> For the complete documentation index, see [llms.txt](https://ramsane.gitbook.io/deep-learning/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ramsane.gitbook.io/deep-learning/master.md).

# Deep learning

### Who Am I?

{% embed url="<https://www.linkedin.com/in/ramanareddysane/>" %}
Linked In Profile
{% endembed %}

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.

### 1. Logistic Regression Playground

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.

{% embed url="<https://ramsane.github.io/ml-playground/logistic_regression/>" %}

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.

### 2. Netflix Movie Recommendation System

{% embed url="<https://github.com/ramsane/NetflixPrizeRS>" %}

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.&#x20;

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.

### 3. Human Activity Recognition

{% embed url="<https://github.com/ramsane/HumanActivityRecognition>" %}

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.&#x20;

### 4. ML Inside Out

{% embed url="<https://github.com/ramsane/ML_Inside_Out>" %}

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.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ramsane.gitbook.io/deep-learning/master.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.