I would like to present my heartful thanks to instructor Andrew Ng for coming up with such a wonderful course & a wonderful explanation on the topics! I really learned a lot from you!
This repository contains the solution of all the weekly quizzes and programming assignments of all five courses in Deep Learning specialization by deeplearning.ai on Coursera.
The first course is: Neural Networks and Deep Learning.
After completing this first course in the specialziation, now I
- Understand the major technology trends driving Deep Learning
- Am able to build, train and apply fully connected deep neural networks
- Know how to implement efficient (vectorized) neural networks
- Understand the key parameters in a neural network's architecture (forward propagation and backward propagation).
The second course is: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization.
After completing this second course in the specialization, now I
- Understand industry best-practices for building deep learning applications
- Am able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking
- Am able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence
- Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance
- Am able to implement a neural network in TensorFlow.
The third course is: Structuring Machine Learning Projects.
After completing this third course in the specialization, now I
- Understand how to diagnose errors in a machine learning system, and
- Am able to prioritize the most promising directions for reducing error
- Understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance
- Know how to apply end-to-end learning, transfer learning, and multi-task learning.
The fourth course is: Convolutional Neural Networks.
After completing this fourth course in the specialization, now I
- Understand how to build a convolutional neural network, including recent variations such as residual networks.
- Know how to apply convolutional networks to visual detection and recognition tasks.
- Know to use neural style transfer to generate art.
- am able to apply these algorithms to a variety of image, video, and other 2D or 3D data.
The fifth course is: Sequence Models.
After completing this fifth and final course in the specialization, now I
- Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs.
- Am able to apply sequence models to natural language problems, including text synthesis.
- Am able to apply sequence models to audio applications, including speech recognition and music synthesis.