Deep Learning Specialization by Andrew Ng (Coursera)
The part of AI that is rising rapidly and driving a lot of developments and transformations that AI is touted for is Deep Learning. This Coursera Deep Learning specialization created and taught by Andrew Ng is a more advanced course series for those looking to learn about AI and deep learning, how to apply it to solve problems and build a career in AI. Since it is not an entry level program, learners are expected to have Python programming and mathematics skills and some knowledge and experience in machine learning. This specialization is in fact cited as the next logical follow up to Andrew Ng’s Machine Learning course on Coursera.
This is a five course specialization where students learn the important technical skills and tools of deep learning. These courses cover the following topics:
- Foundations of Neural networks
- How to build deep neural networks and train them on data
- Practical aspects of deep learning, like hyperparameter tuning, regularizations and optimization
- Structure machine learning projects
- How to set up train/dev/test sets
- End-to-End deep learning and when you should use it
- Build Convolutional neural networks and apply to image data
- Sequence models and how to apply them to natural language processing problems
Alongside this, courses cover various real-world case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. The students get to work on many exciting projects from building a face recognition system, to building a simple translation system, and more. Furthermore, there are interviews and discussions with top leaders and pioneers in the field that give students career advice, inspiration and help them comprehend situations that they are likely to face in the real world.
Key Highlights
- Master the theory of AI and deep learning, and see how it is applied in industry
- Practice in Python and TensorFlow
- Understand industry best-practices for building deep learning applications
- Get advice from deep learning experts and leaders in the field
- Be able to implement a neural network in TensorFlow
- Understand how to diagnose errors in a machine learning system and prioritise directions for reducing error
- Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs
Duration : 4 months, 5 hours per week
Sign up Here