Karan Pathak

When something is important enough, you do it even if the odds are not in your favor

Elon Musk

Optimizing my Life and reducing human efforts using machine learning. Currently working on computer vision problems. Interested in robotics intelligence particularly in reinforcement learning and autonomous driving.


  • DataTurtles

  • Founder

Building a community of thriving researchers, professionals and enthusiasts in AI domain for knowledge sharing through different platforms and media.

Visit us - DataTurtles

July 2020 - Present

  • Schlumberger

  • Data Scientist

  • |Sub-Surface Team

Working on problems to detect various seismic geobodies such as Faults, Top of Salt, and Seafloor using techniques like semantic segmentation with 2D and 3D CNN, deep transfer learning, and weakly supervised deep learning respectively.

  • Working with terabytes of seismic data for training deep machine learning models.
  • Have experience in dealing with problems subjective in nature and having imbalanced classes.
  • Presented my research work on Fault and Seafloor detection using deep learning in TECHDAY conference (internal) at Schlumberger Pune
  • Filed a provisional patent on SEAFLOOR DELINEATION USING MACHINE LEARNING. U.S. Provisional Patent Application no.: 62/914,608.

July 2018 - June 2020

  • Schlumberger

  • Software Engineer

  • |Data Ingestion Team

Built various microservices in python and nodeJs to ingest user’s Oil Field data in cloud environment - DELFI portal.

  • Worked on technologies like grpc, microservice architecture etc.
  • Developed microservices to parse and store gigabytes of data within few minutes.
  • Have experience in building and deploying microservices in google app engine
July 2017 - June 2018


  • Data Science Intern

  • |8hoarding

Worked for an advertisement management startup. Internship was focused on data extraction and data cleaning for media hoarding booking product named “8hoarding”.

  • Built web scrapers to extract hoarding information from different websites.
  • Developed complex scrapers to handle AJAX pagination on websites.
  • Used SFrame python module for data cleaning.

Letter of Acknowledgement

15th August 2016 - 30th September 2016


Fault geobody detection

  • Deep Learning Application
  • |Schlumberger

Global model for fault geobody detection using deep supervised learning

  • Built a supervised 2D deep CNN to detect fault geobody in seismic signals.
  • Trained on multiple surveys with different distributions to achieve a global model.
  • Used Unet as the model architecture.

Seismic Noise removal using V-Net

Built a supervised 3D CNN model to enhance fault detection by removing noise (small faults, false positives and non-laterally pervasive faults) from global fault model predictions.
December 2018 - Present

Salt body detection using network-based deep transfer learning

  • Deep Learning Application
  • |Schlumberger
  • Built a model to detect the Top of Salt geobody using very few training data.
  • Used Tiramisu architecture for semantic segmentation.
  • Performed transfer learning by training only the last few layers of the decoder of a model pre-trained on seismic fault data and froze the remaining layers of the model.
July 2018 – November 2018

Sea-Floor detection using weakly supervised deep learning

  • Deep Learning Research Application
  • |Schlumberger
  • Designed and developed a unique process for accurately detecting seafloor.
  • Built a global model using weakly supervised learning to predict seafloor and applied a series of smart post processors on top of the model’s prediction to increase the overall accuracy.
  • Filed provisional patent. U.S. patent no.: 62/914,608
July 2019 – September 2019

Real Time Mouse Cursor Control using Machine Learning

  • Capstone - Machine Learning Research Project
  • |VIT
  • Developed a novel algorithm for controlling mouse cursor in real time using webcam.
  • The algorithm is a two step process - skin detection followed by gesture classification.
  • Solution is Rotation and Scale invariant.
  • Designed novel features for gesture classification using image processing techniques.
  • Defined custom hand gestures to imitate major mouse functionalities like cursor movement, left click, right click, drag and drop etc.
  • Developed a desktop app in python including a control panel to adjust cursor movement sensitivity.
January 2017 – April 2017

Client Library for Logstore

  • Software Engineering
  • |Schlumberger

Logstore is a distributed logs storage system used to store well logs of an Oil Field. I worked on building client library for logtore, and integrated logstore with different microservices developed by my team using the client library.

March 2018 – June 2018

DLIS parser

  • Software Engineering
  • |Schlumberger

A DLIS file is a log file created by sensors that monitor petroleum wells. I worked on creating a DLIS parser for extracting log headers and data from a DLIS file and store the information extracted in the logstore.

October 2017 – January 2018

Clustering using Brainstorm Optimization

  • Machine Learning
  • |Coursework

Applied Brainstorm optimization, a swarm intelligence technique, to find optimal cluster clusters in protein dataset. Used Dunn index and DB index for internal cluster validity indices.

March 2016 – May 2016

Smart Gui for linux terminal

  • Operating Systems
  • |Coursework

Developed a smart terminal GUI for Debian Linux Kernel 3.14-kali. Created new commands using linux system calls. Stored the user’s history to filter top five frequently used commands and displayed it on the GUI.

Code: View Code
February 2015 – April 2015

Text search using Trie

  • Data Structure & Algorithms
  • |Coursework

Developed a cross-platform desktop app in C++ and Qt for searching text in a given paragraph using Trie data structure.

Code: View Code
August 2014 - October 2014

KUcart Ecommerce

  • Web Development
  • |Coursework

A simple E-commerce website.

Code: View Code
March 2015 – April 2015


  • Filed a provisional patent with co-authors on SEAFLOOR DELINEATION USING MACHINE LEARNING while I was working on seafloor detection project in Schlumberger. Serial number of the United States Provisional Patent Application: 62/914,608.


  • Presented a paper titled “Hand Gesture Recognition and FingerTip Detection using Neural Networks” in World Summit On Advances in Science, Engineering and Technology conference at the University of Cambridge, U.K. in 2018


  • Presented my research work on Fault and Seafloor detection using deep learning in TECHDAY conference (internal) at Schlumberger Pune



Vellore Institute of Technology

Bachelor of Technology in Computer Science and Engineering

Cumulative GPA: 8.92/10

  • Data Structures and Algorithms
  • Computer vision
  • Reinforcement learning
  • Self-driving cars
  • Data Science
    • Agent based intelligent systems
    • Soft computing
    • Computer vision
    • Data warehousing and data mining
  • Mathematics
    • Multivariable calculus and differential equations
    • Differential and difference equations
    • Discrete mathematical equations
    • Linear algebra
    • Numerical Analysis
    • Graph theory and its applications
    • Applied probability, statistics and reliability
  • Data Structures and Algorithms
    • Data Structures and Algorithms
    • Algorithm design and analysis
CAPSTONE PROJECT DEMO : https://www.youtube.com/watch?v=gcHJ179Yop4
July 2013 - August 2017

Somerville School

Science Student

Class XII CBSE - AISSCE: 85.2% (Maths 90%, Physics 91%, Computer Science 90%)

Class X CBSE - AISSE: 9.0/10 (Maths:10, Science: 10, Social Science:10)

April 2006 - February 2012


  • Coursera

Deep Learning specialization by deeplearning.ai
  • Neural Networks and Deep Learning see credentials
  • Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization see credentials
  • Structuring Machine Learning Projects see credentials
  • Convolutional Neural Networks In progress
TensorFlow in Practice specialization by deeplearning.ai
  • Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning see credentials
  • Convolutional Neural Networks in TensorFlow In progress
Self-Driving Cars Specialization by University of Toronto
  • Introduction to Self-Driving Cars In progress
  • DataCamp
  • edX