/Deep-Learning-Projects

Earlier DNN projects from theory to application, guided by Andrew Ng from Deep Learning Specialization (TF + Keras)

Primary LanguageJupyter Notebook

Deep Learning Projects

Deep learning projects from beginner (ex. shallow NN, backprop) to advanced (ex. YOLO, generate jazz music). Topics including deep neural network, improving neural network, building neural network project, convolutional neural network, and sequence model. Started with only using NumPy for shallow NN, then moved on to tensorflow with/without keras for deeper networks.

The primary areas tackled were fundamentals of deep learning, CNN, and RNN. I have also worked on Generative Adversarial Network (GAN) and Reinforcement Learning (RL).

Convolutional Neural Network Projects



Artistic Neural Style Transfer - manipulate an image to have the style of the another image



_________________________________________________________________________



Facial Recognition - recognize different faces with corresponding names with triple loss



_________________________________________________________________________



Vehicle Detection - use transfer learning to detect vehicle from roof camera (checkout my Self-Driving-Car-Projects repo if this field interests you)



Recurrent Neural Network Projects



Text Generator - make fake dinosaur names and even Shakespearean poems


_________________________________________________________________________



Jazz Improvisation - generate Jazz music with LSTM



_________________________________________________________________________



Emoji Generator - append emoji to sentences with word embeddings



_________________________________________________________________________



Date Translation - translate date format from "DAY MONTH YEAR" to "YEAR-MONTH-DAY" with attention architecture



Topics

Neural Networks and Deep Learning

  • Introduction to deep learning
  • Neural Networks Basics
  • Shallow Neural networks
  • Deep Neural Networks

Improving Deep Neural Networks

  • Practical aspects of Deep Learning
  • Optimization algorithms
  • Hyperparameter tuning, Batch Normalization and Programming Frameworks

Structuring Machine Learning Projects

  • Diagnose and Treat Errors in Machine Learning Model
  • Understand Complex Machine Learning Settings and Limitations
  • Apply End to End, Tranfer, and Multitask Learning

Convolutional Neural Network

  • Foundations of Convolutional Neural Networks
  • Deep convolutional models: case studies
  • Object detection
  • Special applications: Face recognition & Neural style transfer

Sequence Models

  • Recurrent Neural Networks with LSTM
  • Natural Language Processing & Word Embeddings
  • Sequence models & Attention mechanism

Papers

Reading these papers allowed me to see how the state of the art models evolve and to gain more indepth understanding of the theory behind deep learning.

Visualization of the evolution of CNN architectures

Acknowledgement

As declared in the description, this collection of projects is mentored by Stanford Professor Andrew Ng through the Coursera Deep Learning Specialization. Thanks to his guidance, I gained balanced knowledge of both the theory and the practical application of deep learning.