Complete course along with lecture slides,additional notes and project notebooks taught by the famous Andrew Ng !!
- This repository is for those interested in learning Deep-Learning from scratch and although it's not necessary but its good to have basic understanding of machine learning (You can refer [https://github.com/rahulg-101/Complete-Machine-Learning-Guide-using-Scikit-Learn], mathematics behind few algorithms like Logistic Regression, and python knowledge.
- Also, if you are not very fond of getting a certificate and rather want to just expand your knowledge base in the field or if you're also a little short on budget to purchase the actual course, then you are at THE RIGHT PLACE !!
This repo although has all the contents associated with the original course but
SOME PROJECTS
from particular weeks if you try to run locally in your system might not work from Course 4(Week 2) & 5(Week 1 and Ungraded Labs 2 & 3 from Week 4) since the associated project dependencies were too large and due to GITHUB memory constraints, I was unable to push them into the repository.
The course is formulated in very simple and easy to understand way but since the course covers a whole lot of topics,so completing it might take some time but ITS TOTALLY WORTH !! The videos associated with particular courses' of the specialization are also available on YouTube if you need them, so you have everything you need to get started !!
This repo consists of all the course lecture slides along with project notebooks present in a structured manner as present in the original course.
Course Number > Week > Week Slides & Project Notebooks
-
Course 1 - Neural Networks and Deep Learning
-
Week 1 - Intro to Deep Learning
-
Week 2 - Neural Network Basics
- Python Basics with Numpy
- Logistic Regression with a Neural Network Mindset
-
Week 3 - Shallow Neural Networks
- Planar Data Classification with One Hidden Layer
-
Week 4 - Deep Neural Networks
- Building your Deep Neural Network: Step by Step
- Deep Neural Network - Application•180 minutes
-
-
Course 2 - Improving Deep Neural Networks Hyperparameter Tuning, Regularizaiton and Optimization
-
Week 1 - Practical Aspects of Deep Learning
- Initialization
- Regularization
- Gradient Checking
-
Week 2 - Optimization Algorithms
- Optimization Methods
-
Week 3 - Hyperparameter Tuning, Batch Normalization and Programming Frameworks
- TensorFlow Introduction
-
-
Course 3 - Structuring Machine Learning Projects
- Week 1 - ML Strategy 1
- Week 2 - ML Strategy 2
-
Course 4 - Convolution Neural Networks
-
Week 1 - Foundations of Convolution Neural Networks
- Convolutional Model, Step by Step
- Convolution Model Application
-
Week 2 - Deep Convolution Models
- Residual Networks
- Transfer Learning with MobileNet
-
Week 3 - Object Detection
- Car detection with YOLO
- Image Segmentation with U-Net
-
Week 4 - Special Applications : Facial Recognition and Neural Style Transfer
- Face Recognition
- Art Generation with Neural Style Transfer
-
-
Course 5 - Sequence Models
-
Week 1 - Recurrent Neural Networks
- Building your Recurrent Neural Network - Step by Step
- Dinosaur Island-Character-Level Language Modeling
- Jazz Improvisation with LSTM
-
Week 2 - NLP and Word Embeddings
- Operations on Word Vectors - Debiasing
- Emojify
-
Week 3 - Sequence Models and Attention Mechanisms
- Neural Machine Translation
- Trigger Word Detection
-
Week 4 - Transformer Network
- Transformers Architecture with TensorFlow
- Optional Labs
- Transformer Pre-processing
- Transformer Network Application: Named-Entity Recognition
- Transformer Network Application: Question Answering
-