A model is a set of rules, formulas, or equations that can be used to predict an outcome based on a set of input fields or variables.
This blog will cover some quick tips including FAQs on the topics that we covered in the Day 7 & 8 live sessions which will help you to clear Certification [MLS-C01] & get a better-paid job.
The previous week, In Day 5 & 6 sessions we got an overview of Data Engineering in AWS and Data Analysis in AWS. And in this week Day 7 & 8, we covered the concepts of Modeling in AWS, Artificial Intelligence in AWS, and Introduction to SageMaker. We also performed some Hands-on Apache Spark on EMR, EMR Notebooks, Security, and Instance Types, Amazon Lex, Amazon Polly, Amazon Rekognition, Amazon Translate from 30+ extensive labs.
So, here are some of the FAQ’s that help you keep you in pace with us from the Live session from Module 6: Modeling in AWS
> Modeling in AWS
A model is a set of rules, formulas, or equations that can be used to predict an outcome based on a set of input fields or variables
For example, a financial institution might use a model to predict whether loan applicants are likely to be good or bad risks, based on information that is already known about past applicants.
Q1: What is Softmax function?
A: Softmax function as an activation function which is used as final output layer to converts outputs to probabilities of each classification as hot encoded
Q2: Explain typical usage of CNN with Keras/Tensorflow?
A: Here is a detailed explanation of it. Let’s start from the input layer in our network
Input layer->Convo Layer->Pooling Layer->flatten layer
Input layer: The input layer in CNN should contain image data. Image data is represented by a three-dimensional matrix usually. Then we do reshape that image, for example, let’s consider the MNIST data image which is 28 x 28 = 784 into the single column before feeding it into the input layer.
Convo Layer: The convo layer is sometimes called the feature extractor layer because features of the image (As we discussed extracting the features stop sign in an image) are get extracted within this layer. First of all, a part of the image is connected to the Convo layer to perform convolution operations.
Pooling Layer: The pooling layer is used to reduce the spatial volume of the input image after convolution. It is used between two convolution layers usually
Flatten layer: Once the pooled featured map is obtained from the pooling layer, the next step is to flatten it. Flattening involves transforming the entire pooled feature map matrix into a single column which is then fed to the neural network for processing.
Q3: What is the ideal batch size in tuning neural networks?
A: There is no ideal batch size, it also depends on what Kind of algorithm you choosing, as part of AWS inbuilt algorithms there are suggested range for choosing a batch size, for example, BlazingText suggest to use the batch size from [8 to 32]
Q4: How Specificity is different from Sensitivity?
A: Sensitivity (True Positive rate) measures the proportion of positives that are correctly identified (i.e. the proportion of those who have some condition (affected) who are correctly identified as having the condition).
Sensitivity = TP/TP + FN is all about true positive rate
Specificity (True Negative rate) measures the proportion of negatives that are correctly identified (i.e. the proportion of those who do not have the condition (unaffected) who are correctly identified as not having the condition)
Specificity = TN/TN + FP is all about the true negative rate
Source: Wikipedia
Q5: Which is cheaper (i) configuring own EC2 for deep learning or (ii)launching SageMaker?
A: EC2 is going to charge more as compared to SageMaker because, for example, once you launch a deep learning instance for ec2, so it comes with lots of configuring software like SageMaker configured with MXnet, TensorFlow along with some Nvidia packages. But it also depends on what size of memory you are going to pick and some other factors.
Also Check: Our blog post on Amazon Rekognition. Click here
>Artificial Intelligence In AWS
Artificial Intelligence (AI) in the field of computer science dedicated to solving cognitive problems commonly associated with human intelligence, such as learning, problem-solving, and pattern recognition
Source: AWS
Q6: Can Amazon Comprehend handle a lot of text messages for different customers?
A: Yes, Amazon Comprehend can handle a lot of text messages for different customers
Source: AWS
Q7: In Amazon Forcast, there are univariate or multivariate time series?
A: Amazon Forecast promises they support any time series forecast, as per personal experience they have produced efficient results for Univariate Time Series
Source: AWS
Q8: Is Amazon Forecast going to give a different best model for each product or select a model for all?
A: Amazon Forecast will automatically examine your business data & will choose the best suitable model to produce forecasted results(It may select a different model depending on your business data). But still, we have an option to choose models manually
Q9: Amazon Lex use cases in the work environment?
A: Amazon Lex can be used to implement some of the following business use cases. Commerce ChatBot, allowing you to order food for dinner. Enterprise ChatBot, allowing you to connect to enterprise data resources
Name a few here TransUnion, GE Appliances, Johns Creek, Twilio
Q10: Amazon Textract is different from RPA?
A: In more advanced level Amazon Textract uses advanced Optical Character Recognition (OCR) technology to identify form labels and values and extracts information from tables without compromising the structure, it’s different from RPA
Source: AWS
Q11: AI services in AWS are black-box algorithms or we can view their code?
A: We cannot view the code of the services as these are the black-box algorithms. But you can make your own algorithm.
> Introduction to SageMaker
Amazon SageMaker is a fully managed machine learning service. With Amazon SageMaker, data scientists and developers can quickly and easily build and train machine learning models, and then directly deploy them into a production-ready hosted environment.
It provides an integrated Jupyter authoring notebook instance for easy access to your data sources for exploration and analysis, so you don’t have to manage servers.
Q12: Why Amazon SageMaker?
A: Amazon SageMaker is a fully managed machine learning service. With Amazon SageMaker, data scientists and developers can quickly and easily build and train machine learning models, and then directly deploy them into a production-ready hosted environment.
It provides an integrated Jupyter authoring notebook instance for easy access to your data sources for exploration and analysis, so you don’t have to manage servers.
Feedback Received…
From our AWS-ML Day 7 & day 8 session, we received some good feedback from our trainees who had attended the session, so here is a sneak peek of it.
To know more about AWS-ML certification and whether it is the right certification for you, read our blog on AWS Certified Machine Learning – Specialty[MLS-C01]: Everything you must know
Quiz Time (Sample Exam Questions)!
With our AWS Certified Machine Learning – Specialty training program, we cover 150+ sample exam questions to help you prepare for the certification [MLS-C01].
Check out one of the questions and see if you can crack this…
Ques: A multinational banking organization provides loan services to customers worldwide. Many of its customers still submit loan applications in paper form in one of the bank’s branch locations, The bank wants to speed up the loan approval process for this set of customers by using machine learning. More specifically, it wants to create a process in which customers submit the application in a matter of minutes.
What can the bank use to read and extract the necessary data from the loan applications without needing to manage the process?
A) Amazon Textract
B) An LSTM model
C) Amazon Personalize
D) A Customer CNN Model
Comment with your answer & we will tell you if you are correct or not!!
Related/References
- AWS Certified Machine Learning Specialty: All You Need To Know
- AWS Certified Machine Learning – Specialty: Step-by-Step Hands-On
- Exploratory Data Analysis With AWS Machine Learning
- Data Engineering With AWS Machine Learning
- Amazon Kinesis Overview, Features And Benefits
- [MLS-C01] AWS Certified Machine Learning – Specialty QnA Day 1 & 2 Live Session Review
- [MLS-C01] AWS Certified Machine Learning – Specialty QnA Day 3 & 4 Live Session Review
Next Task For You
If you are also interested and want to more about the AWS certified Machine Learning Specialist then join the Waitlist.
Leave a Reply