# atcold/pytorch-deep-learning-minicourse

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/atcold-pytorch-deep-learning-minicourse).**

6,810 stars · 2,232 forks · Jupyter Notebook · NOASSERTION

## Links

- GitHub: https://github.com/Atcold/pytorch-Deep-Learning-Minicourse
- Homepage: https://atcold.github.io/NYU-DLSP20/
- awesome-repositories: https://awesome-repositories.com/repository/atcold-pytorch-deep-learning-minicourse.md

## Description

This is an educational curriculum for building and training neural networks using PyTorch. It serves as a deep learning training guide and resource, providing a structured series of lessons on tensor computation and architecture development.

The course uses an interactive learning model that synchronizes academic theory with practice. It pairs theoretical lecture slides with exercise-driven notebooks, requiring students to implement model logic within predefined templates to validate their conceptual understanding.

The curriculum covers a broad range of deep learning capabilities, including model optimization via gradient descent and regularization, and the implementation of convolutional, recurrent, and transformer architectures. It also includes instructions for processing multimodal data and applying self-supervised learning through contrastive methods and autoencoders.

The content is delivered through a modular sequence of Jupyter Notebooks.

## Tags

### Education & Learning Resources

- [Deep Learning Courses](https://awesome-repositories.com/f/education-learning-resources/deep-learning-courses.md) — An educational curriculum focused on building and training neural networks using PyTorch.
- [Deep Learning Curriculum](https://awesome-repositories.com/f/education-learning-resources/deep-learning-curriculum.md) — Provides a structured learning path for neural network development through exercise-driven notebooks.
- [Curriculum Architectures](https://awesome-repositories.com/f/education-learning-resources/curricula-instructional-design/educational-frameworks-architectures/curriculum-design-patterns/curriculum-architectures.md) — Provides a structured educational path that progresses linearly from basic tensor operations to complex architectures.
- [Deep Learning Education](https://awesome-repositories.com/f/education-learning-resources/deep-learning-education.md) — Provides curated educational resources for learning the theory and practice of deep learning.
- [Machine Learning Courses](https://awesome-repositories.com/f/education-learning-resources/educational-resources/ai-learning-resources/ai-machine-learning-tutorials/machine-learning-courses.md) — Offers a structured training program combining theoretical lecture slides with practical notebook exercises.
- [Deep Learning Computation Tutorials](https://awesome-repositories.com/f/education-learning-resources/educational-resources/reference-and-media/tutorials-media-curated-lists/technical-tutorials/machine-learning-ai/deep-learning-computation-tutorials.md) — Provides educational content focusing on deep learning computation and architecture development.
- [Interactive Notebook Learning Resources](https://awesome-repositories.com/f/education-learning-resources/interactive-notebook-learning-resources.md) — Uses Jupyter notebooks to synchronize academic theory with practical PyTorch code execution.
- [Lecture-Notebook Pairs](https://awesome-repositories.com/f/education-learning-resources/jupyter-notebook-curricula/lecture-notebook-pairs.md) — Pairs theoretical conceptual slides with corresponding practical notebooks for synchronized learning.
- [Deep Neural Network Training Optimization](https://awesome-repositories.com/f/education-learning-resources/technical-interview-preparation/ml-interview-preparation/deep-learning-review/deep-neural-network-training-optimization.md) — Covers the application of gradient descent, backpropagation, and regularization to optimize neural network training. ([source](https://atcold.github.io/NYU-DLSP20/))

### Artificial Intelligence & ML

- [Dynamic Graph Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/computational-graph-frameworks/dynamic-graph-frameworks.md) — Implements a curriculum centered on building models with dynamic computational graphs for automatic gradient calculation.
- [Deep Learning Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/architectures/neural-network-components/deep-learning-implementations.md) — Provides guided implementations of convolutional, recurrent, and transformer networks from first principles. ([source](https://atcold.github.io/NYU-DLSP20/))
- [Neural Network Model Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-model-implementations.md) — Demonstrates the practical implementation of diverse neural network architectures for images and text.
- [Multimodal Data Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-data-processing.md) — Supports the processing of diverse input signals including computer vision data and text sequences. ([source](https://atcold.github.io/NYU-DLSP20/))

### Part of an Awesome List

- [Multimodal Architectures](https://awesome-repositories.com/f/awesome-lists/ai/multimodal-architectures.md) — Teaches the implementation of diverse neural network types including convolutional, recurrent, and transformer models.
- [Self-Supervised Learning](https://awesome-repositories.com/f/awesome-lists/ai/self-supervised-learning.md) — Includes lessons on learning representations from unlabeled data using contrastive methods and autoencoders. ([source](https://atcold.github.io/NYU-DLSP20/))
- [Learning Resources](https://awesome-repositories.com/f/awesome-lists/ai/learning-resources.md) — A comprehensive deep learning mini-course.
- [Tutorials](https://awesome-repositories.com/f/awesome-lists/more/tutorials.md) — Listed in the “Tutorials” section of the The Incredible Pytorch awesome list.

### Development Tools & Productivity

- [Model Implementation Exercises](https://awesome-repositories.com/f/development-tools-productivity/computational-notebooks/deep-learning-notebooks/model-implementation-exercises.md) — Provides interactive coding tasks where students implement specific neural network architectures within notebooks.
- [Educational Code Templates](https://awesome-repositories.com/f/development-tools-productivity/template-based-code-generators/educational-code-templates.md) — Employs a template-based approach where students fill in missing logic to learn model construction.

### Software Engineering & Architecture

- [Exercise-Driven Validations](https://awesome-repositories.com/f/software-engineering-architecture/interface-driven-validation/exercise-driven-validations.md) — Validates student understanding by requiring the implementation of theoretical concepts in code.