Deep learning
Last updated
Logistic Regression - ML playgroundLast updated
I am a simple guy who likes to code and learn new things. I've worked on projects that involves pure signal processing, image processing in Python with some libraries like numpy and scipy.
After that I worked on some projects that involves Machine learning and deep learning. you can find the code in my GitHub.
This is my next biggest attempt to understand how Logistic Regression works. I have created the front-end to tune the parameters and see how the algorithm optimizes it.
Here you can create your own dataset and see how the model will train on that data. You can even try adding as many features as you want.
In this project, the task is to predict the rating of a movie for a user given his past ratings for several movies that he or she watched and the ratings of the movie by similar other users. There is no information regarding user or movie, Just the ratings are given. This dataset is part of the famous Netflix competition that was held for four years.
In this one, I've got a chance to learn about at several recommender systems and the algorithms that were developed during the competition. I've learned about several algorithms like SVD, SVD++ etc..More about these are available here.
Based on the readings from accelerometer and the zyrometer, we have to predict whether the person is walking , standing, sitting , walking up stairs or down the stairs. It is a multiclass classification and I've got a chance to apply several machine learning models based on the data and a deep learning model using LSTM as well.
This is a small attempt to understand how each algorithm behaves as we change the hyper parameters. I thought of doing for all the algorithms. But I could only do it for KNN and Linear Regression. It gave me clear understanding of how gradient descent works.
