Course deliverables from the Coursera Deep Learnining Specialization by Andrew Ng.
Far from a topical overview, Andrew Ng's deeplearning.ai specialization on Coursera is a five-part series of courses exploring foundational concepts of Deep Learning.
Using Matrix algebra, Linear Calculus (differentiation), and Python as the programming language of choice, students black box and more intentional approaches to implementing Neural Networks (NNs) - from forward passing and back propagation within a simple deep NN and Bayesian methods for calculating weights and improving accuracy to more complex architectures, like Convolutional NNs and Recurrent NNs.
Moreover, the specialization guides thought in building intuitions about hyper-parameter tuning, decision making for future employers and research projects, and diffuses the potential career paths for this emerging area in tech through guest interviews with thought leaders in the space.
In later parts of the specialization, Ng requires students to implement well-known algorithms from scientific papers; providing a platform to iterate on and improve or lead research and DL projects of our own interest.
- Neural Networks and Deep Learning
- Improving Deep Neural Networks
- Structuring Machine Learning Projects
- Convolutional Neural Networks
- Sequence Models
| Instructor | Background |
|---|---|
| Andrew Ng | Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain |
| Kian Katanforoosh | Adjunct Lecturer at Stanford University, deeplearning.ai, Ecole Centrale Paris |
| Younes Bensouda Mourri | Mathematical & Computational Sciences, Stanford University, deeplearning.ai |