Questions tagged [training]

The tag has no usage guidance.

147 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
46 views

Help interpreting GAN output, and how to fix it?

After a few tries, I had trained a GAN to produce semi-sensible output. In this model, it almost instantly found a solution and got stuck there. The loss for both the discriminator and generator were ...
3
votes
0answers
33 views

Repeated k-fold Cross Validation for time series data?

I have a relative small sample size (330 with 45 features) + it's time series data. I want to train my LightGBM regression model for best generalized RMSE score and want to use repeated CV. I use ...
3
votes
0answers
39 views

NN training with repetitive features

I posted the question also on ai.stackexchange but it didn't get any answers so I though I could try here. Here is a copy paste: Let's say you are training a NN in a RL setting where the state (i.e. ...
3
votes
1answer
64 views

How to deal with annotation errors?

I know my annotators are not perfect, sometimes making mistakes. What would be the best way to deal with the annotation errors for my training data? Thanks!
3
votes
1answer
407 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 ...
3
votes
0answers
34 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 ...
3
votes
1answer
51 views

Validation data shall be in broken down into batches or not?

I am using fit_generator to train the model. The training dataset is being read from a generator function which gives data in a constant batch size. Now I want to ...
3
votes
0answers
165 views

Training deep CNN with noisy dataset

I am training a Mask RCNN model with a train dataset that has been generated from some simple computer vision operations (color thresholding) and some morphological filtering. The train set captures ...
3
votes
0answers
271 views

How to add a new label to a multi-label dataset (like Open Images)

Given N classes in a multi-label dataset and a trained classifier C, how would we add a new class N+1 to the dataset, and fine-tune the trained classifier C such that it now predicts N+1 labels? (lets ...
2
votes
1answer
33 views

what does the standard deviation plot around my learning curve indicate?

I plotted a learning curve below. There is a thick red band around the top portion of my training score. Why is it so high at the beginning? Below is a snippet of the code used: ...
2
votes
0answers
24 views

In YOLO training, what if two objects' centers fall in the same grid?

As I know, YOLO predicts one classification result (as well as some bounding boxes) for each grid. But when training yolo, what if two or more objects' centers fall in the same grid? How to choose the ...
2
votes
1answer
82 views

Making sense of loss and accuracy curves

This is an issue that I have come across over and over again. Loss (cross-entropy in this case) and accuracy plots that do not make sense. Here is an example: Here, I’m training a ReNet18 on CIFAR10. ...
2
votes
1answer
58 views

Setting BATCH SIZE when performing multi-class classification with imbalanced dataset

I have a question regarding BATCH_SIZE on multi-class classification task with imbalanced data. I have 5 classes and a small dataset of around ...
2
votes
0answers
14 views

What is the appropriate approach for training time series data against multiple, consecutive labels?

Let's say we have a time series $\{{\bf x}_i\}$ of features and are trying to learn to predict a time series $\{t_i\}$ using a neural network. Our goal is to be able to predict the time series value $...
2
votes
0answers
19 views

Training pipelines where featurization/NLP is more expensive than backprop

I'm working on a document classification project and I'm using a neural net in tensorflow, where the features are 300-dimensional word embeddings, either from fastext or word2vec (yes I know that ...
2
votes
1answer
88 views

How to re-train a model from false positives

I'm still a bit new to deep learning. What I'm still struggling, is what is the best practice in re-training a good model over time? I've trained a deep model for my binary classification problem (...
2
votes
2answers
3k 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
845 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 ...
2
votes
2answers
42 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. ...
2
votes
1answer
68 views

Training a model where each response in the observation data has a different known varience

I have a dataset where each response variable is the number of successes of N Bernoulli trials with N and p (the probability of success) being different for each observation. The goal is to train a ...
2
votes
1answer
113 views

Training data : forecasted or actual?

I am working on a time series prediction problem. I am using keras models for machine learning. For this prediction, weather variables are used as input. They can be of two types: forecasted and ...
2
votes
0answers
64 views

Replacing mean by median over batch-size to lessen the impact of outliers

In the case of training a Neural Network on a regression task. Assuming the data has a significant amount of outliers. Provided that the error needs to be RMS and not MAE. Can it be better (as in less ...
2
votes
0answers
56 views

Performance diagnostics in mxnet gluon (e.g. plotting training vs validation loss over time)?

Tensorflow has tensorboard, is there any recommended way to plot classification error/loss over time in mxnet?
2
votes
0answers
29 views

Correct approach to usage of class labels in cell imaging data

As part of a group project at university, we are given a series of videos of cell cultures over a 24 hour period. A number of these cells (the "knockout" cells) have had a particular gene removed, ...
2
votes
0answers
663 views

How to train the generator in a recurrent GAN (Keras)

I am trying to train a Recurrent GAN that is meant to generate geospatial movement data (sequences of 3-tuples of latitude, longitude and time). You may simply consider it a sequences of vectors with ...
2
votes
0answers
156 views

How to resolve the instability of average reward per episode in training of DQN (Deep Q-Network)?

what is shown when average reward per episode in training is unstable? If there is big difference between average reward per episode and final reward by test section, what we can say? For instance in ...
2
votes
0answers
25 views

Force Neural Net to attempt to predict every class

I am training a (deep) neural net to classify approximately 60 different classes. The range of occurrences of each class in the dataset is wide, 3 orders of magnitude from the most represented to the ...
2
votes
0answers
398 views

Matlab: setting static iterations per epoch in a CNN

I'm building a convolutional neural network using Matlab's neural network toolbox. I have code designed to cross-train the network with different data sets, using the previous network's layers in ...
2
votes
0answers
26 views

keras evaulate method results vary with equal testset

I trained segnet on a dataset of remote sensing imagery. When I run model.evaluate a set of metrics is returned. When I compile the model again with the same ...
2
votes
0answers
995 views

Backpropagation with step or threshold activation function

I understand that gradient descent is local and it deals only with the inputs to the neuron, what it outputs and what it should output. In all I've seen, gradient descent needs the activation function ...
2
votes
0answers
36 views

Term for Methods of Representing Repeated Text in Classifier

A colleague told me that there are terms for two different methods of representing repeated text in the training set for a classifier, but he could not recall them. What are the terms for the options ...
2
votes
0answers
70 views

How to select samples for a trainings set

My dataset contains half a million unlabeled entries with over 100 binary features. A third of these features are present in less than 1000 samples. I want to classify a few samples by hand (into ...
2
votes
1answer
158 views

Ideal difference in the training accuracy and testing accuracy

In a data classification problem (with supervised learning), what should be the ideal difference in the training set accuracy and testing set accuracy? What should be the ideal range? Is a difference ...
2
votes
0answers
142 views

Multiple models vs. Single model for prediction

I am using the Darknet Convolutional Neural Networks to detect people (as in, humans) and furniture in a single image. If I train the model twice, one for people, one for furniture. I seem to get ...
1
vote
1answer
22 views

What am I supposed to see on tensorboard images tab?

I'm training an object detection model with Tensorflow and monitor the training task with tensorboard. I was expecting in the Images tab of tensorboard that displayed images would show a bounding box (...
1
vote
2answers
31 views

Will my validation loss eventually go down?

I'm currently training a binary classifier that takes in 2 inputs, and outputs which object it thinks is "better." I have an absolutely massive dataset, about 2 trillion records, and I'm ...
1
vote
1answer
40 views

what is the complexity of a bidirectional recurrent neural network?

In particular, what is the complexity of a bi-directional recurrent neural network taking into account the variants of LSTM and GRU as well for training? I am hoping if I can get links to some ...
1
vote
0answers
17 views

How to train Ngram models

i am fairly new to Natural language processing and a might be misunderstanding some concept of of it, i am doing some homework: Training N-GRAMS i wanted to know ...
1
vote
1answer
36 views

Hypothesis vs Hyperplane in Machine Learning

I am finding it hard to understand the clear difference between Hypothesis and Hyperplane. I know that Hypothesis is a candidate model that maps inputs to outputs after training . And , Hyperplane is ...
1
vote
2answers
39 views

What is the purpose of the 'train model' step in data mining?

My understanding is that training a model is something done in machine learning using training data so that the model can predict values when new data is given to it. Data mining is the process to ...
1
vote
0answers
24 views

libraries for multiple machine NN training?

As detailed here, the way to go to break NN training over multiple machines/threads, is decompose training data set on multiple chunks and send to each node, then sum results back in main node. There ...
1
vote
1answer
20 views

GRU and LSTM does not “take risk” predicting

I tested LSTM and GRU models to predict the exchange rate between currencies. I do not take the raw price but a the delta with the previous day, so the data is stationnary around zero. My problem is ...
1
vote
0answers
37 views

Fine tuning a automatic speech recognition model with my own dataset

I'm using wav2letter to develop a speech-to-text system. wav2letter has pre-built acoustic and language models which is great, however the audio that I am transcribing from is unique in comparison to ...
1
vote
0answers
8 views

Checkerboard artefacts vs distinct objects in GANs

I found a very good solution for getting rid of checkerboard artefacts in GANs: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/190 Instead of using Transposed Convolution, use bilinear ...
1
vote
0answers
35 views

Will setting up time series data in this way cause data leakage?

I am trying to predict future stock market values using a gradient boosted tree model. As far as I know, gradient boosted trees use the data in one row, and only that row, to predict the target ...
1
vote
1answer
30 views

How to calculate change in Loss Function w.r.t Weights for a fully connected NN

I read this article: Optimal Brain Damage by Yann LeCun, John S. Denker and Sara A. Solla. where the authors discuss about estimating the saliency of each weight of a neural network, which they define ...
1
vote
1answer
18 views

What's the best way to train a model when having a very big dataset split in batches?

I was wondering what is the best way to train my Keras Model, in a binary classification context. My full dataset is composed of 2.3M rows and 120 columns, which is really big. As you would imagine, ...
1
vote
1answer
25 views

Label A records B times or label A*B records

This question concerns pre-training data sourcing. Suppose you have a human workforce of B individuals and a potentially unlimited source of data. The task is ...
1
vote
0answers
12 views

Defining objects in training data for deep learning

I am performing end-to-end deep learning in ArcGIS Pro 2.5, following a similar procedure to the one set out in this tutorial: https://learn.arcgis.com/en/projects/use-deep-learning-to-assess-palm-...
1
vote
0answers
12 views

Solving Feature Distribution variance between Training and Prediction for Ranking models

I am building a linear regression model to improve ranking of documents. And trying to identify problems due to which model performance estimates don't match actual impact One major problem is ...