Implementation of AI on AWS Cloud

Machine Learning on AWS

Putting machine learning in the hands of every developer

AWS offers the broadest and deepest set of machine learning services and supporting cloud infrastructure, putting machine learning in the hands of every developer, data scientist and expert practitioner. AWS is helping more than one hundred thousand customers accelerate their machine learning journey.

That’s why more than one hundred thousand customers, from the largest enterprises to the hottest startups, choose AWS AI— more than any other cloud platform.

Explore AWS AI Services

AWS pre-trained AI Services provide ready-made intelligence for your applications and workflows.

AI Services easily integrate with your applications to address common use cases such as personalized recommendations, modernizing your contact center, improving safety and security, and increasing customer engagement.

Because we use the same deep learning technology that powers Amazon.com and our ML Services, you get quality and accuracy from continuously-learning APIs. And best of all, AI Services on AWS don’t require machine learning experience.

Services learned on Day1

~ Got the overview about some of the AI services used in AWS Amazon Rekognition, Amazon Translate, Amazon Polly, Amazon Transcribe, Amazon Personalize, Amazon Kendra, Amazon Fraud detector, Amazon Lex, Amazon Textract, Amazon Forcast, Amazon Codeguru, Amazon Comprehend
~ AI is branch of computer science concerned with building smart machines capable of performing tasks that typically requires simulation of human brain intelligence.
~ Advantage of using cloud-based AI is AI apps are robust and are able to quickly discover important and relevant findings during the processing of big data and also minimalize the use of resources.
~ Since for better result its always great to have as much as data we can afford to have and companies like Amazon and Google they generate terabytes of data and they use there data itself in the services they provide in AWS. Henceforth its always preferrable to use these AI services on the top of the cloud for better performance in results.
~ Image recognition is the ability of a system or software to identify objects, people, places, and actions in images.
~ Speech recognition is the process by which a machine identifies spoken words. Basically, it means talking to our computer, and having it correctly recognized what we are saying.
~ Confidence Score is a threshold that determines what the lowest matching score acceptable to trigger an interaction

~ Jupyter notebook is a web tool which free and open source it provides the interactive data science environment.
~ import opencv-python library can click the picture.

~ boto3 python library helps in contacting to the AWS services from Python.
~ S3 is the scalable object a storage service from amazon where documents, metadata files etc are stored and there are various permissions inside the same using which we can provide necessary security and host files if needed.
~ IAM(Identity Access Management) allows to manage access to AWS services, it also gives permission to create AWS users and groups.
~ We can use all these services from GUI but its always preferred to use the CLI as per Industry Standards
~ Code to upload file into Scalable Storage Object : -
import boto3
s3 = boto3.resource(‘s3’)
s3.Bucket(<bucket_name>).upload_file(<object_name> , <file_name>)
~ client( ) function in boto3 is to be used for aws rekognition.
~ Dictionary is datatype of response from the recognition.
~ Amazon Polly is a cloud service by AWS, that converts text into speech.
~ It allows developers to create speech-enabled applications and products.
~ Speech Synthesis Markup Language is an XML-based markup language for speech synthesis applications.
~ Code to connect to polly from python using boto3:-
import boto3
po = boto3.client(‘polly’)
res= po.synthesize_speech(Text = “”, OutputFormat= ‘choose_as_per_choice’, VoiceId = ‘choose_as_per_choice’)
~ To play audio in Python, we use IPython library:
IPython.display.Audio(‘filename.mp3’)

Services learned on Day2

~ Amazon Lex is a service used for building conversation based interfaces into any application using voice and text. Its more of like chat bot service where we can create and customzie our own chatbot.
~ NLP is a field in machine learning with the ability of a computer to understand, analyze, manipulate, and potentially generate human language.
~ An intent represents an action that the user wants to perform. We create a bot to support one or more related intents.
~ Amazon Kendra is a service provided by AWS that acts as an internal search engine like a Google search engine.
~ Benifits of Amazon Kendra is that this service is not just limited to files but also searches for matching REGEX inside those files which makes this unique in its own way.
~ Amazon codeguru is a developer tool provided by AWS which helps to give recommendation how to improve the performance of an app or software in terms of space and time complexity.
~ The python library that needs to be installed to access the profiler of Code Guru is codeguru_profiler_agent.

~ command for running the agent of Code Guru is:- $ python -m codeguru_profiler_agent-r <region><program_name>.
~ Amazon Comprehend is an NLP service that uses machine learning to uncover information in unstructured data.
~ Amazon Textract is a machine learning service that automatically extracts text, handwriting and data from scanned documents.
~ Amazon Translate is the service that helps to translate content from one language to another.
~ Amazon Personalize is a fully managed machine learning service that goes beyond rigid static rule based recommendation systems.
~ Amazon Fraud Detector is a fully managed service that makes it easy to identify potentially fraudulent online activities such as online payment fraud and the creation of fake accounts.

I’m very much thankful to Vimal Daga sir and LinuxWorld Informatics Pvt Ltd India to have organized such useful and wonderful workshop.

Thank You.