23 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 ...
1
vote
2answers
446 views

error when input function called with shape (2,2)

I am new to Tensorflow and machine learning. I am trying to use high level API from Tensorflow. Please tell me what i am doing wrong. ...
6
votes
1answer
78 views

how to generate automatically images meshing up different shapes with a deep learning software?

My pursuite is to generate something like a grottesque(a kind of painting producing human-animals and plants hybrids). I need to do something like this paints in order to create an art exhibition. I ...
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
3answers
805 views

Training LSTM with different sequence lengths in Keras functional api

I am trying to train an LSTM model using Keras functional API. My training data is of shape: >>> data.shape() (100000,variable_sequence_lengths,295) ...
1
vote
1answer
120 views

Intuitive explanation of Lovasz Softmax loss for Image Segmentation problems

Lovasz Softmax is used a lot these days for segmentation problem and the original paper is really bad at explaining why it works.
2
votes
0answers
30 views

How do I use the supervised learning classification in my project? [closed]

Just to give an idea of what I'm doing: I'm doing a project with financial data (tick data) and I'm trying to create a way make a model learn what happens before a breakout. Usually there ...
1
vote
1answer
168 views

What is the difference between TextGAN and LM for text generation?

I'm new to LeakGAN or SeqGAN or TextGAN. I know GAN is to generate text and let discriminator un-judge-able to real text and gen-text. LM(language model) is the task of predicting the next word and ...
1
vote
2answers
29 views

What is the dimension of the filters if the input image has only one channel?

I have a grayscale image with dimension HxWx1 (one channel). To build a CNN using the grayscale image as an input image, what is the dimension of the filters? I read from some websites, it says that ...
0
votes
1answer
157 views

Architecture for multivariate multi-time-series model where some features are TS specific and some features are global

I'm looking to build a time series model (using a TCN or a LSTM) with $N$ different series, each of which has $P$ series-specific features $\mathbf{X}$. My input array is of dimension $N \times t \...
35
votes
3answers
35k views

Multi GPU in keras

How we can program in the keras library (or tensorflow) to partition training on multiple GPUs? Let's say that you are in an Amazon ec2 instance that has 8 GPU's and you would like to use all of them ...
1
vote
1answer
26 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 ...
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 ...
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 ...
5
votes
1answer
43 views

How to train the predicting boxes in a YOLO network?

I have just finished this tutorial that explains how YOLO networks work. Instead of training the network's weights with a training set, the author loads pre-trained weights and uses them to test the ...
4
votes
1answer
1k views

Gradient flow through concatenation operation

I need help in understanding the gradient flow through a concatenation operation. I'm implementing a network (mostly a CNN) which has a concatenation operation (in pytorch). The network is defined ...
2
votes
1answer
167 views

How does BERT deal with catastrophic forgetting?

In the ULMFit paper authors propose a strategy of gradual unfreezing in order to deal with catastrophic forgetting. That is, when the model starts be fine-tuned according to a downstream task, there ...
88
votes
9answers
90k views

Choosing a learning rate

I'm currently working on implementing Stochastic Gradient Descent, SGD, for neural nets using back-propagation, and while I understand its purpose I have some ...
3
votes
1answer
76 views

Is it a red flag that increasing the number of parameters makes the model less able to overfit small amounts of data?

I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~...
2
votes
1answer
407 views

How to choose the best optimiser in Deep Learning algorithms?

I have been training a CNN to classify 4 faulty (acoustic emission/250KhZ) signals. I have no problem in implementing the algorithm using tensorflow libraries, but I am confused with which optimizer ...
0
votes
1answer
54 views

Encoder-Decoder performance time

I have two encoder-decoder models. *First model: *Second model: When I check the performance of the models I get approximately the same performance time (First model ~ 42 sec, Second model ~ 40 ...
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
24 views

Approach fpr extracting/cropping features images using deeplearning and no annotations

Let's say I want to have a bunch of images of hats from videos. How would I priniciple build something that would learn to recognize, and crop or bound box hats? I heard you need a dataset with ...
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 ...
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 ...
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 ...
0
votes
1answer
21 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 ...
2
votes
1answer
792 views

What is the difference between shuffle in fit_generator and shuffle in flow_from_directory?

I am using Keras to create a deep learning model and I would like to know that what is the difference between shuffle argument in ...