Anthill Inside 2019

A conference on AI and Deep Learning

Make a submission

Accepting submissions till 01 Nov 2019, 04:20 PM

Taj M G Road, Bangalore, Bangalore

About the 2019 edition:

The schedule for the 2019 edition is published here: https://hasgeek.com/anthillinside/2019/schedule

The conference has three tracks:

  1. Talks in the main conference hall track
  2. Poster sessions featuring novel ideas and projects in the poster session track
  3. Birds of Feather (BOF) sessions for practitioners who want to use the Anthill Inside forum to discuss:
    - Myths and realities of labelling datasets for Deep Learning.
    - Practical experience with using Knowledge Graphs for different use cases.
    - Interpretability and its application in different contexts; challenges with GDPR and intepreting datasets.
    - Pros and cons of using custom and open source tooling for AI/DL/ML.

Who should attend Anthill Inside:

Anthill Inside is a platform for:

  1. Data scientists
  2. AI, DL and ML engineers
  3. Cloud providers
  4. Companies which make tooling for AI, ML and Deep Learning
  5. Companies working with NLP and Computer Vision who want to share their work and learnings with the community

For inquiries about tickets and sponsorships, call Anthill Inside on 7676332020 or write to sales@hasgeek.com


Sponsors:

Sponsorship slots for Anthill Inside 2019 are open. Click here to view the sponsorship deck.


Anthill Inside 2019 sponsors:


Bronze Sponsor

iMerit Impetus

Community Sponsor

GO-JEK iPropal
LightSpeed Semantics3
Google Tact.AI
Amex

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more

Srikanth Gopalakrishnan

@srikrvd91

Sizing biological cells and saving lives using AI

Submitted Oct 18, 2019

AI techniques are finding applications in a wide range of applications.Crowd counting deep learning models have been used to count people, animals, and microscopic cells. This talk will introduce some novel crowd counting techniques and their applications. A pharma case study will be presented to show how it was used for drug discovery to bring about 98% savings in drug characterization efforts.

Outline

Solutions that can generate accurate estimates of counts are in demand, whether it is for tallying the number of people in a video frame, counting the number of animals of an endangered species, estimating the number of objects or shapes in a picture, or for a variety of similar industry applications.

*Shortcomings of traditional approaches: *
Traditional crowd counting methods and models that use detection or regression-based approaches have been plagued by challenges such as occlusion, non-uniform distribution, perspective distortion, camera angles, and background clutter. They are not robust and often fail with even simple changes to the planned scenarios.
*State-of-the-art CNNs in counting and area estimation: *
Deep learning based crowd counting solutions offer an excellent recourse to such problems. Cascaded CNN’s use density-based estimations to preserve the spatial information and can localize the count and estimate area of cells. Such neural network architectures capture the global and local features and have been drastically improved over the past months, to achieve remarkable accuracy. There are several architectures that are being experimented – such as cascaded CNNs, muti-column CNNs.
*Real-world case studies: *
Pharma companies develop generic drugs by determining the patented drug’s composition. Solid-state characterization is a process that is critical in determining similarity of composition with in-house drug formulation. This is usually done through shape classification on a microscopic liposome image. Cells are counted and areas estimated to measure the similarity.

This is a painful, manual process performed by pathologists. AI can help simplify this task. We used a deep learning-based algorithm to automate this two-step process of counting cells and estimating the areas of cells. The task which took hundreds of hours for every set of 10 images was cut down to under 30 minutes. This led to huge savings in time, apart from helping improve accuracy.

This solution was productionized by packaging it as a visual deep learning application. The interactive UI helped keep humans in the loop. In this session, the case study will be presented with a live solution demo.

Requirements

Projector

Speaker bio

Srikanth is currently working as a Senior data scientist at Gramener, Bangalore office. He comes from a Solid mechanics background with a Masters in Simulation Sciences from RWTH Aachen University, Germany, and with work experience at EDF, Paris. After a short stint at Aeronautics department, Purdue University, he returned to India and transitioned to Data Science.
He works on interesting problems on various verticals. Srikanth is also a visiting faculty teaching data science at Department of Mechanical Engineering, PES University. He loves giving tech talks at various forums which helps him get interesting problems and suggestions from the
audience perspective.

Links

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Make a submission

Accepting submissions till 01 Nov 2019, 04:20 PM

Taj M G Road, Bangalore, Bangalore

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more