Questions tagged [training]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0
votes
2answers
16 views

How to deal with a feature that has lot of categorical values?

I know this question has been asked before and I have tried a few things but those things are not working as expected for my usecase. I have a 500 length feature vector. One of these features is a ...
0
votes
0answers
10 views

Beating Roulette with Neural Networks, YoloV3, and PyTorch

Background: I am in my last semester of electrical engineering, and I am working on my senior design project. The senior design project is a two-semester design project in which students outline, or ...
1
vote
1answer
19 views

Accuracy noise patterns during model training

I'm training a logistic regression model on a small dataset. I have about 1300 samples that I split into a training and a testing set (70% and 30% respectively). The training seems ok, however when I ...
1
vote
0answers
35 views

Data leak when training on future data and testing on present [closed]

Given a time series dataset. Using simple train_test_split, then reversing the train to test and test to train i.e. using the future data to train and present data to test, where does one induce leak ...
0
votes
2answers
34 views

What can be the cause of a sudden explosion in the loss when training a CNN (Deeplab)

I am training the following deeplab CNN: https://github.com/tensorflow/models/tree/master/research/deeplab During training I see the following loss: The first 50k steps of the training the loss is ...
2
votes
1answer
40 views

Given a machine learning algorithm, what is the minimum size of the training set for it?

I understand that the more data we have, the more reliable is our model trained on that data. I also understand that the more parameters a machine learning model has, the more training data it ...
0
votes
0answers
9 views

Shrink the training set during the learning process

Is there any way to change the size of the training set during the learning process? For example, let's say we have four classes (with their distribution): [A (90%), B (5%), C(2%), D(3%)]. Can we ...
0
votes
1answer
11 views

LSTM loss function and backpropagation

I'm trying to understand the connection between loss function and backpropagation. From what I understood until now, backpropagation is used to get and update matrices and bias used in forward ...
1
vote
1answer
65 views

Training an ensemble of small neural networks efficiently in TensorFlow 2

I have a bunch of small neural networks (say, 5 to 50 feed-forward neural networks with only two hidden layers with 10-100 neurons each), which differ only in the weight initialization. I want to ...
0
votes
0answers
18 views

How to prepare training data for deep learning models

I am working on a project which involves the application of deep learning models. I have collected training data. In collected images, I have more than one object in interest. I am not very clear how ...
2
votes
1answer
53 views

how is correct usage of the validation split in neural networks?

I have a dataset separated in train, test and validation splits. After each epoch, I evaluate the loss and accuracy in the validation split. When the loss in validation split is not better, I stop ...
0
votes
1answer
33 views

How to deal with a constant value as an output from neural network?

I am using feedforward neural network for regression and what I get as a result of prediction is a constant value visible on the graph below: Data I use are typical standardised tabular numbers. The ...
2
votes
1answer
24 views

On design of the training set: conceptual question

I am curious to know how training data should be constructed so that it scales to examples that are not a part of the training data. For example, the problem that I am facing right now is in the ...
2
votes
2answers
36 views

Resampling for imbalaced datasets: should testing set also be resampled?

Apologies for what is probably a basic question but I have not been able to find a definitive answer either in the literature or in the Internet. When dealing with an imbalanced dataset one possible ...
0
votes
1answer
16 views

Should inputs be shuffled for training a model with expected time dependency?

Consider a prediction model with numerical inputs and outputs. Suppose data is inserted tick by tick, i.e., when new data is available it is inserted asynchronously. Current output depends on current ...
0
votes
0answers
10 views

SRCNN - the colors disappear from the output

I'm training a custom CNN (built for academic purpose) to perform Super-Resolution. I based my work on this review. The input of the network is a RGB color image, so 3 channels of size image_width x ...
1
vote
2answers
46 views

Splitting training and test set with financial data

I am using trees algorithms (decision tree, random forest and XGBoost) to forecast the sign of the returns in the stock market (classification). I am using this article as a reference: http://...
0
votes
1answer
43 views

DC GAN with Batch Normalization not working

I'm trying to implement DC GAN as they have described in the paper. Specifically, they mention the below points Use strided convolutions instead of pooling or upsampling layers. Use only one fully ...
1
vote
2answers
42 views

Which service could I use to train my networks?

My laptop's Intel i7 3630QM 2.4GHZ, 8Gb RAM and GXForce 670M are clearly not sufficient... By reading some papers, I've written an SRGAN with Python Keras. At runtime there is no error but training ...
2
votes
2answers
25 views

How to gather training data for simple voice commands?

I'm trying to build a machine learning model for recognizing simple voice commands like up, down, left, etc. On similar problems based on images, I'd just take the picture and assign a label to it. ...
0
votes
0answers
22 views

Architecture choice for variable input dimension sizes

So, I am doing this project where I have lets say a bunch of points. Each of those points can have a different number of RGB values. So lets say point 1 might have 30 RGB values, point 2 might have ...
0
votes
0answers
23 views

LSTM validation loss not improving

I'm a noob in the ML world and am currently building an LSTM to forecast the next page a user is going to visit on a website. My dataset is pretty much a mapping (with sliding window) from one page to ...
0
votes
0answers
15 views

Neural Network to generate data for another network?

I was wondering if its possible to develop and train a neural network that generates training data for another network (or possibly itself). I came to this thought wondering the difficulty in creating ...
0
votes
0answers
15 views

How strong is the generalization ability of YOLO?

I have a question about the generalization ability of YOLO or deep learning methods in general: I am working on vehicle detection and classification in highway traffic surveillance videos. As you ...
0
votes
1answer
13 views

Is it okay to use training data for validifying the trained model?

Currently, I have trained my model through 5-fold cross validation with very small amount of the sample (n=240). I used whole data set to train and got quite low performance in terms of accuracy, ...
3
votes
2answers
187 views

In the context of Deep Learning, what is training warmup steps

I found this term "training warmup steps" in some of the papers, what exactly does this term mean? Has it got anything to do with "learning rate"? If so, how does it affect?
1
vote
1answer
45 views

How to split a dataset into train and test sets for time series (multiple step-multiple output forecasting)?

I am trying to use a LSTM neural net to do multiple step / multiple output forecasting (I predict multiple values in one time knowing some values in the past). But, I have realized that I must be ...
2
votes
2answers
66 views

Is it correct to join training and validation set before inferring on test-set?

I would like to know if is a correct procedure to join training-set and validation-set together, in order to train the model on ...
1
vote
1answer
40 views

Neural network is getting partially trained

So I am writing my own neural network library using back-propagation as my training algorithm. Everything seems fine the error is getting decreased more and more at each iteration however when I am ...
1
vote
2answers
30 views

How to transform time series data to apply supervised learning algorithms to it?

Apologies in advance for what may be a very basic question. I have a dataset consisting of marketing calls to different clients, which include the timestamp for the call. My goal is to train a model ...
2
votes
0answers
25 views

How does permutation of training data improve convergence time when training a perceptron or neural network model? [duplicate]

I'm currently studying some basic concepts regarding Deep Learning and Neural Networks with this material. When discussing the training algorithm for a perceptron, the author states that looping ...
0
votes
0answers
25 views

Transformer for neural machine translation: is it possible to predict each word in the target sentence in a single forward pass?

I want to replicate the Transformer from the paper Attention Is All You Need in PyTorch. My question is about the decoder branch of the Transformer. If I understand correctly, given a sentence in the ...
1
vote
1answer
23 views

How interpret keras training loss without compare with validation loss?

I have several implementation of the same neural network, but each one with different starting parameter. This is one of my plot comparing the training loss of the base experiment with the training ...
0
votes
0answers
10 views

How to check performance of a model on a test set?

I have transformed my training set (predictor variables) using step_YeoJohnson for satisfying the assumptions of model. But now how do I run my model on test set which is not transformed and has ...
0
votes
0answers
23 views

Creating artificial blurred image to train neural network for super resolution

I would like to create blurred images from images obtained from large pdf with the intention of creating a training data set. I would like to create the blur as shown in the uploaded picture. Which ...
0
votes
0answers
16 views

Is there any formula that estimates the training time of a CNN?

Is there any formula which estimates the training time of a CNN? (with respect to the number of layers, the size of the dataset ...
2
votes
1answer
103 views

Smart data split (train/eval) for Object Detection

I am looking for a smart way of splitting object detection data (images with labelled objects inside them) while taking into account the distribution of the objects themselves and not just the images. ...
0
votes
3answers
59 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
8 views

Looking for approaches to large scale NER train test split without overlaps

I would like to train test split a list of texts with the associated entities so there are no entities overlapping splits. Ensuring no overlaps is challenging: I currently achieve it with 2 groupby ...
5
votes
1answer
69 views

Why could an overfitted CNN model have a higher validation accuracy?

I am currently training a CNN model by using cifar10 images (50000 for training, another 10000 for validation). I plot training loss, validation loss and accuracy against training iteration: I am ...
2
votes
1answer
38 views

How to predict based on multiple samples?

I am relatively new to ML so I apologies in advance if my question shows lack of understating of the field. The problem A particular study course has a high drop-out rate and we want to reduce it. ...
3
votes
0answers
26 views

A Deep CNN model delivering better results with standardization, when compared with normalization

I developed a deep CNN model, based on the architecture discussed in this paper, to generate predictions for time series data. My training data is shown in the figure below: In order to train the ...
0
votes
1answer
27 views

Ideal score of a model on training and cross validation data

The question is little bit broad, but I could not find any concrete explanation anywhere, hence decided to ask the experts here. I have trained a classifier model for binary classification task. Now ...
0
votes
1answer
31 views

Potential problems with expanding training set

The problem is a binary classification one. My dataset contains users with activity over multiple days, where they all start with class 0 and can become class 1 after a certain activity (which is not ...
0
votes
1answer
35 views

What could make a set of the train data more predictive than the whole train data

I took a sample of my training data and balanced it and then trained my model. The results obtained are more accurate than using the whole set of train data (balanced or imbalanced). My question is: ...
0
votes
1answer
82 views

Do we have to split our dataset into training & testing when using ARIMA model?

I am working on a project where I predict the total quantities sold at the ITEM/DAY leve. As for the model, I decided to with an ARIMA model (I'm using R). For guidance, I decided to follow the two ...
3
votes
1answer
123 views

Does increasing kernel size in a CNN result in higher accuracy on the training set?

In a convolutional neural network, does increasing the size of kernel always result in better training set accuracy? For example, if I use 5x5 kernels in a CNN instead of 3x3 ones, will it always ...
0
votes
0answers
9 views

What research exists to help design training data sets where contamination due to privacy is an issue?

Suppose one is building a classifier that: takes as input the e-mail body text returns true or false if person X should be included in the address list To build this classifier we have historical ...
1
vote
1answer
18 views

Model biased towards low frequency data?

Generally model gets biased towards data_samples/target whose frequency is high in training data set. Is it possible during training that model gets biased towards low frequency training data set.
0
votes
0answers
13 views

The principle and understanding of adversarial training

In the paper《ADVERSARIAL TRAINING METHODS FOR SEMI-SUPERVISED TEXT CLASSIFICATION》and its related papers. The researcher apply the adversarial perturbation to word embeddings. Why do this methods ...