Deep Learning Specialization by Coursera
Instructor: Andrew Ng
This repository contains a compiled version of my projects that were completed in a span of 5 months while taking the Deep Learning Specialization on Coursera taught by Andrew Ng
This course presents the most current material on deep learning today. Although, there are many other algorithms, lessons, research, and ways that deep learning is being studied, this course does a fantastic job of offering material that is relevant and can be implememnted with support from many projects in the DL community. This course uses the commong frameworks like Tensorflow and Keras and uses Python libraries such as Numpy and SciPy. Obviously, learning dense material like this from a MOOC platform is different from an academic setting like personal time with a professor or instructor, instructor quality, and lesson quality. This specialization in particular is taught by a top AI reseracher in the world who has real industry experience in applied Machine Learning and Deep Learning applications. The material was presented in a way that is relatively basic and easy to understand while honing in on the complexity of the algorithms and how the concepts are applied to solve real world problems. Generally, this course covers real world applications like computer vision, natural language processing, voice detection and facial recognition.
This course is part of my continuing study of Deep Learning and AI. For some relevant information regarding AI, Deep Learning, and the Human brain; I recommend these books:
-
Superintelligence: Paths, Dangers, Strategies by Nick Bostrom
-
Deep Learning Book by Ian Goodfellow, Yoshua Bengio, Aaron Courville
-
How to Create a Mind by Ray Kurzweil
Course 1: Neural Networks and Deep Learning
- Week 2 - Logistic Regression with a Neural Network mindset
- Week 3 - Planar data classification with one hidden layer
- Week 4 - Building your Deep Neural Network: Step by Step
- Week 4 - Deep Neural Network for Image Classification: Application
Course 2: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
- Week 1 - Initialization
- Week 1 - Regularization
- Week 1 - Gradient Checking
- Week 2 - Optimization Methods
- Week 3 - TensorFlow Tutorial
Course 3: Structuring Machine Learning Projects
- There are not programming assignments for this course
Course 4: Convolutional Neural Networks
- Week 1 - Convolutional Model: step by step
- Week 1 - Convolutional Model: application
- Week 2 - Keras - Tutorial - Happy House
- Week 2 - Residual Networks
Course 5: Sequence Models
- Week 1 - Building a Recurrent Neural Network - Step by Step
- Week 1 - Character level language model - Dinosaurus land
- Week 1 - Improvise a Jazz Solo with an LSTM Network
- Week 2 - Operations on Word Vectors
- Week 2 - Emojify
- Week 3 - Neural Machine Translation with Attention
- Week 3 - Trigger Word Detection
Follow me on Twitter : Nathan Curtis - nathan_jcurtis
LinkedIn : Nathan Curtis