Questions tagged [machine-learning]

Machine Learning is a subfield of computer science that draws on elements from algorithmic analysis, computational statistics, mathematics, optimization, etc. It is mainly concerned with the use of data to construct models that have high predictive/forecasting ability. Topics include modeling building, applications, theory, etc.

2,846 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
9
votes
2answers
1k views

Input for LSTM for financial time series directional prediction

I'm working on using an LSTM to predict the direction of the market for the next day. My question concerns the input for the LSTM. My data is a financial time series $x_1 \ldots x_t$ where each $x_i$...
7
votes
0answers
1k views

AdaBoost implementation and tuning for high dimensional feature space in R

I am trying to implement the AdaBoost.M1 algorithm (trees as base-learners) to a data set with a large feature space (~ 20.000 features) and ~ 100 samples in R. ...
6
votes
1answer
988 views

Math Behind GOSS (Gradient-Based One Side Sampling)?

As per my understanding through books & Google Search, GOSS (Gradient-Based One Side Sampling) is a novel sampling method that downsamples the instances on the basis of gradients. As we know ...
6
votes
1answer
221 views

Training stateful LSTM with different number of sequences

I'm using a stateful LSTM for stock market analysis, and I have varying amounts of data for each stock, ranging from 20 years to just a few weeks (i.e. for newly listed stocks). I use 3 years of data ...
6
votes
1answer
136 views

How to model segmentation of a sequence to similar parts?

I guess LSTM is good for sequence modeling but how would you model "clustering" with it? Meaning, the input is a sequence and the output is labels with similar properties (I have labeled data). For ...
5
votes
1answer
67 views

Imbalanced training set vs smaller balanced training set?

Say I am using a maximum likelihood approach and my output unit computes a softmax function. My training set is distributed as follows over 6 classes: ...
5
votes
1answer
389 views

Dataset image size and inference speed

Does training/fine tuning a pre-trained model on a the same dataset but with sizes scaled down (e.g., by 70%) improve inference speed? More generally, does training a CNN on smaller images improve ...
5
votes
0answers
66 views

Training value neural network AlphaGo style

I have been trying to replicate the results obtained by AlphaGo following their supervise learning protocol. The papers specify that they use a network that has two heads: a value head that predicts ...
5
votes
0answers
133 views

Deep advantage learning: how to predict the value

I'm currently working on a collection of reinforcement algorithms: https://github.com/lhk/rl_gym For deep q-learning, you need to calculate the q-values that should be predicted by your network. There ...
5
votes
1answer
105 views

Predicting change of shapes/coordinates

I'm trying to find a way to predict/calculate how a shape (e.g. outline of a glacier) will change in the future—based on its history (previous shape) and additional factors (e.g. Δtemperature). In my ...
5
votes
3answers
693 views

Hyperparameter tuning in multiclass classification problem: which scoring metric?

I'm working with an imbalanced multi-class dataset. I try to tune the parameters of a DecisionTreeClassifier, ...
5
votes
1answer
662 views

Time Series pattern recognition and classification problem

I have some labeled sensor data. Now, I would like to know how to extract features from time series using DFT, DWT, and HAAR transforms. I know that the transformations above transform a signal to ...
5
votes
0answers
486 views

differences between LSQR and FTRL when working with very sparse data

I have a 2M instances dataset with millions of very very sparse dummy variables created using the hashing trick = ...
5
votes
3answers
242 views

Cluster evolution over time

I have a dataset of transactional data with customer ID and I want to segment the dataset into groups using cluster analysis. I'm interested in following the evolution of each cluster over time, but ...
4
votes
1answer
95 views

Linear Regression bad results after log transformation

I have a dataset that has the following columns: The variable I'm trying to predict is "rent". My dataset looks a lot similar to what happens in this notebook. I tried to normalize the rent ...
4
votes
1answer
219 views

Self-attention mechanism did not improve the LSTM classification model

I am doing an 8-class classification using time series data. It appears that the implementation of the self-attention mechanism has no effect on the model so I think my implementations have some ...
4
votes
1answer
59 views

What ML architecture fits fixed length signal regression?

My problem is of regression type - How to estimate a fish weight using a fixed-length signal (80 data points) of the change in resistance when the fish swim through a gate with electrodes (basically 4 ...
4
votes
1answer
133 views

Learning parameters when loss is a piecewise function

I have a network to generate a single number $T$. I know in advance: a property of the loss function is that, when $T \in [a_1, a_2]$, the loss has the same value $L_1$; when $T \in [a_2, a_3]$, the ...
4
votes
0answers
282 views

How to use multiple text features for NLP classifier?

I am trying to build text classifier, Usually, we have one text column and ground truth. But I am working on a problem where dataset contains many text features. I am exploring different ways how to ...
4
votes
0answers
316 views

How to detect vanishing and exploding gradients with Tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
4
votes
1answer
137 views

tensorflow pseudo inverse doesn't work for complex matrices!

The Tensorflow documentation here says that: tf.linalg.pinv is ''analogous to numpy.linalg.pinv. It differs only in default value of rcond''. However, tf.linalg.pinv requires the matrix to ...
4
votes
0answers
23 views

How can I test the relationship between events and categorical data

I have a dataset comprised of mostly categorical data, in particular, different name tags of events that happen within a process. Those are accompanied of their <...
4
votes
1answer
66 views

Training Machine Learning Model - Neural Network - Islands Problem

I was working on the following leetcode problem: Given a 2d grid map of '1's (land) and '0's (water), count the number of islands. An island is surrounded by water and is formed by connecting ...
4
votes
1answer
513 views

Why does degradation occur in deep neural networks?

It has been shown that "plain" neural networks tend to have an increased amount training error, and accompanied test error, as more layers are added. I am not quite certain as to why this occurs. In ...
4
votes
4answers
216 views

Backpropagation: Relevance of the error signal of a neuron

During my quest to understand back propagation in a more rigorous approach I have come across with the definition of error signal of a neuron which is defined as follows for the $j^{\text{th}}$ neuron ...
4
votes
1answer
118 views

What does big O mean in KNN optimal weights?

Wiki gives this definition of KNN In pattern recognition, the k-nearest neighbors algorithm (k-NN) is a non-parametric method used for classification and regression. In both cases, the input consists ...
4
votes
2answers
5k views

Saving and loading keras.callbacks.History object with np.save and np.load

I have been saving my training history in keras as follows: ...
4
votes
2answers
1k views

How can I use two different datasets as a training model for svm

I know that you're supposed to scale your test data using the parameters (mean and stdev) from your training data. This is relatively simple; but what if the number of samples is limited in one ...
4
votes
2answers
77 views

What are the reasons for drawing initial neural network weights from the Gaussian distribution?

Are there theoretical or empirical reasons for drawing initial weights of a multilayer perceptron from a Gaussian rather than from, say, a Cauchy distribution?
4
votes
1answer
155 views

Evaluation of regression models with different evaluations (MSE, variance, VAF etc.)

When comparing several regression models in terms of quality, it seems like most have agreed on the MSE. There are also papers comparing "variance" and "variance accounted for (VAF)". However, there ...
4
votes
1answer
82 views

EM-ELM Cross validation

I know that cross validation is used to find the best hyperparameters that minimize the average error. For example, the number of neurons that minimize the average error of cross-validation is ...
4
votes
0answers
316 views

Multiple activation functions with TensorFlow estimator DNNClassifier

I just want to know if is it possible to use tf.estimator.DNNClassifier with multiple different activation functions. I mean, could I use a DNNClassifier estimator which use different activation ...
4
votes
0answers
212 views

Confidence value in AdaBoost?

I read this introduction about AdaBoost (http://www.cs.man.ac.uk/~nikolaon/~nikolaon_files/Introduction_to_AdaBoost.pdf), and am curious why confidence for each model is defined as $$\alpha_j=\frac{...
4
votes
0answers
75 views

Classify driver based on time-series sensor data

I want to build a model that can detect which driver is driving now the car based on a dataset that contains 20 driver records for 3600s each driver ( the dataset contains all the car sensors values ...
4
votes
2answers
222 views

Support Vector Regression trained with data sets

I am now searching for a long time on the internet and on papers for an answers of simple questions. Am I able to train a Support Vector Regression algorithm with different data sets? If yes, how is ...
4
votes
2answers
3k views

fix first two levels of decision tree?

I am trying to build a regression tree with 70 attributes where the business team wants to fix the first two levels namely country and product type.To achieve this,I have two proposals: 1.Build a ...
4
votes
0answers
269 views

how to propagate error from convolutional layer to previous layer?

I've been trying to implement a simple convolutional neural network. But I've been stuck at this problem for over a week. To be specific, assume there are 3 layers in a convolutional pass, marked as ...
4
votes
1answer
442 views

Illustrating the dimensionality reduction done by a classification or regression model

Tl;DR: You can predict something, but how do you explain the prediction? Your usual classification/regression setup Lets say the data is a classic regression/classification problem: several numerical ...
4
votes
1answer
212 views

How to automatically verify official documents?

I am new to machine learning and data science. I apologise if the question seems very basic. I have a requirement where I need to verify information submitted via a form with the corresponding ...
3
votes
0answers
29 views

Struggling to understand/implement Transformer Decoder

I'm struggling to understand the decoder in a Transformer model, specifically with regards to some aspects of its architecture as well as how it actually handles the data during training. What I have ...
3
votes
1answer
36 views

Keras use of ImageNet?

Keras mentions that it provided models pretrained on ImageNet. However, it doesn't specify what they mean by "ImageNet" - like is it a certain subset of ImageNet of the complete set of ...
3
votes
1answer
38 views

How do I know that model performance improvement is significant?

Say I am running a Machine Learning model that produces a certain result (say accuracy of 80%). I now change a minor detail in my model (say, in a Deep Learning model, increase the kernel size in one ...
3
votes
1answer
43 views

How to identify if there is a relationship between 5 categorical independent variables to a binary dependent variable?

My dataset has 5 independent variables, each with a value of either Large, Medium or None and a binary dependent variable. The dataset has 67 rows with a split of 17:50. I would like to identify if ...
3
votes
0answers
33 views

Using softmax for multilabel classification (as per Facebook paper)

I came across this paper by some Facebook researchers where they found that using a softmax and CE loss function during training led to improved results over sigmoid + BCE. They do this by changing ...
3
votes
0answers
60 views

Unbiasedness of random forests

Suppose that I am trying to build a random forest by subsampling the data and choosing a single feature per tree randomly. For example, suppose there is some dataset, $D = \{(x_{1},y_{1}), ......(x_{N}...
3
votes
2answers
40 views

Understanding Weighted learning in Ensemble Classifiers

I'm currently studying Boosting techniques in Machine Learning and I happened to understand that in Algorithms like Adaboost, each of the training samples is given a weight depending on whether it was ...
3
votes
2answers
338 views

Why is the “dying ReLU” problem not present in most modern deep learning architectures?

The $ReLU(x) = max(0,x)$ function is an often used activation function in neural networks. However it has been shown that it can suffer from the dying Relu problem (see also What is the "dying ...
3
votes
0answers
35 views

Finding the position of an arbitrary object in a static image?

One common object detection scenario involves finding trained models in an arbitrary scene. For example, we can train a model to understand what a "bicycle" looks like, by providing various ...
3
votes
1answer
50 views

How to train YOLOV4?

I am going to write yolov4 real-time object detection, and I have to do it for car then vehicle plate number, but it does not have to find plate number if there is no car, first car then number on car,...
3
votes
2answers
62 views

What to do when seed has a big impact on model performance?

I have a training procedure set up for an image recognition task. Each time I train a model, I record training loss, validation loss, validation precision and validation recall. Recently I switched ...

1
2 3 4 5
57