Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [training]

The tag has no usage guidance.

0
votes
1answer
15 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
18 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 ...
0
votes
0answers
4 views

effects of number of running time periods on examining the DQN quality?

What are the effects of the number of running time periods on examining the DQN quality? I mean "T": time periods of training and testing. If there is not an obligation to set it to a value in the ...
0
votes
0answers
13 views

How apply Reinforcement Learning in the following case?

Suppose that I have to move from point A to B and I have to choose among 3 different paths. But we don't know the traffic in each path, so what is the training rule to use to learn the best behaviour? ...
1
vote
0answers
100 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
18 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
33 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 ...
0
votes
0answers
9 views

Semantic segmentation training on images of different sizes - good practices

What are the good practices of handling images when training the neural networks for semantic segmentation, but the images have different sizes and aspect ratios? Also, how to properly handle small ...
0
votes
1answer
15 views

Prediction in LM and SVM [closed]

I am learning Datascience. I see youtube videos and online training sessions. I have 3 questions: In regression problems,svm,etc the trainer say let us predict and pass the data set to predict. Then ...
1
vote
0answers
9 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. ...
1
vote
0answers
42 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
19 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
56 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 ...
1
vote
2answers
48 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 ...
0
votes
0answers
31 views

Triplet loss training problem

My results are very poor and I cannot make out the reason on why is it so? I am using euclidean distance measure for hard mining of triplets. It is prior to training with the initial random set of ...
2
votes
1answer
38 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
15 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
43 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
22 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: ...
-1
votes
0answers
16 views

Stacked machine learning models train - test split on time series data

I have a question about the best approach to a problem I am facing. I have time series data, say from day 1 to day 100. I Split the data into a training and test set, 80:20 and apply 3 machine ...
0
votes
0answers
3 views

How to split a Bunch type

I have a dataset of images saved in python, in a Bunch type. In this buch, one key is 'train' that assume the values 1 or 0. I need to split them in X_train and X_test in a deterministic way (in ...
5
votes
3answers
79 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
34 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
votes
0answers
43 views

How can i take advantage of google Speech Commands dataset

I am building a Simple audio recognition for key word spotting taking inspiration from here.Apart from the dataset available Speech Commands dataset. i would also like to add words like "move" and a ...
0
votes
0answers
27 views

What does it mean when a model trained in Keras has zero loss for much of each epoch?

I'm attempting to train a model in Keras and I've noticed a pattern that seems to be occurring. Namely, for much of each Epoch, the loss is identically zero. For example, in a model I'm currently ...
2
votes
0answers
84 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
23 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
32 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
50 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
64 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
98 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
20 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
32 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 ...
0
votes
0answers
12 views

Nvidia pggans: training network on my own dataset

I want to train network using Nvidia Progressive growing of Gans. I have my own images. I generated tfrecords files using dataset_tool.py create_from_images. What ...
1
vote
2answers
19 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 ...
0
votes
1answer
118 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
16 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 ...
0
votes
0answers
53 views

Imbalanced dataset: undersampling or splitting the dataset first?

I am doing a binary classification on an imbalanced data set, like 30:1 ratio for the two categories. One of the basic methods that I've read is to undersample the majority class such that there is ...
1
vote
1answer
31 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
14 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 ...
0
votes
0answers
12 views

what does frame mean? what is its difference in comparison with training epoch in DQN?

what does frame mean? what is its difference in comparison with training epoch in DQN? http://arxiv.org/abs/1810.07286 Also, I have seen in DQN nature paper it has written they trained on 1 ...
0
votes
1answer
20 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
0answers
22 views

Is it possible to fine tune a model on the training dataset to extract features for the validation dataset?

I have 2 models to train. The first is VGGFace, which is already trained. I have to fine tune it using my dataset (labeled frames where labels describe emotions). then, I am going to extract features ...
0
votes
1answer
34 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
29 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
36 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
28 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 ...
3
votes
1answer
152 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
27 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, ...