Google has just released a new three-month free course on Deep Learning.
It aims to help data scientists get to grips with deep learning as well as TensorFlow — the in-house machine learning software that Google open sourced last November. This is an intermediate to advanced level course offered as part of the Machine Learning Engineer Nanodegree program. To really understand the course, you had better first take a course in machine learning, and get familiar with supervised learning methods.
What is Deep Learning?
As a new area of Machine Learning research, Deep Learning has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. Some typical use cases of Deep Learning include
|Voice recognition||UX/UI, Automotive, Security, IoT|
|Voice search||Handset maker, Telecoms|
|Flaw detection (engine noise)||Automotive, Aviation|
|Fraud detection (latent audio artifacts)||Finance, Credit Cards|
|Log analysis/Risk detection||Data centers, Security, Finance|
|Enterprise resource planning||Manufacturing, Auto., Supply chain|
|Predictive analysis using sensor data||IoT, Smart home, Hardware manufact|
|Business and Economic analytics||Finance, Accounting, Government|
|Recommendation engine||E-commerce, Media, Social Networks|
|Sentiment Analysis||CRM, Social media, Reputation mgt.|
|Augmented search, Theme detection||Finance|
|Thread detection||Social media, Govt.|
|Fraud detection||Insurance, Finance|
|Image search||Social media|
|Machine vision||Automotive, aviation|
|Photo clustering||Telecom, Handset makers|
|Motion detection||Gaming, UX, UI|
|Real-time thread detection||Security, Airports|