Skip to content

Details

Its a colloborative event between TFUG Mysuru ,Co- learning Lounge and Applied Singularity

Kindly subscribe to our Youtube channel - https://lnkd.in/e9mME-a

Follow me on Twitter for event updates : https://twitter.com/URengaraju

https://www.youtube.com/watch?v=Ot2LLlrAEgY

Talk 1 : Designing and implementing domain-specific sentiment analysis
(6 to 7 pm)

As we move towards specificity and contextualisation in our AI products and initiatives, sentiment analysis is one of the most common ones that doesn’t pass this test for us. While using out-of-the-box solutions like CoreNLP, Google, Watson etc., it’s useful to keep in mind that they do not adapt to different situations very well.

This session covers the current drawbacks with sentiment analysis solutions, how to think about it to solve your problems, and exploring multiple ways to build your first domain specific sentiment analysis solution.

Agenda:

  • What is Sentiment Analysis and where is it used?
  • What are the drawbacks and why is domain specificity required?
  • Sentiment Analysis as a spectrum versus hard-classification
  • Lexicon based versus Classification versus Word-Embedding solutions
  • LexScore Algorithm
  • Picking what fits your context the best
  • Use-cases
  • Q/A

Shantanu is an MIT New Ventures Leadership (Class of 2019) graduate & on the Alumni Advisory Board. He co-created MiMent, a finalist of the program structured around personalized learning plans for Indian university students looking out for jobs and places to apply their skills.
He is the author of the LexScore algorithm, an internationally published researcher in Natural Language Processing, Domain Specific Sentiment Analysis and Analytics with equally strong extracurricular accolades at the national level. A 2-time winner of the world’s largest annual code competition (AI Theme) & an active contributor to Stanford Scholar with one of his papers voted highest on the platform.

Talk 2 -- Topic : [HandsOn] Transfer Leaarning with Tensorflow 2.0

Speaker Bio :

Joinal Ahmed is a skilled Data Scientist and an open source enthusiast. He has experience in developing Deep Learning Models and Building AI Systems from Scratch. With 3 year of experience working with startups in Machine Learning , Computer Vision and Data Science, I have developed several Ml/DL models, working from Data Cleaning, to Training models to fine tuning them. Have Worked with Cloud Factory, NIH, Maxin AI, Fankave , Spline.ai as Consultant for ML,Computer Vision, ETl and Data Pipelines.

Abstract :

in this tutorial we will explain how to do transfer learning with TensorFlow 2. covering topics like:

Handling Customized Dataset
Restore Backbone with Keras's application API
Restore backbone from disk
saving models and callbacks

Talk 3 -- Topic : Machine Learning in Javascript (8 to 9 pm)

Speaker Bio :

Gant Laborde is an owner of Infinite Red, mentor, adjunct professor, published author, and award-winning speaker. For 20 years, he has been involved in software development and continues strong today. He is an “open sourcerer”, team leader, and aspires to one day become a mad scientist. He blogs, videos, and maintains popular repositories for the community.

Community Partners for the event:

Co-Learning Lounge :
"Co-learning lounge" is the community where they are transforming global education with the help of collaborative learning.
Know more about the community here: www.colearninglounge.com and subscribe to their YouTube channel to never miss any learning: https://bit.ly/CLLYT

Applied Singularity:

Applied Singularity is a platform where IoT, AI and Bio professionals can learn about the latest in frontier tech, develop usable skills, find top jobs, access key resources and build their professional networks. Download the Applied Singularity mobile app from www.appliedsingularity.com/app.

You may also like