An open API service indexing awesome lists of open source software.

https://github.com/kacemmathlouthi/deep-ml-problems

a collection of solved machine learning, linear algebra, and deep learning problems from deep-ml.com
https://github.com/kacemmathlouthi/deep-ml-problems

deep-learning linear-algebra machine-learning numpy python

Last synced: 7 months ago
JSON representation

a collection of solved machine learning, linear algebra, and deep learning problems from deep-ml.com

Awesome Lists containing this project

README

          

# Deep ML Practice Problems Repository

Welcome to the **Deep ML Practice Problems** repository! This repository contains a collection of solved machine learning, linear algebra, and deep learning problems from [deep-ml.com](https://deep-ml.com). The solutions are implemented in Python and structured for learning, experimentation, and skill enhancement.

---

## Repository Structure

The repository is organized into directories, each representing a problem or concept:

```
.
├───2D Translation Matrix Implementation
├───Calculate 2x2 Matrix Inverse
├───Calculate Accuracy Score
├───Calculate Correlation Matrix
├───Calculate Image Brightness
├───Calculate Jaccard Index for Binary Classification
├───Calculate Mean by Row or Column
├───Calculate R-squared for Regression Analysis
├───Calculate Root Mean Square Error (RMSE)
├───Feature Scaling Implementation
├───Implement F-Score Calculation for Binary Classification
├───Implement Precision Metric
├───Implement Recall Metric in Binary Classification
├───Implement ReLU Activation Function
├───Implementation of Log Softmax Function
├───Leaky ReLU Activation Function
├───Matrix Times Vector
├───One-Hot Encoding of Nominal Values
├───Scalar Multiplication of a Matrix
├───Sigmoid Activation Function Understanding
├───Single Neuron
├───Softmax Activation Function Implementation
├───Transpose of a Matrix
```

---

## Features and Topics Covered

This repository covers a variety of fundamental concepts and operations in machine learning and deep learning:

1. **Linear Algebra**
- Matrix operations (e.g., transpose, scalar multiplication, matrix-vector multiplication).
- Inverse and determinant calculations.
- One-hot encoding and feature scaling.

2. **Performance Metrics**
- Accuracy, precision, recall, F-score.
- R-squared and RMSE for regression.
- Jaccard index for binary classification.

3. **Activation Functions**
- Sigmoid, ReLU, Leaky ReLU, and Softmax.
- Log-Softmax implementation.

4. **Miscellaneous**
- Image brightness calculation.
- Correlation matrix computation.
- Understanding the behavior of a single neuron.

---

## License

This repository is open-sourced under the [MIT License](LICENSE).