AWS Certified Machine Learning: Advanced SageMaker Functionality
AWS Certified Machine Learning: Advanced SageMaker Functionality
- discover the key concepts covered in this course
- list the frameworks that are supported in Amazon SageMaker for native code
- work with training Keras/Tensorflow models with SageMaker
- use the integrated capabilities in SageMaker to connect EMR clusters with SageMaker Notebooks
- work with SageMaker to tune models over time and manage training and tuning costs by using Spot training
- describe the distributed capabilities of SageMaker and its different methods
- work with distributed data and model parallel training practices to your Pytorch model
- work with SageMaker Autopilot to automate the key stages in a machine learning project, such as data exploration, model training, and tuning
- work with SageMaker Debugger to debug, monitor, and profile training jobs in real-time and reduce costs of your machine learning models by optimizing resources
- work with SageMaker Experiments to organize, track, compare, and evaluate iterative machine learning experiments
- work with SageMaker Clarify to build explainable machine learning models
- work with SageMaker Clarify to analyze post-training bias of machine learning models
- summarize the key concepts covered in this course
Amazon SageMaker can be used with multiple other frameworks and toolkits to precisely define machine learning (ML) algorithms and train models and is not limited to a specific set of algorithms for ML. SageMaker also provides a wide range of tools that can be used for incremental training, distributed training, debugging, or explainability. Use this course to learn about advanced SageMaker functionality, including supported frameworks, Amazon EMR, and autoML. You'll also gain hands-on experience in using new features, such as SageMaker Experiments, SageMaker Debugger, Bias Detection, and Explainability. Once you have finished this course, you'll have the skills and knowledge to implement SageMaker's advanced functionalities. Further, you'll be a step closer to preparing for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: AI Services & SageMaker Applications
AWS Certified Machine Learning: AI Services & SageMaker Applications
- discover the key concepts covered in this course
- work with Amazon Rekognition for detecting, analyzing, and comparing faces
- work with Amazon Polly for text-to-speech conversion
- work with Amazon Transcribe and Translate to explore natural language processing (NLP) capabilities
- work with seq2seq models in SageMaker for natural language processing (NLP)
- tackle forecasting problems using DeepAR
- work with BlazingText for optimized text classification capabilities
- work with object2vec general-purpose embeddings used for natural language processing (NLP) tasks
- work with SageMaker's built-in object detection algorithms
- work with SageMaker's built-in image classification algorithms
- work with SageMaker's built-it semantic segmentation algorithms
- summarize the key concepts covered in this course
Integrating AWS AI services and SageMaker with any machine learning (ML) or deep learning project is a great way to enhance its capabilities. Through this course, learn more about the additional AWS AI Services that are ready to use in the form of direct API without the need to train any ML models and dive deeper into more SageMaker functionality. Get familiar with AWS AI services that can be fully integrated into your applications in minutes. This course will also introduce you to some pre-trained algorithms in SageMaker for building high-performance natural language processing (NLP) and computer vision apps using fine-tuning techniques. After completing this course, you'll be able to identify several AI services that can be used as APIs in AWS and describe SageMaker's extensive capabilities in handling text and images. You'll also be a step closer to preparing for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: AI/ML Services
AWS Certified Machine Learning: AI/ML Services
- discover the key concepts covered in this course
- extract insights and patterns from unstructured text using natural language processing
- increase information accessibility of apps by introducing an AI-powered search engine
- increase the usability of apps by adding speech-to-text features
- describe how to enhance applications by giving them a voice
- analyze images and videos in applications to distinguish assets and extract meaningful information
- increase customer retention by adding personalized recommendations powered by Amazon's past data
- work with Amazon Forecast to accurately forecast time series without any machine learning (ML) experience
- work with Amazon Textract to parse millions of documents in no time and integrate them with Augmented AI
- describe other AI/ML services in AWS such as fraud detection, Amazon Lex, and Amazon translate
- outline how to integrate multiple AI/ML services to create an automated system
- summarize the key concepts covered in this course
Amazon offers a variety of high-level no-code services for specialized machine learning (ML) tasks. These services are primarily used to implement complex pre-built algorithms for using ML with textual and visual information. Use this course to learn more about these services. Use this course to explore services, such as Amazon Kendra, Transcribe, Polly, Rekognition, Personalize, and Textract in greater detail. You'll also delve into other AWS AI/ML services through case studies. After you're done with this course, you'll be able to describe the use cases of these services and have a general overview of how to combine multiple AWS AI/ML services to work within a single application. Moreover, you'll be a step closer to preparing for the AWS Certified Machine Learning – Specialty certification exam
AWS Certified Machine Learning: Amazon S3 Simple Storage Service
AWS Certified Machine Learning: Amazon S3 Simple Storage Service
- discover the key concepts covered in this course
- describe what Amazon S3 is used for and its main benefits
- describe how to categorize data in Amazon S3 using buckets, partitions, and tags
- define the use cases of Amazon Storage Lens and name its main features and workflows
- define the use cases of Amazon Intelligent Tiering and name its main features and workflows
- define the use cases of Amazon Access Points and name its main features and workflows
- define the use cases of Amazon Batch Operations and name its main features and workflows
- define the use cases of Amazon Block Public Access and name its main features and workflows
- work with the Amazon S3 Management Console to create buckets and use Storage Lens, Intelligent-Tiering, Access Points, Replication, and Batch Operations
- name major use cases of Amazon S3 and specify its role as the foundation for any data-related functionality of AWS
- describe how global businesses are using Amazon S3 to tackle real-world problems
- summarize the key concepts covered in this course
Amazon Simple Storage Service (S3) is widely used for many machine learning applications. Using Amazon S3, you can quickly and easily run machine learning algorithms on large databases using remote machines. In this course, you'll explore the various data formats Amazon S3 uses for machine learning pipelines. You'll then examine several Amazon S3 services in detail, looking at their use cases, workflows, and features. You'll also learn about the vital Amazon S3 functionalities related to security and access management and data storage, archiving, and analytics. When you've finished this course, you'll be able to outline how Amazon S3 is used for machine learning tasks, taking you one step closer to being fully prepared for the AWS Certified Machine Learning – Specialty exam.
AWS Certified Machine Learning: Athena, QuickSight, & EMR
AWS Certified Machine Learning: Athena, QuickSight, & EMR
- discover the key concepts covered in this course
- describe how Amazon Athena works and its use cases
- describe how tables, databases, and data catalogs work in Amazon Athena and how to query data from other AWS services in Athena
- work with Amazon Athena to create databases and tables and run queries
- describe Amazon QuickSight and its use cases
- define the main Amazon QuickSight processes and terms
- work with Amazon QuickSight to create a simple multi-visual analysis and a dashboard
- work with data, analyses, visuals, ML insights, and dashboards in Amazon QuickSight
- outline how Amazon Elastic MapReduce (EMR) works and list its benefits
- describe the use cases for Amazon Elastic MapReduce (EMR), recognize when to deploy it, and compare EMR and Glue
- outline how the Apache Hadoop open-source framework works with Amazon Elastic MapReduce (EMR) and its real-world use cases
- describe how the Apache Spark open-source framework works with Amazon Elastic MapReduce (EMR) and its real-world use cases
- summarize the key concepts covered in this course
Amazon offers a wide range of services that help enhance AWS workflows, making it much easier to create automated data processing and machine learning pipelines. Use this course to get to grips with some of these services. Explore how Amazon Athena is used for querying data and how Amazon QuickSight integrates with Athena to help decision-makers analyze data and interpret information in an interactive visual environment. Then, get hands-on practice working with both tools. Moving along, learn how Amazon EMR is used to process large amounts of data and investigate its integrations with various Apache frameworks, such as Hadoop and Spark. When you're done, you'll know how to use Amazon services to automate machine learning processes, further preparing you for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Data Analysis Fundamentals
AWS Certified Machine Learning: Data Analysis Fundamentals
- discover the key concepts covered in this course
- differentiate between categorical and numerical data types
- define Bernoulli, uniform, and binomial data distributions
- define normal, Poisson, and exponential data distributions
- describe the key role of visualization in communicating information from analyzed data
- name and describe traditional graphic types used in data analysis
- name and describe modern graphic types used in data analysis
- work with Python toolkits to implement various types of data visualization
- describe what's meant by time series analysis and define its role in data science
- recognize what's meant by advanced time series analysis concepts, such as trends, seasonality, and autocorrelation
- work with time series data in Python, implementing data analysis pipelines
- summarize the key concepts covered in this course
Data Analysis is a primary method for deriving valuable insight from raw and unstructured data. The appropriate application of data analysis techniques is vital in deriving only the relevant insight and factual knowledge from available data. Picking the correct data distribution or visualization technique can become critical to the overall data analysis results. Using this course, become familiar with the core foundations of data – the essential ground for any data analysis and machine learning operation. Examine the various types of data that exist, inherent data distributions, both traditional and modern methods of visualizing data, and how time series analysis works. When you've completed this course, you'll be able to describe the core concepts of data analysis and implement some valuable visualization and analysis techniques using Python. This course will prepare you for the AWS Certified Machine Learning - Specialty certification exam.
AWS Certified Machine Learning: Data Engineering, Machine Learning, & AWS
AWS Certified Machine Learning: Data Engineering, Machine Learning, & AWS
- discover the key concepts covered in this course
- define the basics of data engineering, its real-world applications, and the role of a data engineer
- describe the main stages of the data science pipeline (collect, store, transform, label, and optimize)
- define machine learning and list its applications in the real world
- define terminology used in machine learning and name typical approaches and workflows
- compare machine learning to other fields, like artificial intelligence, data mining, and statistics, discussing applications, limitations, and ethics
- describe how data repositories and data warehouses are used
- describe how data ingestion works and define a data pipeline
- describe how to transform data for processing
- outline the basic concept behind Amazon Web Services and describe its capabilities
- describe the ML capabilities of the AWS platform, various tools it offers, and example real-world applications where it can be used
- summarize the key concepts covered in this course
Machine learning (ML) has become indispensable across all industries. With staggering amounts of data generated globally every second, it's impossible to make sense of it without using such advanced data analytics. The AWS Certified Machine Learning - Specialty certification is one of the most coveted yet challenging certs a data engineer or scientist can get. To pass the associated exam, candidates must demonstrate knowledge of various machine learning concepts and the ability to solve real-world business challenges. Use this course to prepare for acquiring this valuable certification. Get to grips with key data engineering and machine learning terminology, concepts, tools, tasks, and workflows. Then, dive into how the AWS Machine Learning platform is used for real-world applications. Upon completing this course, you'll recognize key ML concepts and how to prepare datasets, develop ML models, and optimize models for improved predictive accuracy.
AWS Certified Machine Learning: Data Movement
AWS Certified Machine Learning: Data Movement
- discover the key concepts covered in this course
- describe how AWS Glue works and list its benefits
- specify the capabilities of AWS ETL pipelines
- recognize AWS Glue's functionality
- define data streaming and list its use cases and benefits
- compare the differences between traditional batch processing and evolving stream processing
- describe the functionality of AWS Kinesis and outline its features and workflows
- describe the capabilities of working with AWS Kinesis
- specify how to work with video streams in AWS Kinesis
- specify how to work with data streams in AWS Kinesis
- describe how data firehouse functions in AWS Kinesis
- describe how to use AWS Kinesis for data analytics tasks, such as real-time alerts and actions
- outline the functionalities of AWS Kinesis data stream
- summarize the key concepts covered in this course
As the amount of data being collected has exploded, it has become crucial for businesses to rapidly access, transform, and analyze data. From the traditional batch processing to the ever-evolving real-time data analytics, AWS has various tools to handle large volumes of data and perform real-time analytics to ensure high-service uptimes and personalize recommendations. Explore various Amazon tools like AWS Glue, AWS Data Catalog, and AWS Kinesis using this course. These tools are commonly used for data movement. This course will also help you understand how these processes function on the AWS platform and familiarize you with the data movement workflows. Data movement and processing are at the core of any data analysis, and after completing this course, you'll be familiar with multiple tools and approaches that can be used to conveniently transform raw data, combine databases, and stream data, Further, you'll be able to prepare for the AWS Certified Machine Learning - Specialty certification.
AWS Certified Machine Learning: Data Pipelines & Workflows
AWS Certified Machine Learning: Data Pipelines & Workflows
- discover the key concepts covered in this course
- describe how AWS data pipelines work and name their main benefits
- configuring an AWS Data Pipeline application using the AWS console
- compare the functionalities of AWS Data Pipeline and AWS Glue
- describe the functionality of AWS Batch and its main benefits
- specify real-world use cases of AWS Batch
- describe how AWS Step Functions works and name the principles behind workflow design
- specify real-world use cases of AWS Step Functions
- work with AWS Step Functions to manage a batch job
- describe how real-time and video data engineering pipelines work
- describe how batch processing and analytics data engineering pipelines work
- summarize the key concepts covered in this course
Creating a data pipeline is essential to making any data-related product. AWS Data Pipeline, AWS Batch, and AWS Workflow frameworks allow you to manage data using ETL data management across various AWS tools and services, making AWS a perfect platform for combining data from multiple sources. In this course, you'll learn how to automate data movement and transformation processes on AWS and define data-driven pipelines and workflows. Investigating how data pipelines enable seamless, scalable, and fault-tolerant data transfer between AWS storage and computational tools helps illuminate the full potential of AWS in machine learning. By the end of this course, you'll have a working knowledge of the most common use cases of AWS Data Pipeline, AWS Batch, and AWS Workflow, bringing you closer to being fully prepared for the AWS Certified Machine Learning - Specialty certification exam.
AWS Certified Machine Learning: Data Preparation & SageMaker Security
AWS Certified Machine Learning: Data Preparation & SageMaker Security
- discover the key concepts covered in this course
- use summary statistics to perform data preparation for an Amazon Reviews dataset
- perform visualization for data preparation of an Amazon Reviews dataset
- recognize the difference between various SageMaker data formats
- convert a data frame to a sparse matrix
- outline how to create S3 buckets for data storage
- work with Amazon Ground Truth for data labeling jobs
- describe the at rest and in-transit encryption approaches used for security in SageMaker
- work with SageMaker data accessing approaches, including VPCs, IAM, logs, and monitoring
- describe how to monitor an AWS system using CloudWatch
- outline how to record API activity using CloudTrail
- summarize the key concepts covered in this course
Building successful machine learning (ML) applications require the transformation of raw data, such that it meets the requirements of individual ML algorithms. Explore how to prepare data using Amazon SageMaker and S3 and create security services for this data through this course. Start by delving deeper into summary statistics and visualization? before moving on to security best practices for Amazon SageMaker. You'll also examine Amazon CloudWatch and Amazon CloudTrail in greater detail. After taking this course, you'll have a solid grasp of various data formats, data security practices, and monitoring and alerting services used in SageMaker. You'll also have the knowledge to prepare data for machine learning and take a step further in your preparation for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Feature Engineering Overview
AWS Certified Machine Learning: Feature Engineering Overview
- discover the key concepts covered in this course
- describe the basic concepts behind feature engineering
- describe how dimensions and features are linked to each other, specifying their impacts on building accurate ML models
- describe the capabilities of Amazon SageMaker regarding feature engineering
- describe how to use Amazon SageMaker Feature Store to fully manage repositories for ML features
- work with Amazon SageMaker Feature Store to achieve feature consistency and standardization
- describe how Amazon SageMaker Ground Truth works and name its major benefits
- work with Amazon SageMaker Ground Truth to identify its major workflows
- describe how missing data impacts ML models and name ways to deal with missing data
- specify how skewed data can affect ML classification and ways to address it
- describe how data outliers impact data analysis and name common ways to deal with outliers
- summarize the key concepts covered in this course
Feature engineering is key in extracting the right attributes from raw incoming data, which is fundamental in building reliable ML algorithms. Amazon SageMaker, a fully managed machine learning studio on AWS, provides feature engineering functionality and many other machine-learning-related tasks. Use this course to explore fundamental feature engineering concepts and learn how to use Amazon SageMaker for feature engineering tasks. Work with the various tools available in SageMaker for preparing data for ML models, such as Ground Truth (for labeling data) and Feature Store (for storing, retrieving, and sharing features). Moving along, investigate various deficiencies, such as missing values, imbalance, and outliers, in real-world data and learn how to address these challenges. Upon completion, you'll be able to carry out feature engineering tasks efficiently using Amazon SageMaker, further preparing you for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Feature Engineering Techniques
AWS Certified Machine Learning: Feature Engineering Techniques
- discover the key concepts covered in this course
- describe how to perform one-hot encoding and its main purpose
- define binning and discretization as the process of transforming numerical variables into categorical counterparts
- outline how data transformation can be used to make data more useful for data analysis
- define data scaling and normalization and describe why it is important to standardize independent variables
- outline data shuffling and define its role in removing biases and building more robust training models
- work with commonly used feature engineering techniques on real data
- recognize the basic principles behind text feature engineering
- describe the process of term frequency-inverse document frequency (TF-IDF) and its uses in text mining
- describe bag-of-words model and compare it to TF-IDF
- describe the concept of n-gram and why they are used for machine learning
- use Spark and EMR workflows to prepare data for a TF-IDF problem
- summarize the key concepts covered in this course
Raw data is typically not perfect for developing effective machine learning (ML) models. Often, it needs to be processed using various feature engineering techniques to make it more suitable for building accurate and optimized ML models. Take this course to learn about techniques that help prepare the data to be compatible and improve the performance of machine learning models. Investigate techniques that are used to improve data usability, such as one-hot encoding, binning, transformations, scaling, and shuffling. You will also learn about the importance and usage of text feature engineering and major workflows in the AWS environment. After completing this course, you'll be able to implement feature engineering techniques using AWS workflows, further preparing you for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Jupyter Notebook & Python
AWS Certified Machine Learning: Jupyter Notebook & Python
- discover the key concepts covered in this course
- describe the basic features and use cases of Jupyter Notebook related to data cleaning, transformation, visualization, and machine learning
- name Python data analysis packages and describe their functionality
- describe how the NumPy package is used for data analysis
- describe how the Pandas package is used for data analysis
- work with the NumPy package functionalities for solving data analysis tasks
- work with the Pandas package functionalities for solving data analysis tasks
- outline how the Matplotlib package is used for data analytics and visualization
- outline how Seaborn and Bokeh packages are used for data analysis
- work with Matplotlib, Seaborn, and Bokeh packages to solve data analysis tasks
- specify how the scikit-learn package is used for classification, regression, clustering, and other tasks
- work with Python toolkits to tackle a real-world data analysis problem
- summarize the key concepts covered in this course
Exploring and analyzing data to comprehend its underlying characteristics and patterns becomes increasingly vital as vaster amounts are collected. This is key in formulating the most suitable problems, the solving of which helps achieve real-world business goals. Use this course to get your head around the programming fundamentals for machine learning in AWS, which form the basis for most data exploratory steps on the AWS platform. Explore various Python packages used in machine learning and data analysis and become familiar with Jupyter Notebook's fundamental concepts. Then, work with Python and Jupyter Notebook to create a machine learning model. When you're done, you'll be able to use Jupyter Notebook and various Python packages in machine learning and data analysis. You'll be one step closer to being prepared for the AWS Certified Machine Learning - Specialty certification exam.
AWS Certified Machine Learning: Machine Learning in SageMaker
AWS Certified Machine Learning: Machine Learning in SageMaker
- discover the key concepts covered in this course
- describe the features and capabilities of Amazon SageMaker
- work with the basic features of Amazon SageMaker
- work with common SageMaker Studio tasks, such as clone a git repository, upload files, and stop training jobs
- build machine learning (ML) solutions by selecting existing resources and launch them with a single click in SageMaker Studio
- outline how to use Linear Learner and XGBoost (eXtreme Gradient Boosting) for classification and regression problems
- build and train an image classification model in SageMaker
- describe how object detection algorithms built on top of VGG and ResNet work to predict the objects present in the image and their confident score
- recognize the use of SageMaker’s semantic segmentation algorithm to predict the class of each pixel in an image and get shapes of objects
- describe hyperparameter tuning jobs in SageMaker and name recommended practices
- create a SageMaker notebook to train and finetune an object detection algorithm
- summarize the key concepts covered in this course
Amazon SageMaker provides broad-set capabilities for machine learning (ML) as it helps to prepare, train, and quickly deploy ML models. Use this course to learn more about the basic capabilities of SageMaker and work with it to implement solutions to various machine learning problems. Explore features and functionalities of SageMaker through practical demos and discover how to implement hyperparameter tuning. This course will also help you explore algorithms in SageMaker, such as linear learner, XGBoost, object detection, and semantic segmentation. After completing this course, you'll be able to train and tune a range of algorithms in order to solve simple classification tasks for natural language processing (NLP) and computer vision.
AWS Certified Machine Learning: ML Algorithms in SageMaker
AWS Certified Machine Learning: ML Algorithms in SageMaker
- discover the key concepts covered in this course
- describe SageMaker seq2seq algorithm that takes in a sequence and generates a sequence suitable for a range of tasks
- work with BlazingText in SageMaker to solve NLP problems, such as text classification and sentiment analysis
- describe how to use SageMaker’s Object2Vec algorithm that learns low dimensional embeddings of high dimensional objects
- outline how supervised algorithms can be used to forecast time series based on past data
- implement an anomaly detection system using Random Cut Forest in SageMaker
- outline the basics of SageMaker's Neural Topic Model and Latent Dirichlet Allocation algorithms and list their primary use cases
- describe the methodology behind principal component analysis (PCA) and the next level of linear learner
- recognize how to complete clustering tasks in SageMaker
- outline how to use SageMaker's most simple classification/regression algorithm named K-NN and an unsupervised algorithm to find IP usage patterns
- work with SageMaker to implement PCA and K-means algorithm for image clustering
- describe the basics and importance of reinforcement learning and Q-learning
- practice reinforcement learning workflow with SageMaker
- work with Amazon CloudWatch to analyze real-time model performance by viewing training graphs of several performance metrics
- summarize the key concepts covered in this course
Amazon SageMaker is a comprehensive machine learning (ML) toolkit that provides a broad range of functions and can be used for multiple use cases and tasks, making it an ultimate package for ML. Dive deeper into SageMaker’s built-in algorithms for solving problems, such as time series forecast, clustering, and anomaly detection through this course. Examine various functionalities available in Amazon SageMaker and learn how to implement different ML algorithms. Once you have completed this course, you'll be able to use SageMaker's machine learning algorithms for your business case and be a step further in preparing for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Model Training & Evaluation
AWS Certified Machine Learning: Model Training & Evaluation
- discover the key concepts covered in this course
- describe how factorization machines work and specify why they are powerful tools for recommender systems
- list and describe EC2 instances that can be used with SageMaker
- work with training recommender system on Amazon Reviews dataset using Python and SageMaker
- demonstrate how to reduce cost while training machine learning algorithms using Spot instances
- evaluate a trained machine learning algorithm
- deploy a machine learning model using API endpoints
- monitor API usage in real-time
- work with feature engineering and machine learning experimentations using Python and SageMaker
- demonstrate how to run hyperparameter tuning jobs with SageMaker using Python and Amazon Reviews dataset
- conduct A/B testing for models trained on Amazon Reviews dataset using production variants
- summarize the key concepts covered in this course
Training a machine learning (ML) model is the first step of many when developing ML applications that enable businesses to discover new trends within broad and diverse data sets. Use this course to learn more about SageMaker's built-in algorithm and perform model training, evaluation, monitoring, tuning, and deployment using Amazon Elastic Compute Cloud (EC2) instances. Begin by examining factorization machines and the selection of EC2 instances. Next, you'll discover how to perform model training, evaluation, and deployment. You'll wrap up the course by exploring the steps involved in tuning and testing ML models. After you're done with this course, you'll have the skills and knowledge to successfully train and evaluate a model, further preparing you for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Problem Formulation & Data Collection
AWS Certified Machine Learning: Problem Formulation & Data Collection
- discover the key concepts covered in this course
- describe scenarios where using the cloud is preferential to an on-premise solution and list the main types of problems that can be solved using machine learning
- describe the problem formulation process and define the success metrics for a machine learning project
- list examples of business problem formulation relating to machine learning
- outline Amazon's real-life problem formulation practice for commercial use of recommender systems
- describe the theoretical concepts behind recommender systems
- identify the advantages and disadvantages of collaborative filtering
- distinguish between various AWS data storage services
- work with S3 buckets to read a dataset using Python and SageMaker
- perform data quality checks on Amazon Reviews dataset using Python and SageMaker
- enumerate several built-in SageMaker algorithms
- summarize the key concepts covered in this course
In order to build machine learning (ML) applications, it is important to formulate problems and collect data. Examine the choice between the online and on-premise implementation of the problem formulation and data collection phases through this course. Explore how SageMaker algorithms help complete ML projects efficiently and work with various approaches that implement recommender systems. You'll also investigate how and when to use AWS data storage services and learn more about analyzing dataset readiness. After taking this course, you'll be able to describe the advantages and disadvantages of using the cloud over an on-premise solution and define the problem formulation and success evaluation processes. You'll also be a step closer to preparing for the AWS Certified Machine Learning – Specialty certification exam.
AWS Certified Machine Learning: Problem Framing & Algorithm Selection
AWS Certified Machine Learning: Problem Framing & Algorithm Selection
- discover the key concepts covered in this course
- outline machine learning (ML) mindset and compare the ML approach to other problem-solving techniques
- define the key characteristics of good machine learning problems
- describe the most challenging problems in machine learning (ML)
- specify how to clearly define a business problem and set success and failure criteria
- describe how to design a good output for a business problem
- identify how to formulate a business problem into a machine learning problem
- define the importance of the availability of good data and data pipeline design
- evaluate the learning ability of a machine learning model and identify potential risks and biases in the dataset as well as their resulting impact
- specify the factors that impact algorithm selection for a particular use case
- review core machine learning concepts covered in the AWS examination, such as confusion matrices, precision, and recall
- summarize the key concepts covered in this course
Problem framing and algorithm selection is the most important part of any machine learning (ML) project. ML engineers have to apply appropriate techniques that will result in expected prediction behavior. It is important to fully understand a particular task and choose among all the available methods and toolkits before implementing a machine learning project. Use this course to learn more about the ML mindset, discover how goal-oriented business problems can be formulated as machine learning problems, and describe factors that drive the selection of the correct algorithm for a particular scenario. The course will also help you refresh important ML concepts and terminologies. After completing this course, you'll be able to implement machine learning solutions to solve business problems, further preparing you for the AWS Certified Machine Learning – Specialty certification exam.