Questions tagged [training]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
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
1answer
104 views
1
vote
0answers
26 views

Unexpected shape of “training curves” in NN

I'm trying to find the best configuration for my NN (in terms of batch size, learning rate etc) and noticed the following unexpected behavior. The AUC scores, computed on validation data, as ...
5
votes
2answers
366 views

Why do most GAN (Generative Adversarial Network) implementations have symmetric discriminator and generator architectures?

For example, if the discriminator is a vanilla network of n layers, each with n(i) units, then, typically, the generator will also be a vanilla network of n layers, each with n(n-i) units (except the ...
2
votes
5answers
184 views

Face Recognition (Scalability Issue)

Background I would like to build a face recognition model for registration and login for some kind of service. For example, using this approach (CNN + SVM). When a new user wants to register a ...
2
votes
1answer
644 views

Training a convolutional neural network for image denoising in Matlab

I am currently trying to train CNNs to remove Poisson noise from images. The software I am using is Matlab 2018b, however the results I am getting are poor. I have followed the steps provided in the ...
0
votes
1answer
101 views

Confusion on Delta Rule and Error

I'm currently reading Mitchell's book for Machine Learning, and he just started gradient descent. There's one part that's really confusing me. At one point, he gives this equation for the error of a ...
0
votes
2answers
468 views

Normalization before or after resizing

I'm training deep learning network using images (to be exact - I'm solving semantic segmentation problem). What's the proper order of resizing (I need to resize images to fixed width X height) and ...
1
vote
0answers
216 views

“10-year-challenge” data for age algorithms? [closed]

Both on FB and IG, I see people posting themselves before 10y and now. I have no idea how this challenge started. Could it be a way to collect a colossal amount of data, that could be used to train ...
0
votes
1answer
77 views

Difference in labelling and normalizing train/test data

I am working on a dataset comprised of almost 17000 data points. Since it's a financial dataset and the components are many different companies, I need necessarily to split it by date. Therefore, ...
1
vote
3answers
1k views

Is it possible to make a CS:GO Machine Learning AI? [closed]

I am not an expert on Machine Learning, Neural Networks or NEAT. In fact, I probably have no clue what I'm talking about. My question is if you can make a learning AI that learns to play complex ...
1
vote
0answers
30 views

Strangeness in validation loss between CPU vs GPU when training CNN

I've been training an implementation of Mask R-CNN and it was training very successfully on my CPU but I've just set up my GPU and it is giving some strange results when looking at my validation loss. ...
2
votes
0answers
585 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 ...
1
vote
1answer
172 views

Conjugated gradient method. What is an A-matrix in case of neural networks

I am reading about conjugated gradient methods to understand how they exactly work. I understand that a pair of vector $u$ and $v$ are conjugated with respect to $A$ if $u^TAv=0$. I also read that $A$ ...
2
votes
4answers
283 views

Neural Network unseen data performance

I started dabbling in neural networks quite recently and encountered a situation which is quite strange (at least with my limited knowledge). The problem I'm using a NN is a regression problem which ...
3
votes
2answers
1k views

What's the advantage of multi-gpu training in real?

The decreasing speed of training loss is almost the same between one gpu and multi-gpu. After averaging the gradients, the only benefit from multi-gpu is that the model seems to see more data in the ...
2
votes
1answer
162 views

Sequential Modelling: Multiple Sequence to One or Sequence to Sequence

Suppose I have a single sequence of $x_1, x_2, ..., x_n$ and corresponding labels $y_1, y_2, ..., y_n$. An example would be a person makes website visits $x_i$ and the label $y_i$ tells us if there ...
0
votes
1answer
126 views

Can accuracy become worse on the training set with more epochs?

I know that overfitting occurs when the accuracy on the training set improves but the accuracy on the validation set decrease. So, we must stop the training. I would like to know if this is a rule ...
0
votes
2answers
470 views

Validation accuracy is always close to training accuracy

I am trying to tune the hyperparameters of a LSTM I have to do time series forecasting. I have noticed that my validation accuracy is always very close to my training accuracy. I am not sure whether ...
0
votes
1answer
354 views

How to avoid covariate shift in python and distribute classes in each train and test phase?

We all know that with the use of sklearn package from python, we can create X_train, X_test, y_train and y_test via this code: ...
5
votes
3answers
99 views

Can you learn an algorithm from a trained model?

Are there any papers where an algorithm was entirely based on the results of a trained model? Let me explain. Suppose you want to come up with an algorithm that sorts three numbers $a,b,c$. I can ...
0
votes
1answer
2k views

Caret + RStudio: Error “Please make sure `y` is a factor or numeric value” when training

I'm new to Caret and I've been trying a couple things to get the hang of things. But this error happened to me and I'm not sure why. I've been trying to train a model with some data I got from "...
1
vote
0answers
568 views

Time series regression using SVR

I have time series data stored in a data frame as follows: Time, c1, c2, c3 0, 0.55, 0.4 , 0.3 1, 0.8 , 0.1 , 0.6 2, 0.9 , 0.5 , 0.7 .... And I want to ...
1
vote
0answers
26 views

Dynamic window regression model

I have a signal and want to predict y which present Number of requests, using regression models. Currently, I am using OLS regression model to predict y. But the prediction error is very high, as my ...
0
votes
1answer
102 views

Free Service for Alpha Zero training

I'm an AI student I need to train a deep neural network using the Alpha Zero (Silver et al) for a simple game using this implementation: http://web.stanford.edu/~surag/posts/alphazero.html. I was ...
0
votes
3answers
1k views

Downsampling and class ratios

My target variable is whether an application is accepted or not. It is a highly imbalanced target with 98.5% of applications accepted. I am unclear about the concept of downsampling. If I were to ...
1
vote
2answers
2k views

Both train and test error are decreasing in XGBoost iterations

I have an issue with training an XGBoost classifier in a sence that both train and test error only decrease throughout more iterations (num_boost_round) even if I use 1000 num boost rounds and 10 ...
1
vote
1answer
1k views

Tensorflow Fine-tuning a model from my own checkpoint

Assume that I am going to do more training with a similar data set in the future, is there any benefit to me using a fine tune checkpoint from a model that I created from my own training as opposed to ...
1
vote
1answer
91 views

Effect of adding extra unrelated features to linear perceptron

Suppose that we are training a linear regressor (perceptron). Adding extra features that are not related to the target (e.g. randomly generated values) before training will typically ____ our training ...
1
vote
1answer
49 views

neural network training algorithms

When I first read about neural networks, I learned that Backpropagation is the algorithm used to train the neural network. I am interested if there are other alternatives (or better?) to BP. What ...
3
votes
3answers
1k views

Meaning of stratify parameter

I'm training a Neural Network and I'm trying to divide my data into training and testing sets. I have a lot of output classes and for some of them I have as little as 2 examples, so I would like to ...
1
vote
1answer
4k views

How to use two different datasets as train and test sets?

Recently I started reading more about NLP and following tutorials in Python in order to learn more about the subject. The problem that I've encountered, now that I'm trying to make my own ...
0
votes
1answer
20 views

Example data source for educaional use

I'm doing project on subject of affinity analysis for my statistical class in college. In order to complete it, I have to acquire sales database with at least 200-300 records, each containing list ...
1
vote
1answer
36 views

how to split available data into training and testing (Information security)

I was advised to ask my question here. Recently, I made a post about finding suitable dataset for SIEM (Security Information and Event Management) systems. The goal was to work on classification and ...
0
votes
1answer
32 views

Given is the result of the model performance. Help me with this MCQ

You also evaluate your model on the test set, and find the following: Human-level performance 0.1% Training set error 2.0% Dev set error 2.1% Test set error 7.0% What does this mean? (Check the ...
1
vote
1answer
40 views

Tool for test/train automation

I need to test different datasets as well as different algorithm implementations. The current workflow looks like: Perform feature extraction from train set Train classifier on this features Feed ...
0
votes
1answer
258 views

is it acceptable if the reward of test of DQN is lower than reward of training of DQN in minimization problem?

if we train a DQN over 40000-60000 episodes for 500 time steps. The mean of reward during last 100 training steps is about 1.1 times of reward during the test process. Environment is stochastic! The ...
1
vote
1answer
32 views

Training dataset decreasing in quality (Google data science blog)

I have a complex algorithm that decides when it should show customers of an only shop an ad on our website, after they log in, in hope that they will buy what is in the ad. We have no control what is ...
0
votes
1answer
284 views

Training a model for object detection [closed]

I am new to Machine Learning. Need a little direction on how to proceed with training a model for object detection. I have a complete training dataset and test dataset of cars with color images, ...
1
vote
1answer
40 views

How does training a ConvNet with huge number of parameters on a smaller number of images work?

I have two questions: I am wondering why is that a very deep model such as VGG-16 which has approximately 138 million parameters (Source) can be used as a model to be trained on just 1.3 million ...
4
votes
1answer
440 views

How to implement clipping the reward in DQN in keras

How to implement clipping the reward in DQN in keras? especially how to implement clipping the reward? Is this pseudo code correct: ...
1
vote
0answers
80 views

Add training data to YOLO post-training

I've been playing around with YOLOv3 and obtaining some good results on the ~20 custom classes I trained. However, one or two classes look like they can use some additional training data (not a lot, ...
3
votes
1answer
779 views

What are the effects of clipping the reward in stability?

I am looking for stabilizing my results of DQN, I found clipping is one technique to do it but I did not understand it completely! 1- what are the effects of clipping the reward, clipping the ...
0
votes
1answer
63 views

What do I initialise each model in cross validation with in a multi-layer Perceptron?

So, as far as my understanding goes, cross-validation is used to determine the best model. I understand that once we determine the best model, we then train it on the entire dataset. I'm supposed to ...
1
vote
1answer
126 views

What is difference between final episodes of training and test in DQN?

What is difference between running in final episode of training mode and running in test mode in DQN? Is there any difference more than after training and tune the hyper-parameters, we test for one ...
1
vote
1answer
84 views

has number of output layer of DNN any effect in speed of find the optimal answer of DNN?

has number of output layer of DNN any effect in speed of find the optimal answer of DNN? For instance the more episodes is needed to train a DNN when the number of outputs is more? Is it correct?
2
votes
1answer
74 views

Minimum Neurons in Neural Network

I use a brute-force mechanism to determine optimal hidden layers/neurons by incrementing the layers/neurons by 1 up to some maximums and then picking the optimal counts from the best performing model. ...
2
votes
0answers
47 views

Maximum Layers in “any” Neural Network [duplicate]

I have about 6 months of experience in building and using Neural Networks with no prior/formal training. As I explore this field further, I see a lot of discussions about determining how many layers/...
1
vote
0answers
21 views

How to prepare future data for training

Assume I have a large data of ecommerce website sessions with user id key (a user can have multiple sessions with random time between them). The data is on S3 in json gzipped format. On some sessions ...
2
votes
3answers
65 views

Which is more important - stable training results or good test results?

Which is more important - stable training results or good test results? For instance, is obtaining an unstable training accuracy in different epochs, but good test accuracy better? Or is obtaining a ...

1
4
5
6 7 8