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.

0
votes
0answers
6 views

Autoencoder not overfitting data after large number of epochs and small number of samples

I am training a deep autoeocoder on numerical data, with python jupyter notebook. I have 17 samples, each with 534 values, and my auto encoder has all layers to 534, but even after 5,000 epochs, the ...
0
votes
0answers
13 views

Time Series Forecasting with RNNs

I'm attempting to develop a recurrent model to forecast the value one step into the future (i.e., $x_{t+1}$), given its history $(x_{t-h},\cdots,x_{t})$, where $h$ is a fixed hyperparameter for the ...
1
vote
1answer
8 views

Is Faster RCNN the same thing as VGG-16, RESNET-50, etc… or not?

My understanding is that Faster RCNN is an architecture for performing object detection. It finds objects in an image and classifies them. My understanding is also that VGG-16, RESNET-50, etc... also ...
2
votes
2answers
12 views

Does partial transfer learning require a lot of computer power?

I want to be sure my understanding of the problem is correct. I want to do image classification and current state of the art in my field is achieved by transfer learning with VGG16. Since image on ...
1
vote
2answers
26 views

Neural network got a lucky guess. Can it be trusted?

Say you come across a loss curve as shown below. At which loss should you trust the model? The initial lucky guess or after it has stabilized? And more importantly, why?
0
votes
1answer
12 views

LeCun paper on deeplearning (Nature, 2015)

As I was reading Y. LeCun's paper on Deep Learning (Nature, vol. 521, 2015), I came across a figure (the 1st one in the paper) which was associated to the backward pass during backpropagation through ...
0
votes
0answers
4 views

is “choosing a Q” in chapter 2 in the deep learning book an actual step in eigendecomposition?

eigendecomposition or sometimes spectral decomposition is the factorization of a matrix into a canonical form chapter 2 in the deep learning book says If any two or more eigenvectors share the ...
0
votes
0answers
5 views

Application of Varitiational Auto Encoders in improving the generalizability of classifiers when there is limited amount of data?

Is there any prior work on the above topic? Currently, I am working on Domain Adversarial Neural Networks and merging it with VAE to improve generalizability and transfer learning. I could not find ...
1
vote
0answers
17 views

MCMC for finding Bayesian Neural Network

Is someone familiar with such an approach: Suppose I want to build a bayesian neural network, with distributions over my parameters instead of point estimates. First I train my network with standard ...
1
vote
1answer
16 views

Looking for animals dataset for deep learning classification

Do you know any datasets that contain animals and their accurate classifications? I am looking for any dataset that categorizes animals. For example: a dataset with insects, with an image of an ...
0
votes
1answer
16 views

No gradients provided for any variable

I have composed a customized loss function (kl_loss): ...
2
votes
4answers
45 views

How to get high accuracy in CNNs?

ML and Data Science world. I am a newbie to CNNs, but do possess a basic understanding of ML and Neural Networks. I wanted to create my own CNN that works on the Cats and Dogs Dataset. I ...
0
votes
0answers
13 views

How to Reduce Overfitting of Deeplearning models on NLP tasks in unbalanced datasets?

I have a binary classification problem, where the number of examples belonging to Class 0 is 20% on average. And the rest 80% of examples fall into Class ...
0
votes
0answers
13 views

keras custom metric function how to feed 2 model outputs to a single metric evaluation function

I have an CNN object detection model which has two heads(outputs) with tensor names 'classification' and 'regression'. I want ...
1
vote
1answer
24 views

conv net data retrieval on unseen class

I have build a conv net for image classification which work "well" Now I extract features from last fully connected layer and use it for image retrieval (find image most similar to my target image) ...
0
votes
0answers
13 views

Sequential Learning- How to feed Data?

I have trained neural network model with batch data. Now I want to make predictions using this model, but data for the prediction will be sequential. Is it something should have been taken care in ...
0
votes
0answers
10 views

Difference between globalmaxpoolin1d() and attention layer

What's the difference between globalmaxpoolin1d() and attention layer?
0
votes
1answer
17 views

Predict using a saved regression model

I have trained an ANN model for a regression problem which takes 10 parameters as input and gives 1 output. After training, I saved the model as json and weights as a .h5 file using keras. Now I want ...
0
votes
0answers
9 views

How to generate sequence of text(overall trend) by reading stock price

I would like to generate a sequence of text by reading stock price, this sequence text should contain describing the trend of the stock prices and trajectory. There are two types of input sources, ...
0
votes
1answer
12 views

How is the “loss” calculated which is supplied by the callback log in Keras?

I.e. categorical cross entropy? binary cross entropy? Something else? Or is it perhaps the loss function which you pass into the model.compile method?
2
votes
1answer
23 views

Is conditional GAN supervised learning?

I am trying to understand this paper about conditional GAN, it says that extra information y (class labels) is given to the network. However, I cannot understand its usage during training or its ...
0
votes
0answers
12 views

How to decode text output in autoencoders?

I have made an autoencoder for text based input, and fitted it to the data. Now I want to see the output text. Is there any way to decode the numbers to text? ...
0
votes
0answers
19 views

How do I find the distance between the truck and the lane?

I have a bunch of images from different trucks passing the road. The truck needs to be at a certain distance from the lane. Some of the trucks are way close to the lane (that you can see on the ...
0
votes
0answers
24 views

Stock price forecasting example with LSTM or GRU that beats a simple persistence forecast

There are lots of examples in the internet about how to do predict time series. However, they all suffer from at least one of the following problems: tiny data set (like the "shampoo sales" with a ...
0
votes
3answers
39 views

How to know when to stop trainning a deep network?

I've been training several auto encoders containing two GRUs as encoder and decoder during last year. It occurred to me that ...
0
votes
0answers
28 views

In an RNN, if the gradients don't vanish for long/distant terms, won't the derivative of the error be either divergent to infinity or oscillatory?

P.S. Crosss posted here- https://stats.stackexchange.com/questions/413843/in-an-rnn-if-the-gradients-dont-vanish-for-long-distant-terms-wont-the-deriv, as I've got no answer, I'm asking here: In my ...
0
votes
0answers
20 views

Transfer learning on yolo using keras

I am working on a project that uses object detection. I have logo images that need to be detected in a video. I am doing this in keras. I followed this blog to convert the yolo weights to a keras ...
1
vote
1answer
30 views

Strange binary classification result with a model that indicate it has been well-trained

The problem : I am trying to build a model for binary classification for melanoma 'MEL' and nevus 'NV' the dataset is from ISIC archive ISIC 2019 but for 8 different type of skin lesion, I am using ...
0
votes
0answers
12 views

What change should I make in the Image Data Generator to solve the error? [closed]

I am trying to perform Mixup Augmentation (details here) but I am getting a value error as follows : ...
0
votes
0answers
25 views

Python Machine Learning for Data Generation

I am trying to learn machine learning with Python for a specific application to see if it's doable, right now it's just an idea. The goal is to generate or improve meshes for CFD simulations using ML, ...
0
votes
4answers
33 views

Keras model giving error when fields of unseen test data and train data are not same

I have created a simple Keras deep learning model in python. Total no of variables in training are 195 while in unseen test data are 181.All input fields are categorical(converted by one hot encoding)....
4
votes
2answers
47 views

What is a YAML file and where is it used in a machine learning context?

I am not entirely sure if this is on-topic here, so please let me know if it is not. I keep seeing the idea of YAML files pop up while reading machine learning literature. My question is, what exactly ...
1
vote
1answer
22 views

Generating Synthetic Image to improve the performance of classifier

I need some suggestion from experts. For my project work, I have been learning about Generative Adversarial Network. I am trying to make a ...
0
votes
0answers
17 views

Data extraction from documents using NLP and ML [closed]

How do you extract data from documents? As an example, consider an application form which I would like to extract data from. Such as applicant name, application number, etc. The thing is, I wasn't ...
0
votes
0answers
7 views

Algorithm for automatic annotation with landmarks

I worked on iris detection in real-time using deep learning, so it so hard to get an annotated dataset for iris detection with landmarks, and manually annotation takes a long time and this work should ...
0
votes
0answers
7 views

Predicting tool breakage on a CNC/VMC machine using Machine Learning?

I data of a fixture (which holds a component during machining) as vibration in 3 direction, the pressure of hydraulic, and proximity. I would like to know when the tool might get broken in the near ...
0
votes
0answers
21 views

Error propagation in Time series forecast with many-to-many multi-steps RNN/LSTM

I am trying to do a many-to-many time series forecast, which features an encoder-decoder model to predict with variable input and fixed prediction period. In my case, I want to predict for the future ...
0
votes
0answers
9 views

Converting our model to other formats

I am using NVIDIA platform for running some medical imaging workflows. I came to know that NVIDIA accepts model only in the below formats a) graph def b) saved model c) trt plans d) caffe netdefs ...
0
votes
0answers
11 views

Deep Learning - Predict the relative order of data

I am facing a problem in which i want to predict the order of data. I was searching for research papers, however i do not know how this problem is named in academia. I encountered the following well ...
0
votes
0answers
20 views

Test set error significantly less than training set error

I am trying to model an decoder(for specifics of it, refer to the details below) using a MLP. But I am getting strange results. Metric being used here is the bit error rate (ber). My training set and ...
2
votes
0answers
13 views

Best practices for scaling data science / engineering teams

I am trying to find best practices for scaling data science teams, i.e find an efficient workflow/methodology to divide work between Software Engineers and Researchers working on a same product. I’...
0
votes
0answers
17 views

Help needed implementing Convolutional Sequence-to-Sequence Network

I am trying to build convolutional Sequence-to-Sequence network that takes inputs (satellite images) and predicts the next sequence of images. As a result, we can then predict the weather. I have ...
1
vote
1answer
18 views

What are the input and output channels of a convolution in PyTorch?

From the documentation of Pytorch for Convolution, I saw the function torch.nn.Conv1d requires users to pass the parameters "in_channels" and "out_channels". I know they refer to input channels and ...
2
votes
0answers
7 views

wavenet structure explanation

I am a beginner in deep learning and recently I am trying to understand the structure of Wavenet. (for more information, please refer to the paper http://sergeiturukin.com/2017/03/02/wavenet.html) ...
3
votes
2answers
34 views

Multiclass classification of textual data

I have a problem statement in which I have to classify the text data into various classes, but the training data is very less (250-300 data points for 4 classes). I am confused about what approach to ...
3
votes
4answers
63 views

What does embedding mean in machine learning?

I just met a terminology called "embedding" in a paper regarding deep learning. The context is "multi-modal embedding" My guess: embedding of something is extract some feature of sth,to form a vector....
0
votes
0answers
11 views

Q learning advantages

what is the advantages and disadvantages of using Q function in reinforcement learning comparing to other method such as policy gradient
1
vote
3answers
71 views