My research expertise is in the applications of machine learning and deep learning with applications to computer vision and natural language processing. I have worked on a variety of applied research projects and specialize in the introduction of machine learning and deep learning-based solutions to traditional industry problems. I have also technical lead research projects into products and my passion lies in solving challenging research problems and taking those solutions into products and improving business. I am a complete hands-on guy with a "roll up the sleeves and get the job done" attitude all the time!

Work Experience

Senior Research Scientist @ IBM Research AI

NOV 2015 - Current

0. Data Quality for AI: I am currently the technical lead in a new strategic area of "Data Quality for AI". Stressing on the importance of data in the AI lifecycle, the aim of this project is to solve the quality problems in the world of data and prepare the data to be AI-ready. We are building a system and toolkit called "Data Readiness Toolkit for AI"

1. Neural Network Modeller: I served as the technical lead for this project: Problem formulation from scratch -> Filing Disclosures -> Writing Research Papers (NeurIPS 2019, AAAI 2018, ICSE NIER 2017) -> Building Prototyping -> Presenting to clients, workshops, business partners -> Writing product level code -> Leading the team into product integration -> Product Release @ IBM Think Event 2018! This system helps in the extreme rapid prototyping of deep learning models and the implementation of state of art papers.

2. Machine Learning for Creativity: Served as the Global Technical co-lead (2018) for IBM Research AI for the research growth strategy "Machine Learning for Creativity - Building Creative Assistants". Got the prestigious IBM Research recognition award for serving as a global technical co-lead in the Global Technical Outreach AI Leadership program, 2018. We worked on a system "PersuAIDE" to create/generate more creative and persuading taglines and images (published in WWW 2018, KDD workshop 2017).

3. iSight: Lead researcher for project iSight, which aims in creating a cognitive automated system to extract the error context for SAP system screenshots and to supply a structured resolution procedure, mined from previous instances of data.

Teaching Experience

Visiting Faculty@ IIIT Bangalore, India

Jan 2019 - May 2019
Grad Level course on Visual Recognition (Course Information)

Teaching a graduate level course on “Visual Recognition“ at IIIT Bangalore between Jan - May 2019. This course is at the intersection of Deep Learning and Computer Vision.

Visiting Faculty@ ISME Bangalore, India

Oct 2019 - Dec 2019
Foundations of Machine Learning (Course Information)

Teaching a introductory course on “Machine Learning“ at ISM Bangalore between Oct - Dec 2019. This course is for MBA students who does not have a CS/Math background with heavy emphasis on taking ML to business.


Lane Department, West Virginia University (Visiting Research Scholar )

June 2014 - October 2014
Guidance of Prof. Afzel Noore

Eye gaze analysis for latent fingerprint matching: Analyzing the eye gaze patterns of experts while matching latent prints, provides insights of the process and heuristics used by the experts. The gained insights can be used to design better algorithms for automated latent fingerprint matching.

HongKong Polytechnic University (Visiting Research Scholar)

June 2011 - August 2011
Guidance of Dr. Ajay Kumar

Feature level fusion of fingerprints: Propose a novel generic framework to fuse information from multiple data sources at feature level, instead of at match score level or decision level. The framework was applied in fingerprints to use multiple fingers of a person as a more confident biometric than using a single finger.


Doctorate of Philosophy (CS)@ IIIT Delhi

July 2010 - Aug 2017
Guidance of Dr. Mayank Vatsa and Dr. Richa Singh

Thesis title: "Learning Representations of Matching Fingerprint Variants" (More info)

Undergraduate studies (CS) @ Coimbatore Institute of Technology

August 2006 - April 2010

Undergraduate thesis title: "Multi-resolution image query using Haar transformation and image tagging"



S. Agrawal, A. Sankaran, A. Laha, S. Ahmed CG, D. Shrivastava, K. Sankaranarayanan, What is Deemed Computationally Creative?, IBM Journal On Research and Development, Special Issue on Computational Creativity, vol. 63, no. 1, pp. 3:1-3:12, Jan.-Feb. 2019. Impact Factor: 0.962

A. Sankaran, A. Majumdar, M. Vatsa, and R. Singh, Group Sparse Autoencoder, Image and Vision Computing, Special Issue on Regularization Techniques for High-Dimensional Data Analysis, Elsevier, vol. 60, pp. 64-74, 2017. Impact Factor: 2.671

A. Sankaran, A. Jain, T. Vashisth, M. Vatsa, and R. Singh, Adaptive latent fingerprint segmentation using feature selection and random decision forest classification, Information Fusion, Elsevier, vol. 34, pp. 1-15, 2017. Impact Factor: 5.667

A. Sankaran, G. Goswami, M. Vatsa, R. Singh, and A. Majumdar, Class Sparsity Signature based Restricted Boltzmann Machines, Pattern Recognition, Special Issue on Deep Image Video, Elsevier, vol. 61, pp. 674-685, 2017. Impact Factor: 4.582

A. Sankaran, M. Vatsa, R. Singh, Multisensor Optical and Latent Fingerprint Database, IEEE Access, vol. 3, pp. 653 - 665, 2015. Impact Factor: 3.244

A. Sankaran, M. Vatsa, R. Singh, Latent Fingerprint Matching: A Survey, IEEE Access, vol. 2, pp. 982-1004, 2014. (Appeared as one of the top-10 highly viewed publication of 2014). Impact Factor: 3.244

Book Chapters

A. Sankaran, A. Malhotra, M. Vatsa, and R. Singh, Learning Representations for Uncontrolled Fingerprint Recognition, Deep Learning in Biometrics, CRC Press, 2018.

A. Malhotra, A. Sankaran, A. Mittal, M. Vatsa, and R. Singh, Fingerphoto Authentication using Smartphone Camera captured under Varying Environmental Conditions, Human Recognition in Outdoor Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics, Elsevier, 2016. Editors: Maria De Marsico, Michele Nappi and Hugo Proenca

Peer-reviewed Conferences

A. Prabhu, R. Dasgupta, A. Sankaran, S. Tamilselvam, S. Mani. “You might also like this model”: Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets, 33rd Conference on Neural Information Processing Systems (NeurIPS), New in ML 2019.

R. Sinha, A. Sankaran, M. Vatsa, and R. Singh. AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework, 33rd Conference on Neural Information Processing Systems (NeurIPS), MLSys: Workshop on Systems for ML 2019.

S. Tamilselvam, N. Panwar, S. Khare, R. Aralikatte, A. Sankaran, S. Mani, A Visual Programming Paradigm for Abstract Deep Learning Model Development, IndiaHCI, HCI in the age of Machine Intelligence, 2019.

S. Mani, A. Sankaran, R. Aralikatte , DeepTriage: Exploring the Effectiveness of Deep Learning for Bug Triaging, ACM India Joint International Conference on Data Science and Management of Data (CoDS-COMAD), 2019.

N. Gantayat, G. Sridhara, A. Sankaran, S. Dechu, S. Mani, G. Dasgupta, Towards Creating Business Process Models from Images, In International Conference on Service-Oriented Computing (ICSOC), 2018.

A. Sankaran, M. Vatsa, and R. Singh. Intuition Learning, Joint IJCAI/ECAI/AAMAS/ICML Workshop on Domain Adaptation for Visual Understanding (DAVU) 2018.

S. Suri, A. Sankaran, M. Vatsa, and R. Singh. On Matching Faces with Alterations due to Plastic Surgery and Disguise, International Conference on Biometrics: Theory, Applications and Systems (BTAS) , 2018.

R. Aralikatte, N. Gantayat, N. Panwar, A. Sankaran, S. Mani, Sanskrit Sandhi Splitting using seq2(seq)2, In Empirical Methods in Natural Language Processing (EMNLP), 2018.

V. Munigala, A. Mishra, S. G. Tamilselvam, S. Khare, R. Dasgupta, and A. Sankaran, PersuaAIDE ! An Adaptive Persuasive Text Generation System for Fashion Domain, Cognitive Computing Track, TheWebConf (WWW), 2018

A. Sethi, A. Sankaran, N. Panwar, S. Khare, and S. Mani, DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers, Association for the Advancement of Artificial Intelligence (AAAI), 2018

S. Mani, N. Gantayat, R> Aralikatte, M. Gupta, S. Dechu, A. Sankaran, S. Khare, B. Mitchell, H. Subramanian, and H> Venkatarangan, Hi, How can I help you?: Automating enterprise IT support help desks, Innovative Applications of Artificial Intelligence (IAAI), 2018.

A. Sankaran, N. Panwar, S. Khare, S. Mani, A. Sethi, R. Aralikatte, and N. Gantayat, Democratization of Deep Learning using DARVIZ, AAAI - Demo Track, 2018.

S. Mani, N. Gantayat, R. Aralikatte, M. Gupta, S. Dechu, A. Sankaran, S. Khare, B. Mitchell, H. Subramanian, and H. Venkatarangan, Agent Assist: Automating enterprise IT support help desks, AAAI - Demo Track, 2018.

A. Sankaran, R. Aralikatte, S. Mani, S. Khare, N. Panwar, and N. Gantayat. DARVIZ: deep abstract representation, visualization, and verification of deep learning models. International Conference on Software Engineering: New Ideas and Emerging Results Track, pp. 47-50. IEEE Press, 2017.

A. Taneja, A> Tayal, A. Malhotra, A. Sankaran, M. Vatsa, and R. Singh, Fingerphoto Spoofing in Mobile Devices: A Preliminary Study, International Conference on Biometrics: Theory, Applications and Systems, pp. 1-7, 2016.

A. Sankaran, A. Malhotra, A. Mittal, M. Vatsa, and R. Singh. On smartphone camera based fingerphoto authentication, International Conference on Biometrics Theory, Applications and Systems pp. 1-7, 2015

A. Sankaran, A. Agarwal, R. Keshari, S. Ghosh, A. Sharma, M. Vatsa, and R. Singh, Latent Fingerprint from Multiple Surfaces: Database and Quality Analysis, International Conference on Biometrics: Theory, Applications and Systems, pp. 1-6, 2015.

A. Sankaran, P. Pandey, M. Vatsa, R. Singh, On Latent Fingerprint Minutiae Extraction using Stacked Denoising Sparse AutoEncoders, International Joint Conference on Biometrics, 2014, pp. 1-7, (Best Poster Award).

A. Sankaran, M. Vatsa, R. Singh, Automated Clarity and Quality Assessment for Latent Fingerprints: A Preliminary Study, International Conference on Biometrics: Theory, Applications and Systems, pp. 1-6, 2013 (Best Poster Award).

A. Sankaran, M. Vatsa, R. Singh, Hierarchical Fusion for Matching Simultaneous Latent Fingerprint, International Conference on Biometrics: Theory, Applications and Systems, pp. 377-382, 2012.

A. Sankaran, T.I. Dhamecha, M. Vatsa, R. Singh, On Matching Latent to Latent Fingerprints, International Joint Conference on Biometrics, pp. 1-6, 2011.

Technical Reports

S. Mani, A. Sankaran, S. Tamilselvam, A. Sethi, Coverage Testing of Deep Learning Models using Dataset Characterization, arXiv preprint arXiv:1911.07309, 2019.

T. Narendra, A. Sankaran, D. Vijaykeerthy, S. Mani, Explaining Deep Learning Models using Causal Inference, arXiv preprint arXiv:1811.04376, 2018.

N. Panwar, S. Khare, N. Gantayat, R. Aralikatte, S. Mani, and A. Sankaran, mAnI: Movie Amalgamation using Neural Imitation, arXiv preprint arXiv:1708.04923, 2017

V. Munigala, S. Tamilselvam, and A. Sankaran, "Let me convince you to buy my product...": A Case Study of an Automated Persuasive System for Fashion Products, arXiv preprint arXiv:1709.08366, 2017