About the Course

There are four functional roles in Data Science, namely, Business Analyst, Data Analyst, Machine Learning Engineer and Data Engineer. The PA track targets the Machine Learning Engineer role. After mastering the subjects of Data Analysis, viz. Traditional Machine (Shallow) Learning and Statistical Modelling, now is the time to delve into Predictive Analytics.

This course will take you deep into the world of Deep Learning. You will learn both Supervised and Unsupervised Deep learning. Not only that, you will also learn how to apply these skills on Big Data on the cloud. Cutting edge techniques such as transfer learning are also taught.

Prerequisites

• Curiosity
• Basic arithmetic skills - Brackets, division, multiplication, addition, subtraction
• Ability to operate a computer, keyboard and mouse
• Ability to use a web browser to access and use the internet
• Ability to install software on your computer
• Data Analysis (DA Track)

Hardware and Software Requirements

• Physical operational computer (not in virtualization) – Fedora 34 or greater OR PopOS/Ubuntu 20.04 or greater, OR Windows 10 or greater, OR MacOS 10 or greater
• 16 GB RAM
• Broadband internet connection > 5 MBPS
• 100 GB free hard disk space. SSD Drive recommended
• Dedicated graphic card is not required but recommended. Cloud will be used.
• Access to a credit card for Google Cloud Compute account with billing enabled and free $300 credits

Learning Objective

Deep Learning

• Introduction To Tensorflow 2
• Keras
• Supervised
  • Artificial Neural Networks (ANN)
  • Convolution Neural Networks (CNN)
  • Transfer Learning
  • Recurrent Neural Networks (RNN)
  • Weight Initialization

Google Cloud Compute Platform (GCP)

• Google ML APIs
• Google AutoML
• Google Vertex AI
• Bigquery ML

Production ML Systems

Art Of ML

Unsupervised

• Self Organizing Maps (SOM)
• Restricted Boltzmann Machines (RBM)
• Autoencoders

Learning Outcome

• Use Tensorflow 2/Keras to create Deep Neural Network Architectures
• Understand and apply the fundamentals of Artificial Neural Networks
• Learn the fundamentals of Computer Vision and Convolution Neural Networks
• Learn to harness pre-trained models and retrain portions of them on your custom Data
• Learn how to give a short term memory to your Deep Neural Network models by using Recurrent Neural Networks (RNNs)
• Learn to use Google’s Machine Learning APIs
• Learn to use AutoML to create Deep Learning Models
• Learn to apply both Supervised and Unsupervised Deep Learning Models to real world Big Data

Fineprint

• The topics presented are tentative and we reserve the right to add or remove a topic to update or improve the bootcamp, or for a technical or time reasons.
• † taxes extra.