From the course: Amazon Web Services Machine Learning Essential Training
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Best practices for algorithms and architectures - Amazon Web Services (AWS) Tutorial
From the course: Amazon Web Services Machine Learning Essential Training
Best practices for algorithms and architectures
- [Instructor] So to summarize our learning in this course. First around algorithms, use the right algorithm for the job. Simple as possible always wins. I purposely reviewed the same problem using different algorithms and different platforms, the digit classification problem, because that's the way you should look at your analysis problems. You should run them across different algorithms and different platforms, always selecting the simplest one. You want to take advantage of AWS algorithm optimization. Again, I'm going to call out SageMaker here. Amazon has worked very diligently to optimize ten common algorithms, and it should be part of your testing to see if running on the SageMaker platform, with the automatic hyper-parameter tuning included, will help you get your machine-learning model to market quicker. You want to consider using the machine-learning APIs first. Look at Lex, Polly, Recognition, and the growing list. I'm sure there will be more by the time you watch this. This…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.