­­Amara Dinesh Kumar



Bangalore, Karnataka INDIA

Experienced AI Researcher with a demonstrated history of publishing research papers and developing products in the Artificial intelligence industry. Skilled in Python, Data science libraries, TensorFlow, Keras, ROS, Sklearn. Strong researcher and inventor with a Master's degree focused in Automotive Electronics from Amrita Vishwa Vidyapeetham, Coimbatore. Machine learning Engineer at the Tata Consultancy services with 5 years experience. Research areas are Data mining, Machine learning, Data Science, Deep learning, Reinforcement Learning, Robotics.

I strongly believe in open science and reproducible research and actively publish code on my Github profile.

I am Available on the job market!!

Conference Papers

1. Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks

Amara Dinesh Kumar

[ paper ] [ code ]

2. A Brief Survey on Autonomous Vehicle Possible Attacks,Exploits and Vulnerabilities

Amara Dinesh Kumar,Vinayakumar R, Soman KP


3. “Deeptracknet: Camera Based End To End Deep Learning Framework For Real Time Detection, Localization And Tracking For Autonomous Vehicles”. Lecture Notes in Control and Information Sciences. Springer 2019.

Amara Dinesh Kumar, R.Karthika, Soman Kp.

4. DeepImageSpam: Deep Learning based Image Spam Detection

Amara Dinesh Kumar,Vinayakumar R, Soman KP

[paper] [code]

Book Chapters

1. Vinayakumar, R., K. P. Soman, Prabaharan Poornachandran, Vysakh S. Mohan, and Amara Dinesh Kumar. "ScaleNet: Scalable and Hybrid Framework for Cyber Threat Situational Awareness Based on DNS, URL, and Email Data Analysis." Journal of Cyber Security and Mobility 8, no. 2 (2019): 189-240.

2. Using Various Deep Neural Networks to Detect Domain Generation Algorithm Attacks, Deep Learning Applications for Cyber Security, Springer publications [under print]

Amara Dinesh Kumar, Harish Thodupunoori, Vinayakumar R, Soman KP, Prabaharan Poornachandran, Mamoun Alazab and Sitalakshmi Venkatraman

3. “Stereo Camera and LIDAR Sensor Fusion based Collision Warning System for Autonomous Vehicles”. Advance in Computational Intelligence Techniques. Springer 2019 [under print].

Amara Dinesh Kumar, R.Karthika, Soman Kp.


July 2017 - 2019, in Automotive Electronics, Amrita Vishwa Vidyapeetham, Coimbatore

CGPA: 8.6

[ Deep Learning- A+, Reinforcement learning- A+, Multi Sensor Data fusion- A+ ]

June 2010 - June 2014, in Electronics and Communication , Jawaharlal Nehru Technological University, Hyderabad

CGPA: 7.84

Work Experience

Working as Machine learning Engineer from 5 years in Tata Consultancy Services


1. Developed a traffic sign recognition system using deep learning and deployed in an embedded platform for a real time application for a client.

2. Developed an object recognition and tracking system for monitoring purpose from the video stream of ip cameras.

3. Developed a forward collision system for an automotive client by combining the deep learning, Bayesian learning techniques and performed multi sensor data fusion.

4. Developed a data driven network traffic monitoring system using deep learning architecture.

5. Developed a Machine learning based Log Analysis Automation Framework for Test Execution and Result parsing of BT/SV/CP/Performance Test cases.


§ September 2018 shortlisted for quarter finals (from 10,000 teams) IICDC 2018 Hackathon by Indian Government

§ July 2018 Secured 2nd place in DMD 2018 shared task in Cybersecurity domain. More details available at DMD2018

§ July 2018 Registered for IECSIL 2018 Shared Task at IECSIL 2018.

§ July 2018 Registered for Multi-target speaker detection and identification Challenge Evaluation Shared Task at MCE 2018.

§ July 2018 Registered for NIPS 2018: AI for Prosthetics Challenge at AI for Prosthetics Challenge 2018.

§ Participated in Genisis Blockchain Hackaton 2019

§ Participated in Perlin Hackaton 2019

Teaching and Mentoring Experience

· Mentored 12 Teams (from the Upgrad data science PG diploma course) for Reinforcement Learning project.

· Tutored 10 Teams (from the Upgrad data science PG diploma course) for Data science Capstone projects.

· Took sessions on Machine learning, Deep Learning and Computer Vision for Masters Students.

Master's Coursework

  • MA607 - Linear Algebra
  • CN613 - Computational optimization theory - linear and non-linear methods
  • CY603 - Pattern Recognition and Machine Learning
  • CN703 - Computational Methods for Cryptography
  • CN733 - Neural network & Deep learning
  • CY800 - Research Methodology
  • Deep Learning
  • Reinforcement Learning
  • Digital Control System
  • Multi Sensor Data Fusion
  • Probability Graphical Models
  • Sensing For Autonomous Vehicles
  • Electric Vehicle Architecture
  • Power Electronics and Converters
  • Real Time Operating Systems
  • Automotive Embedded Systems
  • Computer Vision and Image Processing
  • Cryptography


Languages : C, Embedded C, C++, Java, Scala, Python, Basics of R, Basics of Julia

Scripting Languages : Html, CSS, JavaScript, Bash, Awk, Sed ,Perl , XML

Embedded System Softwares : Matlab, Simulink, CarSim, Canoe, KEIL, Proteus, Arduino Studio

Frameworks : Scikit-learn, LibSVM, TensorFlow, Theano, Keras, , OpenAI Gym, PyTorch, Basics of Caffe, DeepChem, DragoNN, Weka

Database : MySQL, Introduction to Oracle

Documentation Tools : LibreOffice, Microsoft Office, and Latex

Participated the following events in the department of Computational Engineering and Networking, Amrita Vishwa Vidyapeetham

Shared task conducted by cyber security lab CEN

Shared task on Detecting Malicious Domain names (DMD 2018)

Summer course conducted by CEN

Summer Course on AI & Data Science

Workshops conducted by CEN

1. AISec 2017 Workshop: Modern Artificial Intelligence (AI) and Natural Language Processing (NLP) Techniques for Cyber Security

2. DeepSci 2017 Workshop: Deep Learning for Healthcare and Financial Data Analytics

3. Blockchain 2017 Workshop: Blockchain and Machine Learning

4. A Refresher experiential course on linear algebra and Optimization for Most Modern Signal processing and pattern classification

5. DeepChem 2017: Deep Learning & NLP for Computational Chemistry, Biology & Nano-materials

6. Data -Driven Modelling

7. Reinforcement Learning (Classical and Deep)

8. Modern Signal processing for AI and Data Science

9. DMD and Optimization for AI, Data Science and Control Applications