Integrating Generative AI with Human Expertise
As organizations integrate Gen AI more deeply, it’s essential to determine the right level of human oversight. This blog discusses finding the balance between AI’s capabilities and human insight.
Zero-Shot Learning and Human Analogical Reasoning!
Recently, I read David Epstein’s ‘Range’ and stumbled upon Duncker’s Radiation Problem in Chapter 5, where the author talks about analogical problem-solving. As an AI/ML engineer, I was inspired by the striking resemblance between this concept and how ML algorithms tackle zero-shot learning (ZSL) methods. I want to share the lightbulb moments and insights with you here!
Unlocking Document Intelligence: E2E Azure-Powered Chatbot with Vector-Based Search (Part 2 — Q&A)
Querying the existing vector store from (Part 1 — Embedding) using the natural language questions that drive the heart of our document processing pipeline.
Unlocking Document Intelligence: E2E Azure-Powered Chatbot with Vector-Based Search (Part 1 — Embedding)
Embark on a remarkable journey into document processing. Delve into the development of a robust document embedding mechanism and the creation of a vector store, setting the stage for streamlined and optimized querying.
Build Your First Generative AI Chatbot
Learn how to integrate a pre trained LLM with your database to build a chatbot for efficient domain-specific query responses.
Set Operations on Python DataFrames
We often perform join, union, difference, intersection, etc. operations between python DataFrames. Throughout my data science journey, Understanding the concepts of Set Theory has helped me perform these tasks efficiently. In this article, I would like to use the set theory to implement DataFrame operations.
NLP Use Case With AWS Comprehend
This article covers concepts of Natural Language Processing and how to derive insights from text data using the components of AWS Comprehend.
We will use AWS comprehend to perform sentimental analysis and topic modeling on the employee feedback data to gain an understanding of sentiments and topics in the context of change!
AWS Certified Machine Learning Specialty — Resources and Experience
This article covers my experience in getting certified with AWS Certified Machine Learning — Specialty, and I have shared the resources and cheatsheets, which helped me understand concepts! — March 2022
In the preparation phase of certification, I came across many excellent articles, blogs, and experience posts alongside the courses, which immensely helped me in understanding the width and breadth of the AWS ML world. I want to share my experience and the resources I found along the way, which boosted my confidence to take up the certification! Alright! Let’s fill in some colors.
One Year as Data Analytics Consultant— What's Unique About It?
This article covers my experience at Slalom as an Associate Consultant in the Data & Analytics practice. Previously, I worked in an R&D company as an in-house Data Scientist. These experiences are unique to me in their own ways, but I will focus on my current job in this article. While in grad school, I always wondered what it is like to be a consultant in the data field and what unique skill sets are highly valued in consulting. If you have the same curiosity, stick with me for some time, and I will try to draw a better picture.
5 Reasons to Start Journaling Today!
Journaling has been an effective method to clear my mind and share my thoughts! On and off, I have been journaling for almost seven years, and it has helped me organize my thoughts into actions and unclutter my mind. Sharing my experience of journaling and how it has helped me to think clearer. Happy reading!
Advanced Project Ideas for Data Science Graduates/Enthusiasts to Ease Their Job Search
Data science is an immense field. It can go from placing salsa near chips in a local shop to Mars rover! I will share a few project ideas that will enable you to do more realistic projects best suited for the current technology and business scenario.
Data scientists often do academic/hobby projects on clean, structured data with a straightforward approach. While I agree that it’s best to start with simple datasets, These projects are nowhere related to the real-world scenario, and often we struggle with getting a job with these projects. The companies will look for a more suited candidate for their business than what tools and technologies you worked with. If you can do a more realistic project with the help of tools and languages, then your project story will be in line with the real-world data scenario! If you agree with me so far, then let’s get started.
Data Science Job Search —
What worked for me?
Based on the study, LinkedIn has over 760 million users, with more than 260 million monthly active users. With more than 20 million companies listed on the site and 20 million open jobs, it’s no surprise to find out that 87% of recruiters regularly use LinkedIn. LinkedIn is dominating along with Indeed, which has more than 250 million unique visitors every month.
But, Are these the only platforms to get the job done? Probably, not. Since the number of active users is high in these applications, the applications/job ratio is also high. The chance of our resume getting viewed by the recruiter is less (But not zero). Based on my job search experience, I would like to share some of the not so popular techniques to ease the job search and get interviews.
Ways to Evaluate Regression Models
The very naïve way of evaluating a model is by considering the R-Squared value. Suppose if I get an R-Squared of 95%, is that good enough? Through this blog, Let us try and understand the ways to evaluate your regression model.
Publish Python Project Documentation on Confluence/HTML using Sphinx
The code documentation is essential in every project. Code documentation can be split into multiple parts. The first one is comment blocks, most helpful for programmers; These will be found through every file explaining classes, methods, parameters, possible errors. Then comes the file documentations. These are usually generated through a script that will parse a file and, based on the description in the docstrings, will create an explicit PDF. Afterwards, there should be information about the location of the code repository; additionally, there should be detailed instructions on how to run the project.
In this article, We will look into the file documentation which is generated by Sphinx. This documentation generator can be used to create .pdf, .HTML or publish the technical documentation page to a Confluence instance.
Entire Application and Admission Process for Master’s in the USA
I would like to explain the entire procedure of doing a master’s in the USA. It’s from the perspective of an Indian student. (Wrote on Jan 2019)
Scatter correction and outlier detection in NIR spectroscopy
Recent advancements in the field of AI have given rise to the integration of NIR sensor data and machine learning techniques to achieve the results. In this article, The NIR sensor is interfaced with a PC and the samples were scanned. We performed ten scans per each sample with ten seconds scan time to reduce the errors and include all the parts of the sample. In our case, the scan results were scattered and, we had outliers due to change in the light, working distance and human errors during the scanning. To reduce the scattering and to eliminate the outliers, we implemented Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV) on near-infrared (NIR) data.