Summary of Week 10 -- Capsule 1 -- Distributed Computing for Machine Learning

00:00:00 - 00:15:00

This video discusses how computer power will continue to increase, which will lead to larger data sets that will require more computation. It explains how distributed computing can be used to solve a single problem more quickly than a centralized method. Apache Spark is a framework that allows for fast machine learning.

• 00:00:00 This video discusses how computer power will continue to increase, which will lead to larger data sets that will require more computation.
• 00:05:00 This video discusses Moore's Law, which states that the number of transistors in integrated circuits will continue to increase exponentially. It also discusses how the growth of computation can be slowed or even stopped by the use of different methods. The last option is to distribute the computation across many smaller, more affordable, and faster computers.
• 00:10:00 Distributed computing is a way to divide a large task into smaller pieces that can be processed by many different computers. This can be cheaper and more reliable than using a single large computer.
• 00:15:00 This video explains how a distributed computation can be used to solve a single problem more quickly than a centralized method. Apache Spark is a framework that allows for fast machine learning.