Welcome!

I am currently working as Principal Researcher (Machine Learning) in Bell Labs, Cambridge (UK). Previously I was Principal Researcher (Machine Learning) in Advanced Research Lab, Nokia, Cambridge (UK). I also worked as a Reseach Fellow in Institute for Artificial Intelligence & Biological Systems, University of Leeds. I finished my PhD in March, 2012 in University of Leeds. I was working under Prof. Tony Cohn and Prof. David Hogg in the areas of Machine Learning and Cognitive Vision and was funded by the European Commission's Co-Friend project and DARPA's Mind's Eye project. I also worked in the European Commission's RACE and STRANDS projects.

Employment

2018
Present

Bell Labs

Principal Researcher, Machine Learning (Cambridge, UK)

Principal Researcher: Algorithms, Analytics & Augmented Intelligence Research Lab, Bell Labs, Cambridge (UK).
2015
2017

Advanced Research Lab, Nokia

Principal Researcher, Machine Learning (Cambridge, UK)

I worked on Deep Learning algorithms, depth maps from 360 video content and dialogue systems.
2012
2015

University of Leeds, UK

Research Fellow

I worked in the European Commission's RACE and STRANDS projects where my contribution was to develop novel machine learning algorithms to learn and detect activities in videos.
2006
2008

D.E.Shaw & Co, India

Member - Information Technology

Worked in front office group responsible for building real-time financial data-feed infrastructure, high-performance middleware, interactive trading systems, portifolio management and work flow tools, and quantitative analysis tools.

Education

2008
2012

University of Leeds, UK

PhD (Machine Learning)

I finished my PhD in March, 2012 in University of Leeds under the supervision of Prof. Tony Cohn and Prof. David Hogg in the areas of Machine Learning and Cognitive Vision. The thesis title is Learning Relational Event Models from Videos and was funded by the European Commission's Co-Friend project and DARPA's Mind's Eye project (partner: SRI International).
2004
2006

University of Hyderabad, India

Master of Technology (Artificial Intelligence)

My thesis was N-gram analysis for Computer Virus Detection (Department of CIS' Best Thesis Award and Gold Medal sponsored by TCS, 2006) which I completed under the guidance of Prof. Arun Pujari.
2000
2004

J.N.T. University, India

Bachelor of Technology (Computer Science and Engineering)

My final year project was titled Congestion Control in ATM Networks Using Neural Networks.

Publications

Journals

1) Krishna S.R. Dubba, Anthony G. Cohn, David C. Hogg, Mehul Bhatt, Frank Dylla: Learning Relational Event Models from Video, In Journal of Aritificial Intelligence Research, 2015.

2) Krishna S.R. Dubba, Arun K. Pujari: N-gram Analysis for Computer Virus Detection, Journal in Computer Virology, Vol-2, Number-3, Dec-2006, Springer-France.

Conference Proceedings

1) Joachim Hertzberg, Jianwei Zhang, Liwei Zhang, Sebastian Rockel, Bernd Neumann, Jos Lehmann, Krishna S.R. Dubba et.al. The RACE Project. In KI-Künstliche Intelligenz, 2014.

2) Krishna S.R. Dubba; Miguel R. de Oliveira; Gi Hyun Lim; Hamidreza Kasaei; Luis Seabra Lopes; Ana Tome and Anthony G. Cohn: Grounding Language in Perception for Scene Conceptualization in Autonomous Robots. In AAAI Spring Symposium Series, 2014.

3) Rockel, S.; Neumann, B.; Zhang, J.; Dubba, K.; Cohn, A.; Konecny, S.; Mansouri, M.; Pecora, F.; Saffiotti, A.; Gunther, M.; Stock, S.; Hertzberg, J.; Tome, A.; Pinho, A.; Seabra Lopes, L.; von Riegen, S.; and Hotz, L: An Ontology-based Multi-Level Robot Architecture for Learning from Experiences. In AAAI Spring Symposium Series, 2013.

4) Krishna S.R. Dubba, Mehul Bhatt, Frank Dylla, Anthony G. Cohn, David C. Hogg: Interleaved Inductive-Abductive Reasoning for Learning Event-Based Activity Models, Proc. of ILP, 2011. Berkshire, UK.

5) Krishna S.R. Dubba, Anthony G. Cohn, David C. Hogg: Event Model Learning from Complex Videos using ILP, European Conference on Artificial Intelligence - 2010, Portugal.

6) Krishna S.R. Dubba, Subrat K. Dash, Arun K. Pujari: New Malicious Code Detection Using Variable Length n-grams, LNCS-4332/2006, Springer-Berlin / Heidelberg.

Book Chapters

1) Subrat K. Dash, Krishna S.R. Dubba, Arun K. Pujari: New Malicious Code Detection Using Variable Length n-grams, Algorithms, Architectures and Information Systems Security, Statistical Science and Interdisciplinary Research - VOL3, World Scientific, 2008.

PhD Thesis

Learning Relational Event Models from Videos, 2012.

Research

My work in general falls under the areas of Machine Learning (in particular Statistical Relational Learning, Deep Learning), Cognitive Vision, Knowledge Representation, Graph Analysis and Spatio-Temporal Reasoning. I worked in European Commission's RACE, STRANDS and Co-Friend projects. I also worked in DARPA's Mind's Eye project where we developed systems that learn relational event models from videos.

Grounding Language in Perception for Scene Conceptualization in Autonomous Robots

In order to behave autonomously, it is desirable for robots to have the ability to use human supervision and learn from different input sources (perception, gestures, verbal and textual descriptions etc). In this work, we present a cognitive architecture and learning framework for robot learning through natural human supervision and using multiple input sources by grounding language in perception.

An Ontology-based Multi-Level Robot Architecture for Learning from Experiences

One way to improve the robustness and flexibility of robot performance is to let the robot learn from its experiences. In this work, we propose an architecture and knowledge-representation framework for a service robot being developed in the EU project RACE. As a unique innovative feature, the framework combines memory records of low-level robot activities with ontology-based high-level semantic descriptions.

Learning Relational Event Models from Video

In this paper, we present a novel framework REMIND (Relational Event Model INDuction) for supervised relational learning of event models from large video datasets. The learned models can be used for recognizing events from previously unseen videos. The experimental results on several hours of video data from two challenging real world domains (an airport domain and a physical action verbs domain) suggest that the techniques are suitable to real world scenarios.

Event model learning from complex videos

In this paper, we have proposed and successfully applied a novel supervised framework for learning relational event models from a huge, complex and noisy video dataset. The experimental results on video data from an airport apron where events such as Loading, Unloading, Jet-Bridge Parking etc. are learned suggests that the techniques are suitable to real world scenarios.

N-gram analysis for computer virus detection

Motivated by the success of Machine Learning techniques in intrusion detection systems, recent research in detecting malicious executables is directed towards devising efficient non-signature based computer virus detection techniques that can profile the program characteristics from a set of training examples. In this paper, we describe a new feature selection measure, class-wise document frequency of byte n-grams. We empirically demonstrate that the proposed method is a better method for feature selection. For detection, we combine several classifiers using Dempster Shafer Theory for better classification accuracy instead of using a single classifier. Our experimental results show that such a scheme detects virus program far more efficiently than the earlier known methods.

Blog: Achilles and Tortoise

Also see my non-technical blog Randomish and my full technical blog Achilles and Tortoise.

What it is like to be a bat?

  By Krishna Dubba         computing, philosophy        23 comments

Every now and then I get into conversations (even arguments) with someone and sometimes it gets very hot. For example recently it was on Kashmir and this guy was from US. His arguments were entirely opposed to the views I had and I didn't understand how he can have such views while it looks pretty obvious that my views seem more logical. He told he felt the same. Well somehow we ended our conversation in a very peaceful manner, but the whole thing haunted me for a while. How can people have such diametrically opposite views and still think they are right and their views are logical? After that I came across this seminal paper in an entirely different field: "What is it like to be a bat?" by American philosopher, Thomas Nagel. This paper is a master piece and it says why it is difficult (or rather impossible) to feel or see others perspective because every individual's consciousness is non-intrusive. In fact it raises some profound yet simple questions by asking similar questions like what is it like to hate coffee, what is it like to like chocolate etc. These are impossible to answer unless you experience it. How can you answer the question what is it like to hate coffee when you actually love coffee?

This applies to my conversations with others. It is impossible to see the opposite person's views because "I am not him". Each person is very very unique, they are product of their experiences, memories, emotions etc etc and they all have profound effect on his views on different topics which I may never understand. I think this also applies to religious beliefs, tastes, personal preferences etc.

In fact its fun to ask these questions and some new questions which might be unique to you. Can you answer this: What is it like to be Krishna Dubba?

Why this title?

  By Krishna Dubba         general, philosophy, blog        23 comments

Though the title appears a bit odd to some people, it is not at all surprising to those who know Lewis Carroll (who do you think wrote 'Alice in Wonderland'?). He used the two characters to discuss very subtle philosophical issues in a very humourous way. These characters also got more popular as they appeared in Hofstadter's 'Godel, Esher and Bach' book. Most of the postings in this blog will be broadly in Computing, Artificial Intelligence, Cognitive Science, Machine Learning, Philosophy etc etc.

Contacts