Converting chemical molecular image to Inchi string representation - DL methods

To access this webinar, please register here: https://app.aiplus.training/courses/a-kaggle-winning-approach-for-converting-chemical-molecular-images-to-inchi-string-representations-via-deep-learning-methods

Topic: A Kaggle winning approach for converting chemical molecular images to Inchi string representations via deep learning methods

Speaker#1: Rajneesh Tiwari, Senior Data Scientist/Associate Director at Novartis | Kaggle Competitions Master

Rajneesh works as a Data Scientist II at Novartis and has 10+ years of ML experience across varied domains such as Telecom, Retail, Pharma, etc. He loves competing on Kaggle and is currently ranked top1% within Kaggle’s competitions tier.

Speaker#2: Tanul Singh, NLP Engineer at Jarvis | Kaggle Notebooks Grandmaster&Kaggle Competitions Master

Tanul Singh works as an NLP Engineer at Javis. Tanul loves NLP, and works to build cutting-edge NLP-based solutions. He is a Kaggle Competitions Master and a Kaggle Notebooks Grandmaster (Ranked 9 Globally)

Speaker#3: Shivam Gupta, Data and Applied Scientist at Microsoft | Kaggle Competitions Master

Shivam works as Data and Applied Scientist at Microsoft. He is working on selection and relevance tasks using DNN models on sponsored search ads data. He completed his master’s degree from IIT Kharagpur in Computer Science and Data Processing. He is also Kaggle Competitions Master with Global Rank of 303.

Speaker#4: Nischay Dhankhar, Student at NSUT Delhi | Kaggle Competitions Master

Nischay is currently a second-year Electronics and Communication Engineering student at NSUT, Delhi. He is also a Kaggle competitions master, participated in several competitions within the last two years and is globally ranked under the top 50. He has a passion for ML modeling specifically in tabular data, computer vision and ensemble learning.

Abstract:
In a technology-forward world, sometimes the best and easiest tools are still pen and paper. Organic chemists frequently draw out molecular work with the Skeletal formula, a structural notation used for centuries. Recent publications are also annotated with machine-readable chemical descriptions (InChI), but there are decades of scanned documents that can't be automatically searched for specific chemical depictions.

Automated recognition of optical chemical structures, with the help of machine learning, could speed up research and development.

Our talk will walk through the various high-level aspects of our 7th place Gold medal-winning approach on Kaggle.

Specifically, we will present our model architectures, loss functions, ensemble strategy and post-processing methods.

[September] Ger your Free General Pass to ODSC APAC 2021 - https://bit.ly/3eYLK8h

ODSC Links:
• Get free access to more talks/trainings like this at AI+ Training platform:
https://app.aiplus.training/
• Facebook: https://www.facebook.com/OPENDATASCI
• Twitter: https://twitter.com/odsc & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science
• Slack Channel: https://bit.ly/35pfPZo
• APAC Conference Sept 15th-16th: https://odsc.com/apac/
• West Conference November 15th - 18th: https://odsc.com/california/
• Code of conduct: https://odsc.com/code-of-conduct/