Questions tagged [machine-learning]
Machine learning provides computer algorithms that automatically discover patterns in data and make intelligent decisions from them.
252
questions
4
votes
1
answer
362
views
Machine Learning Model to Predict the Type of Variable Star from Light Curve
I've created this machine learning model that predicts the type of variable star based on the light curve. A variable star is a type of star whose luminosity changes over time. My model predicts ...
- 161
2
votes
1
answer
121
views
Time Series Forecasting
I'm currently working on a project involving time series analysis and have written the following code for the train-test split section. I'm particularly concerned about the correctness of the ...
user284332
0
votes
1
answer
53
views
Low Validation and Test Accuracy with Random Forest on ECG signals
I'm working on a project involving ECG data classification using a Random Forest model. Unfortunately, my model's performance is significantly lower than expected, and I'm struggling to understand why....
1
vote
0
answers
50
views
A machine learning model for predicting bit strings in Java
I have this GitHub repository (BitPredictor.java). Basically, I tried to harness a machine learning model for predicting bit strings. I have implemented it to the best of my understanding and have ...
- 29.1k
3
votes
1
answer
86
views
Pytorch code running slow for Deep Q learning (Reinforcement Learning)
I'm a new student in reinforcement learning. Below is the code that I wrote for deep Q learning:
...
3
votes
1
answer
66
views
Python sklearn rolling yearly validation
I am trying to implement a simple modelling pipeline with rolling c.v., making use of the TimeSeries split. The code is provided below with a working example dataset. (please don't pay too much ...
- 179
4
votes
2
answers
174
views
Matrix Factorisation class packaging methods for factorisation of explicit & implicit data matrices using Gradient Descent, SGD and ALS
Attached below, and also as this GitHub gist, is code for a Python class I wrote as part of a personal learning/portfolio project on collaborative-filtering recommender systems via matrix ...
- 43
5
votes
1
answer
110
views
Making sklearn's decision trees easier to traverse
scikit-learn's decision tree structure is difficult for me to navigate. I would prefer to have functionality like tree.left, ...
- 151
2
votes
2
answers
337
views
Minimal AlphaGo algorithm implementation for game 2048, connect4
I'm writing tutorial code to help high school students understand the MuZero algorithm. There are two main requirements for this code.
The code needs to be simple and easy for any student to ...
- 31
1
vote
1
answer
110
views
Custom neural network implementation in TensorFlow to compare normalisation vs. no normalisation on data
I am performing a sports prediction multi-class classification problem, and wanted to compare the differences in model performance between normalised and non-normalised data. You can see the 2 ...
3
votes
1
answer
212
views
Machine learning training, hyperparameter tuning and testing with 3 different models
I am trying to solve a multi-class classification involving prediction the outcome of a football match (target variable = Win, Lose or Draw). With a dataset of 2280 rows, which is 6 seasons of ...
3
votes
1
answer
141
views
Keras Tuner Subclass for Time Series Cross-Validation
Custom Keras Tuner with Time Series Cross-Validation
I have written my own subclass of the default Keras tuner Tune class.
Objective: I needed a way to incorporate ...
- 131
1
vote
0
answers
128
views
Convolutional Neural Network (CNN) in Julia
I wrote an n-dimensional convolutional neural network from scratch in Julia (check out the GitLab repo or the GitHub repo). It implements the following layer types:
...
0
votes
0
answers
22
views
Efficiently computing a batch of results given a batch assignment vector and series of corresponding matrices
I have a 1D tensor of tokens that belong to different batches. The batch sizes here are uneven. Each batch needs to be multiplied with a corresponding weight matrix. My current approach is using a ...
- 1
-2
votes
1
answer
185
views
Design an algorithm to predict words based on a skeleton from a given dictionary
The model I'm building first selects a secret word at random from a list. The model which uses an API then returns a row of underscores (space separated)—one for each letter in the secret word—and ...
- 232
1
vote
0
answers
49
views
Recurrent Neural Network loss is NAN
I am training a neural network to use approximately 600 features (4103rd to last column of a df) to predict approximately 4000 values (7th to 4102nd column of the same df). I have standardized the ...
- 11
2
votes
1
answer
197
views
Movie genre classification using machine learning
could you review my below code to train a machine learning model to classify movie genres? I've used the data from Kaggle
...
7
votes
1
answer
683
views
Remove hot-spots from picture without touching edges
In the picture below there are some regions which are very bright (i.e. more white). Some bright regions are wide and some are narrow or thin. The red box covers one such wide bright spot, and blue ...
- 173
2
votes
1
answer
138
views
ANN with Backpropagation for MINST data set
I am learning about ANN and tried it for the MINST data sets. Now I am supposted to create a neural network (ANN) with backpropagation.
The structure for the neural network I have is this the input ...
- 47
1
vote
0
answers
113
views
Train a Keras model to recognize and predict speech in real-time using microphone as audio source
Please help me optimize this script. I'm running it in Google Colab GPU runtime. I've implemented many optimizations but they worsened it. I need serious help. I have to submit my project in 3 days!. ...
1
vote
1
answer
66
views
Optimize an algorithm for preparing a dataset for machine learning
I'm learning how to use R coming from a python background. I'm following Andrej Karpathy's zero-to-hero course, reimplementing it in R.
We start with a list of 32033 names. These names have to be ...
- 35
1
vote
0
answers
841
views
Object detection YOLO v1 loss function implementation with Python 3 and TensorFlow 2.x
About the code
Object detection YOLO v1 loss function implementation with Python + TensorFlow 2.x. It based on the Pytorch implementations below and re-implemented with TensorFlow based on my ...
- 111
1
vote
0
answers
50
views
Improving AI model for categorical outcome predictions
I am a novice and would appreciate some guidance. I have been trying to create a machine learning code that will correlatate 10+ binary variable and maybe a couple continuous variables to a binary ( ...
- 11
2
votes
0
answers
84
views
neural network that determines the gender of a word
I wrote a neural network in python using pytorch, which determines the gender of a word in Russian. As a training set: a file containing a word and a number from 0 to 2 (0-masculine,1- feminine and 2-...
user269440
1
vote
1
answer
214
views
Plotting correlation matrix with Seaborn and pandas
I try to plot the correlation matrix of a Pandas DataFrame. As the diagonal elements are always ones, and the matrix is symmetrical, so I can get rid of most than a half of the squares without loosing ...
- 210
1
vote
0
answers
39
views
Machine learning: user-based collaborative filtering
Task:
What to fix in the class, just as a beginner it's hard for me to understand where I messed up?
Code:
Model:
...
- 11
5
votes
1
answer
1k
views
Remove background from a directory of JPEG images
I wrote a code to remove the background of 8000 images but that whole code is taking approximately 8 hours to give the result.
How to improve its time complexity? As I have to work on a larger dataset ...
- 51
1
vote
0
answers
43
views
Implementation of K-Neighbor Algorithm in Python
I would like to get some feedback of my K-Neighbors Implementation using Abalone Dataset and cross-fold validation.
How can I make it more efficient? (No sklearn library allowed)
Where do you see any ...
- 111
1
vote
1
answer
104
views
Decision Tree for classification tasks in Python
I've decided to implement the ID3 Decision Tree algorithm in Python based on what I've learned from George F. Luger's textbook on AI (and other secondary readings). As far as I know, the code is ...
- 357
1
vote
0
answers
34
views
RESNET machine learning code with TensorFlow
I am a PhD student working on a machine learning project with binary classification and RESNET architecture in TensorFlow. I believe I have done everything correctly but I am looking for some ...
- 11
2
votes
0
answers
72
views
CodeReview: CycleGAN Implementation Using Keras FunctionalAPI
Okay So I Am Here Implementing the cyclegan architecture with using keras api
from scratch.
For Those who Wanna Know More About Cyclegan seehere
The CycleGan Compose of Two Phase Architecture Like ...
1
vote
0
answers
104
views
Logistic Regression on Titanic Dataset - Sklearn
The goal of my program is to calculate the chances of a person to survive during Titanic accident, after receiving information such as person's age, class, sex, etc. There's a dataset full of ...
- 173
1
vote
1
answer
75
views
Linear Regression in Scikit_learn
I have 2 datasets (one for training and the other for testing) containing information about days temperature and humidity; My programm should process the training dataset and find a relation between ...
- 173
3
votes
1
answer
238
views
Machine Learning Loss Functions In C++
I was looking for C++ versions of the machine learning metrics implemented in Python's sklearn, but they were surprisingly hard to find. I came across a website that had most of the loss functions ...
- 33
1
vote
0
answers
158
views
Binary classification with pytorch
I wrote a simple neural network binary classification algorithm using Pytorch. It uses the dataset from https://www.kaggle.com/pritsheta/heart-attack, which consists of a table with 300 rows and 14 ...
- 163
3
votes
1
answer
123
views
libsvm++ : Rewritten libsvm in newer C++
The most famous library for Support Vector Machine (SVM) algorithm is libsvm (https://github.com/cjlin1/libsvm/), but I felt that its code style is too old, I rewrote in newer C++ as a hobby project.
...
- 1,713
4
votes
2
answers
1k
views
C++: Linear Regression and Polynomial Regression
I wrote a simple linear/polynomial regressor based on my previous matrix project (https://github.com/frozenca/Ndim-Matrix).
...
- 1,713
2
votes
1
answer
208
views
Generating a matrix with each row having normalized weights
I just asked this question over Stack Over Flow on how to improve my code and reposting it here as someone on Stack Overflow recommended this platform.
I have written two python functions and they are ...
- 21
4
votes
1
answer
78
views
Unsupervised competitive learning algorithm from scratch in javascript
I'm a mathematician who is new to programming and I'm currently reading the book "Theory of Neural Networks" by Rojas. To become better, I try to program every algorithm that is described in ...
- 151
2
votes
0
answers
127
views
Logistic Regression for Fashion MNIST T-shirt vs. Shirt
I wrote a Logistic Regression for Fashion MNIST to classify T-shirt vs. Shirt.
here is the class
...
- 199
2
votes
0
answers
67
views
xagents - implementations of reinforcement learning algorithms
Description
It is valid to say, this work started and evolved from a standalone DQN implementation, which I included in an old question, to a mini-library xagents, housing 7 re-usable tensorflow-based ...
1
vote
0
answers
45
views
The best tensorflow neural net I got so far for iris dataset
Compared to my another post Logistic Regression for non linearly separable data which uses one-layer net, i.e. Logistic Regression to classify the iris data set, this post is to discuss the tensorflow ...
- 199
0
votes
1
answer
104
views
Logistic Regression for non linearly separable data
Iris Data Set consists of three classes in which versicolor and virginica are not linearly separable from each other.
I constructed a subset for these two classes, here is the code
...
- 199
2
votes
0
answers
58
views
DQN implementation
I just wrote my pong DQN. It seems to work. I'm looking for a performance based review on anything that might slow down the training in complex models.
main.py:
...
2
votes
2
answers
87
views
Updated version of my first neural network in c++
I got lot of suggestions for optimizing my neural network last post I made, now I wanted to post updated version of it were I got rid of most of performance eaters, now I would really appriciate ...
- 31
8
votes
3
answers
745
views
My first functional naive neural network in C++
I just wrote my first standard neural network with SGD gradient descent in c++, I am really interested if I have done anything wrong or inefficient, suggestions would help me a ton
(There is lots of ...
1
vote
1
answer
65
views
Logistic regression using Sklearn
I'm trying to learn how to use logistic regression with Sklearn. After learning the theory, I tried implementing it using the Heart Attack Analysis datasheet from Kaggle.
Here's a snippet of the data:
...
- 203
2
votes
1
answer
121
views
a prototype of finding the (almost) best learning rate and initial weights so that a perceptron converges with the minimal iteration
First of all, I chose the nearest data points/training examples
...
- 199
2
votes
1
answer
69
views
A simple clusterness measure of data in one dimension using Java - follow-up 2
(See the previous version here.)
This time, I have encorporated all the suggestions made by Marc. Also, I changed the type of points from Double to ...
- 29.1k
1
vote
1
answer
53
views
A simple clusterness measure of data in one dimension using Java - follow-up
(See the previous version here.)
(See the next version here.)
This time, I have incorporated all the suggestions made by Roman; my new version follows.
...
- 29.1k