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 teaching the computer how to “talk”, its time to teach the computer how to “see”. This course will teach you all the industry standard techniques of Computer Vision (CV). Not only that, you will learn some fascinating developments in Computer Vision such as Generative Adversarial Networks (GANs), which allow the computer to create something new like an artist!

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 Analytics : Intermediate : PA201

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

Computer Vision (CV)

• Introduction
• Numpy Image
• Feature Extraction
• OpenCV
• YOLO
• SSD
• Deep Dream
• Generative Adversarial Networks (GANs)
• Style Transfer using Tensorflow Hub

Interpreting Computer Vision Models

• SHAP
• Keras
• Open CV
• UMAP

Recommender System

• Types Of Recommendation Algorithms
• Intro to Content Based Filtering
• Intro to Collaborative Filtering
• Contrasting Different Recommendation Algorithms
• Understanding The Nearest Neighbors Model
• Measuring Distance Between Users
• Implementing The Nearest Neighbors Model
• Understanding The Latent Factors Model
• Contrasting The Nearest Neighbors And Latent Factors Models
• Decomposing The Rating Matrix
• Implementing The Latent Factor Model
• Associative Rule Learning
• Item Based Collaborative Filtering

Spark

• Spark ML
• ALS on Spark

Learning Outcome

• Understand various non-deep techniques for Computer Vision (CV)
• Teach the computer how to recognize images using Deep Learning
• Teach the computer how to generate (image) Data instead of just recognizing
• Learn to explain CV models to explain their predictions using state-of-the-art techniques
• Learn to create Recommendation Systems

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.
• † 18% Indian taxes extra.