Ml_gallery
This is a master project of some experiments with Neural Networks. Every project here is runnable, visualized and explained clearly.
Overview
The Machine Learning Gallery is a project that showcases various experiments with neural networks. It is designed to help beginners understand the concepts of machine learning through visualizations. Users can train and run neural networks live and see the results for themselves. Each project is accompanied by an explanation of how it works. The majority of the models are trained with PyTorch on a Django backend server, while the frontend is a React app that connects to the backend using Websocket. Some larger models are pre-trained. The technologies used in the project include PyTorch, React, and TensorFlow JS. The project is deployed at https://akhil.ai.
Features
- Feed-Forward Networks: Learn the concepts of feed-forward networks.
- Linear Classifier: Train a linear classifier to classify data.
- Polynomial Curve Learning: Learn to fit a curve using polynomial regression.
- Deep Iris: Understand the concept of computer vision and train a network for iris recognition.
- Character Identification: Train a network to identify characters.
- MNSIT GAN: Generate images of handwritten digits using a generative adversarial network (GAN).
- Image Colorization: Colorize black and white images.
- Number Recognition: Train a network to recognize and identify numbers in images.
- Attention Models: Learn about attention mechanisms in neural networks.
- Style Transfer: Transfer the style of one image onto another using deep learning.
- Natural Language Processing: Learn about word embeddings and text classification.
- Reinforcement Learning: Train agents to play games like TicTacToe, Ping-Pong, and Racer.
- Unsupervised Learning: Learn about autoencoders and self-organizing feature maps.
- Memorization: Train a network to memorize and recall patterns.
- Spiking Neurons: Learn about spiking neural networks.
- MNIST Detection Dataset: Use a pre-trained model to detect objects in the MNIST dataset.
Summary
The Machine Learning Gallery is a project that provides a platform for beginners to learn and explore machine learning concepts through visualizations. It offers a range of projects that cover various topics such as feed-forward networks, computer vision, natural language processing, and reinforcement learning. The gallery uses PyTorch for training models on a Django backend server and connects to a React frontend app. Users can train and run the networks live, with each project accompanied by an explanation of how it works. The gallery is a valuable resource for those looking to gain practical experience in machine learning.
- Gatsby
GatsbyJS is a free and open-source static site generator based on React. It uses a modern development stack including Webpack, GraphQL, and modern JavaScript and CSS frameworks. It also provides a rich set of plugins, starters, and themes.
- React
React is a widely used JavaScript library for building user interfaces and single-page applications. It follows a component-based architecture and uses a virtual DOM to efficiently update and render UI components
- SCSS
SCSS is a preprocessor scripting language that extends the capabilities of CSS by adding features such as variables, nesting, and mixins. It allows developers to write more efficient and maintainable CSS code, and helps to streamline the development process by reducing repetition and increasing reusability.
- Chakra UI
Chakra UI is a popular open-source React component library that provides a set of accessible and customizable UI components to help developers create modern web applications.
- Framer Motion
Alpine.js is a lightweight JavaScript framework that simplifies the process of creating dynamic, reactive user interfaces on the web. It uses a declarative syntax that offers a higher level of abstraction compared to vanilla JavaScript, while being more performant and easier to use than jQuery.
- Recharts
Recharts is a powerful and easy-to-use React library for building customizable and interactive charts. Built on D3.js, it offers a wide range of pre-built chart types, such as line, bar, pie, and scatter charts, all of which can be composed with a declarative syntax.
- Zustand
Zustand is a lightweight state management library for React that provides a simple and intuitive API for managing state in your application. It allows developers to easily create and manage global state, and provides a powerful set of tools for optimizing performance and improving developer productivity. Zustand is designed to be easy to use and easy to learn, making it a popular choice for developers of all skill levels.