Deep Learning
The primary success of Deep Learning is end-to-end learning in multiple scenarios including unstructured complex data such as pictures, speech and text.
It is indispensable that the practicing Data Scientist should become theoretically equipped and practiced enough to face many problems that will be solved by DL in the years to come.
We are living in an AI spring revived by the Deep Learning revolution that has been happening since 2012. Though classified as a sub-discipline of Machine Learning, it has acquired a life of its own and Deep Learning models have generated SOTA solutions in problems of computer vision, speech understanding and natural language processing. It is also competitive in tabular data as well.
The primary success of Deep Learning is end-to-end learning in multiple scenarios including unstructured complex data such as pictures, speech and text. End-to-end learning automatically extracts optimal features as a byproduct of learning and this has caused many breakthroughs in many complex problems.
Though it shares the basic nomenclature with Machine Learning, Deep Learning has introduced many new concepts such as various architectures, new layers of abstraction, training methods and tricks, architecture optimization, etc. Though it seems daunting at first to learn and digest all the materials involving Deep Learning, concepts are converging, e.g. Transformer Networks are becoming the unique architecture to solve a lot of problems. It is indispensable that the practicing Data Scientist should become theoretically equipped and practiced enough to face many problems that will be solved by DL in the years to come.
Sample Topics
- Multilayer perceptrons
- Regularization in Deep Learning
- Optimization in Deep Learning
- Convolutional networks
- Sequence modelling
- Model training, evaluation and selection
- Applications
