Questions tagged [machine-learning]

Methods and principles of building "computer systems that automatically improve with experience."

2,593 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
9
votes
2answers
907 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
191 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 ...
5
votes
1answer
52 views

Which database to use for storing machine learning data?

I am currently storing my training data into HDF5 files and I want my team and I to switch for a database for two main reasons: the data is not used only by me and the different datasets are stored ...
5
votes
0answers
146 views

How to achieve SHAP values for a CatBoost model in R?

I'm asked to create a SHAP analysis in R but I cannot find it how to obtain it for a CatBoost model. I can get the SHAP values of an XGBoost model with ...
5
votes
1answer
39 views

Is there a paper accomplishing finding physical law from observation without premade perception, using machine learning?

For example: Isaac Newton finds law of universal gravitation just by looking a falling apple, without any premade perception of that phenomenon. Is it possible to accomplish that kind of discovery ...
5
votes
1answer
688 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 ...
5
votes
2answers
145 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 ...
5
votes
0answers
60 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
2answers
562 views

Image recognition of selfie images

I developed an Android app that lets anyone upload pictures of encyclopedic things (bridges, museums, dishes, landscapes, paintings, etc) to Wikimedia Commons. Unfortunately, 5% of the users find it ...
5
votes
3answers
546 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
642 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
1answer
134 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
0answers
483 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 = ...
4
votes
0answers
35 views

Can we use embeddings or latent vectors for a recommender system?

I'm having a hard time understanding why people use any vector they find as a candidate for a recommender system. In my mind, a recommender system requires a space where distance represents similarity....
4
votes
1answer
54 views

What ML architecture fits fixed length signal regression?

My problem is of regression type - How to estimate a fish weight using 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
95 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
667 views

BPE vs WordPiece Tokenization - when to use / which?

What's the general tradeoff between choosing BPE vs WordPiece Tokenization? When is one preferable to the other? Are there any differences in model performance between the two? I'm looking for a ...
4
votes
0answers
227 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
61 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
4answers
185 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
2answers
3k 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
366 views

Where does the “deep learning needs big data” rule come from

When reading about deep learning I often come across the rule that deep learning is only effective when you have large amounts of data at your disposal. These statements are generally accompanied by a ...
4
votes
1answer
338 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 ...
4
votes
2answers
888 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
49 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
79 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 ...
4
votes
0answers
296 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
199 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
72 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
221 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
2k 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
268 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
412 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
187 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
33 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
0answers
26 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
0answers
44 views

Detecting pushups based on pose data

I've been playing with Google's MLKit, and decided to detect push ups. As a quick test, I took the position of the left shoulder, and plotted the Y Axis. Here's how a variety of trials look: Five ...
3
votes
0answers
18 views

Force Matching in Coarse Grained Molecular Dynamics with Jax - Forces do not match when neglecting energy loss

I am currently exploring force matching approaches for molecular dynamic simulations. As I am still in an exploration state, I'd tried investigated Force Matching Neural Network Colab Notebook ...
3
votes
0answers
34 views

Train NN for balanced accuracy

I'm trying to get a NN (a CNN, to be precise) to predict labels on hugely imbalanced data, i.e. some classes are much bigger than others. I want to optimize the balanced accuracy. So I give the class ...
3
votes
0answers
29 views

A/B test results contradictory with offline machine learning model performance

This seems to be a common problem when bringing machine learning models to production. Let's say we have an optimized machine learning model which gives decent performance metric in the unseen testing ...
3
votes
0answers
56 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
1answer
268 views

Weighted loss functions vs weighted sampling?

For image classification tasks, is there a practical difference between using weighted loss functions vs. using weighted sampling? (I would appreciate theoretical arguments, experience or published ...
3
votes
0answers
21 views

Possible flaw in the MDS method for dimensionality reduction

The MDS (multidimensional scaling) method is used to solve the problem of dimensionality reduction. Basically, it does the following: given $n$ points $x_1,\cdots,x_n\in\mathbb R^d$, try to find a ...
3
votes
0answers
160 views

Chess deep learning siamese network overfitting when shouldn't in theory

TLDR: My network is training with pairs so instead of 10^6 samples it has 10^12 samples (The number of samples squared) . With that large of a data set is shouldn't overfit but it does after very few ...
3
votes
1answer
109 views

Segmentation Network produces noisy output

I've implemented a SegNet and SegNet ReLU variant in PyTorch. I'm using it as a proof-of-concept for now, but what really bothers me is the noise produced by the network. With ADAM I seem to get ...
3
votes
0answers
337 views

Plotting Gradient Descent in 3d - Contour Plots

I have generated 3 parameters along with the cost function. I have the $\theta$ lists and the cost list of 100 values from the 100 iterations. I would like to plot the last 2 parameters against cost ...
3
votes
0answers
23 views

Visualizing the difference of a set of strings

I have a distance metric on a collection of strings on the order of tens of thousands. What would be an intuitive way to summarize how 'different' these strings are or when they overlap? My goal is, ...
3
votes
1answer
122 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 ...
3
votes
0answers
1k views

How to apply a groupby rolling function to create multiple columns in the dataframe

I am setting up a volume profile series over a stock data. I have implemented the market profile code from this github repo and the link to the data is here and the example here. Some Sample of data ...

1
2 3 4 5
52