Sai Likhith Kanuparthi - Machine Learning - Self Assessment

Role: Mentor for Team 6 ( Topic Recommendation Project) and Contributor in Team 2 (Tag Annotation Project)

Responsibilities:
In Team 6:

  1. Conduct presentations on the topics that are unfamiliar to teammates in Team 6.
  2. Organize scrum and status meeting along with project leads to discuss upon sprint planning.
  3. Conduct FAQ sessions for topics that require a deep-dive as a Subject Matter Expert.

In Team 2:

  1. Project plan and architecture design along with project leads
  2. Part of decision making regarding Tech stack to be used.
  3. Participate in weekly scrums.
  4. Build a recommender system for Tag Annotation with active learning loop implementation.
  5. Deploy the application in dev and test environment for demonstrative and testing purposes using Streamlit
  6. Migrate the entire application to AWS using Deep Learning Ubuntu instance.
  7. Setup Networking, VPC, EC2, RDS, SES and Quota limit of vCPUs on AWS.
  8. Presentation preparation on the work I had contributed for

My weekly assessments are as follows:

Week: 7/20

Overview of Things Performed:

  • Technical Area:
  1. Mentoring the Team 6 with basics of Machine Learning and recommender systems.
  2. Slack channel setup for communication
  3. Delegation of roles and responsibilities among different leads.
  • Tools Used: Jupyter notebooks for coding demos. STEM-Away forum and Slack channel for communication.
  • Soft Skills: Leadership principles, communication with the project leads and technical leads, delegation of authority

Achievements/ Accomplishments

  1. Successfully sketched the project planning and the architected the tech stack that will be required.
  2. Conducted FAQ and greeting sessions with teammates in order to showcase the roadmap of the internship.

Meetings Organized

  1. Kick-off meeting for Team 6
  2. FAQ session

Goals for the Upcoming Week
Deep dive webinar to be conducted on web scraping using python, selenium and Beautiful Soup.

Week: 07/27/2020

Overview of Things Performed:

  • Technical Area: Demonstrated scraping data from the discourse forum with the help of BeautifulSoup and Selenium using Python.

  • Tools Used: Jupyter notebooks for coding. STEM-Away forum, Slack channel for regular communication and posting the updates.

  • Soft Skills: ** - Leadership principles , communication with the project leads and technical leads, delegation of authority

Achievements/Accomplishments:

  1. Demonstrated the reason behind choosing this tech stack. BeautifulSoup4 to scrape data. Why selenium is required for dynamic web scraping using automation features.
  2. Explained potential Data mining techniques that can be used in this project.

Meetings Organized

  1. Web Scraping introduction
  2. Web-scraping presentation and introduction to Data pre-processing techniques

Goals for the Upcoming Week
Help the team members with any issues they might still be facing in web-scraping.

Week: 08/04/2020

Overview of Things Performed:

  • Technical Area: Data Pre-processing using pandas , Introduction to TF-IDF
  • Tools Used: Jupyter notebooks for coding. STEM-Away forum , Slack channel for regular communication and posting the updates.
  • Soft Skills: ** - Leadership principles , communication with the project leads and technical leads, delegation of authority

Achievements/Accomplishments:

  1. Demonstrated Data Pre-processing measures and TF-IDF applications in real-world

Meetings Organized

1.Data pre-processing techniques
2. TF-IDF

Goals for the Upcoming Week
Help the team members with any issues they might still be facing in data-preprocessing

Week: 8/10

Overview of Things Performed:

  • Technical Area: data processing, TF-IDF and BERT model training
  • Tools: pytorch, simple transformers, BERT
  • Soft Skills: #communication, #teamwork

Achievements Highlights

  • Compared and contrasted several methods and implemented the model as a topic classifier instead of a forum classifier.

Meetings Organized

  • Present Pre-Processing and TF-IDF
  • Implementing the BERT Model

Goals for the Upcoming Week

  • Make a forum classifier
  • Assist any team members for the Topic classifier to prepare an recommender algorithm

Week: 8/17

Working on Tag Recommender system for Team 2 and Mentoring for Topic Recommender system for Team 6.

Overview of Things Performed:
Team 2:

  • Technical Area: data processing, BERT model training
  • Tools: torch, transformers
  • Soft Skills: #communication, #teamwork

Achievement Highlights

  • Figured out how to implement the model as a category classifier instead of a forum classifier because we just had the data of one forum that was divided into multiple categories.

Meetings attended

  • 8/10 - Present Pre-Processing and TF-IDF
  • 8/12 - Check-in about implementing the BERT Model

Goals for the Upcoming Week

  • Complete the Topic Recommender system and guide the team 6 to do so.
  • Finalize a model for tag recommender system (in between TF-IDF + Logistic Regression or TF-IDF +Neural Networks or BERT+ NN)