[Skillshare] Machine Learning on AWS SageMaker for Beginners
About This Class
Build, train, and deploy a machine learning model using SageMaker ; Data Wrangling for Machine Learning on AWS Cloud
This course is designed for the students who are at their initial stage or at the beginner level in learning the Machine Learning concepts integrated with cloud computing using the Amazon AWS Cloud Services.
This course focuses on what cloud computing is, followed by some essential concepts of Machine Learning. It also has practical hands-on lab exercises which covers a major portion of setting up the basic requirements to run projects on SageMaker
This course covers five (5) projects of different machine learning algorithms to help students learn about the concepts of ML and how they can run such projects in the AWS SageMaker environment. Below is list of projects that are covered in this course:
1- Titanic Survival Prediction
2- Boston House Price Prediction
3- Population Segmentation using Principal Component Analysis (PCA)
4- Population Segmentation using KMeans Clustering
5- Handwritten Digit Classification (MNIST Dataset) -> Capstone
Today Data Science and Machine Learning is used in almost all the industries, including automobile, banking, healthcare, media, telecom and others.
Amazon SageMaker helps data scientists and developers to prepare, build, train, and deploy high-quality machine learning (ML) models quickly by bringing together a broad set of capabilities purpose-built for ML.
Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to prepare build, train, and deploy machine learning (ML) models quickly. SageMaker removes the heavy lifting from each step of the machine learning process to make it easier to develop high quality models. SageMaker provides all of the components used for machine learning in a single toolset so models get to production faster with much less effort and at lower cost.
Look forward to see you enroll in this class to learn Machine Learning in AWS SageMaker platform. Best of luck!
Hands-on Class Project
The course has 1 capstone project (Digit Classification – MNIST Handwritten) at the end, this project walks students through the entire workflow of applying the necessary steps to implement a complete machine learning project. Students perform the process for uploading the dataset, evaluating it, performing the exploratory and data analysis towards the final step of training the model to perform the required task. This demonstrates the basics learned by the students in the former sections. The solution of the project is provided but it is recommended that the student first try to solve the problem on their own and then move to the solution. Below is the description of the project:
- The first project is to develop and training a working model for the MNIST handwritten dataset. The students are required to import the dataset and then prepare it for model training. The working model should be able to identify among various handwritten images available in the test dataset.
2: What action the student must take in order to complete the project
Students should watch all course sections in the order as the course is designed. Students must create an AWS account and enable the sagemaker feature in free tier to proceed and should perform all the labs in order to complete the project.
3: What skills they need to apply to complete the project.
Students must be able to learn the concepts explained in the course. To be completely able to solve the project problems, a student must have knowledge of importing data, data cleaning, data manipulation, adding calculated fields, creating visuals, performing the EDA process, training the model and deploying it with the help of endpoints. All these concepts are well explained in each section with indepth details.
4: How students can share the project with other students on the platform in order to get feedback.
Students can share their notebooks using the cloud sharing platforms and ask for collaboration or any help if required directly from the instructor.
All the resources are shared in the resource section for this course.
Size: 1.50 GB