vicb1 / deep-learning

deep-learning

This repository contains Deep Learning references and examples in Python.

The notebook-examples directory contains Jupyter Notebook examples from various courses. Installation should be straightforward with the provided pip and conda requirements.

The image-classification-SSD and GAN-deep-convolutional examples in this root directory provide detailed instructions on how to replicate the results, for both Ubuntu and Windows.

These examples were organized from the following courses:

• Coursera Deep Learning Specialization, with the following sections:
  1. Neural Network and Deep Learning
  2. Improving Deep Neural Networks-Hyperparameter tuning, Regularization and Optimization
  3. Structuring Machine Learning Projects
  4. Convolutional Neural Networks
  5. Sequence Models
• Kaggle Deep Learning Course
• Udemy course: computer-vision-a-z
• Udemy course: advanced-computer-vision
• Stanford Deep Learning for Computer Vision course

The following are links to my other repositories that would help in the understanding of this material:

• Machine Learning (note this is a private repo due to coursework sharing policies, please contact me over Linkedin if you'd like access) - including:

  • Machine Learning coursework: Course description, and Lectures
  • Machine learning for Stock Trading coursework: Course description, Lectures, and Assignments/reference information
  • Additional notes/examples

• Computer Vision (note this is a private repo due to coursework sharing policies, please contact me over Linkedin if you'd like access) - including:

  • Computational Photography coursework: Course description, Lectures
  • Computer Vision coursework: Course description and Lectures
  • Other working examples of computer vision techniques
  • Additional notes/examples

• AI with Computer Vision (note this is a private repo due to coursework sharing policies, please contact me over Linkedin if you'd like access) - including:

  • Knowledge-Based AI coursework: Course description and Lectures
  • Additional notes/examples

• Python reference - including:

  • Code examples for: numpy, pandas, multi-dimensional visualization (often helpful for creating interpretability plots), error handling, Spark (common querying method for parallel datastores), and algorithms
  • Python setup commands
  • Python cheat-sheets

• Ubuntu 18.04 setup notes - helpful tips for setting up the Ubuntu environment, especially with configuring a CUDA environment

The following are other related courses that may be good resources:

• Deep RL course
• Stanford Deep learning for NLP course
• Neural networks for machine learning lectures

The following is a list of additional helpful links on the topic:

• paperswithcode
• deepmind
• WaveNet
• When to Use MLP, CNN, and RNN Neural Networks
• Understanding LSTM Networks
• The fall of RNN / LSTM
• Understanding SSD MultiBox — Real-Time Object Detection In Deep Learning
• Theanos examples
• max pooling
• CNN/RNN summary
• A list of cost functions used in neural networks, alongside applications
• A Neural Network in 13 lines of Python (Part 2 - Gradient Descent)
• How the backpropagation algorithm works
• GIMP convolution example
• CNN example for number recognition
• The 9 Deep Learning Papers You Need To Know About
• Cross-entropy error, as opposed to mean-squared error
• Dynamic Graphs capability of pytorch and tensorflow