MY FRIEND AND PARTNER IN CRIME – FROM BACK THEN IN THE HOOD OF HALL3 IIT K

Arunava's Photograph

Associate Professor Department of Computer & Information Science & Engineering

3990f-olga2bshulman2blednichenkop2bajay2bmishra2bcasablanca2b-2bnumbers2band2balphabets2b-2bgeography2bmathsm2br2btheta2bphi2b-2bhere2bis2ba2band2b62bcaleld2ba2b62b-2bparrot

My primary research interest lies in the field of Computational Neuroscience. (A corpus of simulated spike train data generated with NSF support can be found here). Below is a high level description of my research objectives.

My current and old PhD students are:

Current Students:

  • Inchul Choi,
  • <a href=”mailto:gkaya,
  • Sk Minhazul Islam,
  • <a href=”mailto:tsk,
  • Michael Kummer,
  • <a href=”mailto:fardad,

Students that have graduated:

  • Subhajit Sengupta, graduated with a Ph.D in 2013.
  • <a href=”mailto:ksg (co-advised with Prof. Anand Rangarajan) graduated with a Ph.D in 2011.
  • Ajit V. Rajwade (co-advised with Prof. Anand Rangarajan) graduated with a Ph.D in 2010.
  • <a href=”mailto:nfisher graduated with a Ph.D in 2010.
  • Venkatakrishnan Ramaswamy graduated with a Ph.D in 2011.
  • <a href=”mailto:ndv graduated with a Ph.D in 2009.
  • Ritwik Kumar (coadvised with Prof. Baba Vemuri) graduated with a Ph.D in 2009.
  • <a href=”mailto:snsk (coadvised with Prof. Baba Vemuri) graduated with a Ph.D in 2009.
  • Ami Greenberg, graduated with a Ph.D in 2008.
  • <a href=”mailto:hmeng graduated with a Ph.D in 2006.

 

My primary research interest lies in the field of Computational Neuroscience. (A corpus of simulated spike train data generated with NSF support can be found here). Below is a high level description of my research objectives.My current and old PhD students are:

Current Students:

Students that have graduated:


Perspective

The abstract computational device that underlies a digital computer is a Finite State Automaton (or a Turing Machine if one assumes infinitely expandable memory). Our familiarity with the artifact, the digital computer in all its forms, is ultimately founded on this knowledge.

Interest in the nature of the human mind can be traced to the beginning of recorded history. There is now general consensus that the brain is implicated in cognition and behavior. If we are to decipher the nature of the human mind (and this includes all perception: visual, auditory, olfactory, tactile, or proprioceptive, higher order faculties such as language comprehension, and the most abstract of qualities such as attention), we must first consider the corresponding problem with regard to the brain: What abstract device underlies this physical system.

Research Objective

My principal research objective has been to determine the nature of the abstract computational device that recurrent (and feedforward) systems of spiking neurons in the brain are a physical embodiment of. My approach has been to address the issue in stages, namely, to first determine the salient dynamical characteristics of such systems, and subsequently, to exploit this knowledge to arrive at a principled resolution of the matter.

I have been pursuing the following questions with regard to the dynamics of systems of spiking neurons in the brain.

  • Are there coherent spatio-temporal structures in the dynamics of neuronal systems that can denote symbols.My usage of the term “symbol” conforms with the limited notion of a symbol as used in Computer Science—discrete states that mark a computational process regardless of representational content, if any, and not the notion of a symbol in the greater sense of the word—the physical embodiment of a semantic unit, as used in the Cognitive Sciences. The question therefore does not presuppose a position on the contentious issue of Representationalism.
  • If such structures exist, what restrictions do the dynamics of the system at the physical level impose on the dynamics of the system at the corresponding abstracted symbolic level.

In order to address these questions, I have formulated an abstract dynamical system that models recurrent systems of spiking biological neurons (Banerjee, 2001a). The abstract system is based on a limited set of realistic assumptions and in consequence accommodates a wide range of neuronal models. I have evaluated the viability of the system by conducting extensive simulation experiments with the system set to model a typical column in the cortex. The characteristic behavior of the system is akin to that observed in neurophysiological experiments.

A thorough understanding of the dynamical behavior of the system can be achieved only by way of a comprehensive formal analysis of its dynamics. My approach has been to address the problem in stages. I began by analyzing the dynamics of the system under stationary conditions with either no input or input given by a stationary process. My efforts culminated in, among other results, a formal demonstration of the fact that under normal operational conditions, the dynamics of a typical neocortical column is governed by attractors that are not only almost surely (with probability 1) chaotic but are also potentially anisotropic (Banerjee, 2001b, 2003).

The general case must, however, address a problem of far greater complexity—the dynamics of systems with unconstrained inputs. This requires a mathematical framework that allows for the formal analysis of the transient dynamics of non-autonomous systems. A crucial question in this context is whether there is a formal counterpart to the concept of an attractor, an issue I am currently investigating.

 

 

Publications


Journal Articles:

  1. Martínez C.A., Khare K., Banerjee A., Elzo M. A. (2017) Joint genome-wide prediction in several populations accounting for randomness of genotypes: A hierarchical Bayes approach. II: Multivariate spike and slab priors for marker effects and derivation of approximate Bayes and fractional Bayes factors for the complete family of models . Journal of Theoretical Biology , 417, pp. 131-141.
  2. Martínez C.A., Khare K., Banerjee A., Elzo M. A. (2017) Joint genome-wide prediction in several populations accounting for randomness of genotypes: A hierarchical Bayes approach. I: Multivariate Gaussian priors for marker effects and derivation of the joint probability mass function of genotypes . Journal of Theoretical Biology , 417, pp. 8-19.
  3. Banerjee A. (2016) Learning Precise Spike Train to Spike Train Transformations in Multilayer Feedforward Neuronal Networks. Neural Computation, 28(5), pp. 826-848.
  4. Pourreza A., Lee W.S., Etxeberria E., Banerjee A. (2015) An evaluation of a vision-based sensor performance in Huanglongbing disease identification. Biosystems Engineering, 130, pp. 13-22.
  5. Ramaswamy V., Banerjee A. (2014) Connectomic Constraints on Computation in Feedforward Networks of Spiking Neurons. Journal of Computational Neuroscience, 37(2), pp. 209-228. [Supplement]. (DOI http://dx.doi.org/10.1007/s10827-014-0497-5)
  6. Rajwade A., Rangarajan A., Banerjee A. (2013) Image Denoising using the Higher Order Singular Value Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(4), pp. 849-862.
  7. Alptekinoglu A., Banerjee A., Paul A. A., Jain N. (2013) Inventory Pooling to Deliver Differentiated Service. Manufacturing and Service Operations Management 15(1), pp. 33-44.
  8. Kumar R., Banerjee A., Vemuri B. C., Pfister H. (2012) Trainable Convolution Filters and their Application to Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(7), pp. 1423-1436.
  9. VanderKraats N. D., Banerjee A. (2011) A Finite-Sample, Distribution-Free, Probabilistic Lower Bound on Mutual Information. Neural Computation, 23(7), pp. 1862-1898.
  10. Kumar R., Barmpoutis A., Banerjee A., Vemuri B. C. (2011) Non-Lambertian Reflectance Modeling and Shape Recovery of Faces using Tensor Splines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3), pp. 553-567.
  11. Gurumoorthy K. S., Rajwade A., Banerjee A., Rangarajan A. (2010) A Method for Compact Image Representation using Sparse Matrix and Tensor Projections onto Exemplar Orthonormal Bases. IEEE Transactions on Image Processing, 19(2), pp. 322-334.
  12. Gurumoorthy K. S., Banerjee A., Paul A. (2009) Dynamics of 2-worker bucket brigade assembly line with blocking and instantaneous walk-back. Operations Research Letters, 37(3), pp. 159-162. (Available via Science Direct here)
  13. Rajwade A., Banerjee A., Rangarajan A. (2008) Probability Density Estimation using Isocontours and Isosurfaces: Application to Information Theoretic Image Registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(3), pp. 475-491.
  14. Meng H., Banerjee A., Zhou L. (2007) BLISS 2.0: a web-based tool for predicting conserved regulatory modules in distantly-related orthologous sequences. Bioinformatics, 23(23), pp. 3249-3250.
  15. Banerjee A., Series P., Pouget A. (2007) Dynamical Constraints on using Precise Spike Timing to Compute in Recurrent Cortical Networks. Neural Computation, 20(4), pp. 974-993.
  16. Banerjee A., Paul, A. (2007) On Activity Correlation and PERT Bias. European Journal of Operational Research, 189(3), pp. 1208-1261. (Available via Science Direct here)
  17. Banerjee A., Carrillo, J. E., Paul, A. (2007) Projects with Sequential Iteration: Models and Complexity. IIE Transactions, 39, pp. 453-463.
  18. Meng, H., Banerjee A., Zhou, L. (2006) BLISS: biding site level identification of shared signal-modules in DNA regulatory sequences. BMC Bioinformatics, 7:287.
  19. Banerjee A. (2006) On the Sensitive Dependence on Initial Conditions of the Dynamics of Networks of Spiking Neurons. Journal of Computational Neuroscience, 20(3), pp. 321-348. (The original publication is available athttp://www.springerlink.com/content/yt95x8665754735x)
  20. Banerjee A., Paul A. (2005) Average Fill Rate and Horizon Length. Operations Research Letters, 33(5), pp. 525-530. (Available via Science Direct here)
  21. Macskassy S. A., Hirsh, H., Banerjee A., Dayanik A. A. (2003) Converting Numerical Classification into Text Classification.Artificial Intelligence, 143(1), pp. 51-77.
  22. Banerjee A. (2001) On the Phase-Space Dynamics of Systems of Spiking Neurons. II: Formal Analysis. Neural Computation, 13(1), pp. 195-225.
  23. Banerjee A. (2001) On the Phase-Space Dynamics of Systems of Spiking Neurons. I: Model and Experiments . Neural Computation,13(1), pp. 161-193.
  24. Banerjee A. (2001) The roles played by External Input and Synaptic Modulations in the Dynamics of Neuronal Systems. BBS commentary on I. Tsuda, “Towards an interpretation of dynamic neural activity in terms of chaotic dynamical systems”. The Behavioral and Brain Sciences, 24(5), pp. 811-812.
  25. Ellman T., Keane J., Banerjee A., and Armhold G. (1998) A Transformation System for Interactive Reformulation of Design Optimization Strategies . Research in Engineering Design, 10(1), pp.30-61.

Conference Papers:

  1. Kaya, G., Banerjee, A. (2017) Signal Coding and Reconstruction Using Deterministic Spiking Neurons . International Joint Conference on Neural Networks (IJCNN).
  2. Kang, T. S., Banerjee, A. (2017) Learning Deterministic Spiking Neuron Feedback Controllers . International Joint Conference on Neural Networks (IJCNN).
  3. Raiturkar, P., Kleinsmith, A., Keil, A., Banerjee, A., Jain E. (2016) Decoupling Light Reflex from Pupillary Dilation to Measure Emotional Arousal in Videos. ACM Symposium on Applied Perception (SAP).
  4. Islam, M. Sk, Banerjee, A. (2016) Denoising Time Series by way of a Flexible Model for Phase Space Reconstruction. The 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD).
  5. Islam, M. Sk, Banerjee, A. (2016) Automatic Detection of Latent Common Clusters of Groups in MultiGroup Regression. Machine Learning and Data Mining in Pattern Recognition (MLDM).
  6. Sengupta, S., Wang, J., Lee, J., Muller, P., Gulukota, K., Banerjee, A., Ji, Y. (2015) BayClone: Bayesian Nonparametric Inference of Tumor Subclones Using NGS Data . Pacific Symposium on Biocomputing (PSB).
  7. Islam, M. Sk, Banerjee, A. (2014) Variational Inference on Infinite Mixtures of Inverse Gaussian, Multinomial Probit and Exponential Regression . Thirteenth International Conference on Machine Learning and Applications (ICMLA).
  8. Ramaswamy, V., Banerjee, A. (2013) Connectomic Constraints on Computation in Networks of Spiking Neurons . Computational and Systems Neuroscience (COSYNE).
  9. Ramaswamy, V., Banerjee, A. (2012) On the trade-off between single-neuron complexity and network size with respect to spike-timed computations . Twenty First Annual Computational Neuroscience Meeting: CNS*2012.
  10. Kumar, R., Banerjee, A., Vemuri, B. C., Pfister, H. (2011) Maximizing All Margins: Pushing Face Recognition with Kernel Plurality. International Conference on Computer Vision (ICCV).
  11. Fisher, N., Banerjee, A. (2010) A Novel Kernel for Learning a Neuron Model from Spike Train Data. Advances in Neural Information Processing Systems 24 (NIPS).
  12. Kumar, R., Vemuri, B. C., Banerjee, A. (2010) Eigenbubbles: An Enhanced Apparent BRDF Representation. International Conference on Pattern Recognition (ICPR).
  13. Rajwade, A., Rangarajan, A., Banerjee A. (2010) Automated Filter Parameter Selection using Measures of “Noiseness”. Canadian Robot Vision Conference (CRV).
  14. Kumar, R., Banerjee, A., Vemuri, B. C. (2009) Volterrafaces: Discriminant Analysis using Volterra Kernels. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
  15. Rajwade, A., Banerjee, A., Rangarajan, A. (2009) Image Filtering Driven by Level Curves. International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR).
  16. Gurumoorthy, K. S., Rajwade, A., Banerjee, A., Rangarajan, A. (2008) Beyond SVD: Sparse Projections Onto Exemplar Orthonormal Bases for Compact Image Representation. International Conference on Pattern Recognition (ICPR).
  17. Kodipaka, S., Banerjee, A., Vemuri, B. C. (2008) Large Margin Pursuit for a Conic Section Classifier. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
  18. Barmpoutis, A., Kumar, R., Vemuri, B. C., Banerjee, A. (2008) Beyond the Lambertian Assumption: A generative model for Apparent BRDF fields of Faces using Anti-Symmetric Tensor Splines. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
  19. Banerjee, A., Kodipaka, S., Vemuri, B. C. (2006) A Conic Section Classifier and its Application to Image Datasets. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
  20. Rajwade, A., Banerjee, A., Rangarajan, A. (2006) A New Method of Probability Density Estimation with Application to Mutual Information Based Image Registration. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
  21. Rajwade, A., Banerjee, A., Rangarajan, A. (2006) Continuous Image Representations Avoid the Histogram Binning Problem in Mutual Information Based Image Registration. The Third IEEE International Symposium on Biomedical Imaging (ISBI).
  22. Banerjee A., Pouget A. (2003) Dynamical Constraints on Computing with Spike Timing in the Cortex. Advances in Neural Information Processing Systems 15 (NIPS).
  23. Macskassy S. A., Hirsh, H., Banerjee A., Dayanik A. A. (2001) Using Text Classifiers for Numerical Classification. The Seventeenth International Joint Conference on Artificial Intelligence (IJCAI).
  24. Macskassy S. A., Banerjee A., Davison B. D., Hirsh H. (1998) Human Performance on Clustering Web Pages: A Preliminary Study.The Fourth International Conference on Knowledge Discovery and Data Mining (KDD).
  25. Banerjee A., Hirsh H., and Ellman T. (1995) Inductive Learning of Feature Tracking Rules for Scientific Visualization. Workshop on Machine Learning in Engineering, IJCAI.
  26. Hirsh H., Ellman T., Banerjee A., Drischel D., Yao H., and Zabusky N. (1995) Reduced Model Formation for 2D Vortex Interactions Using Machine Learning. Systematic Methods of Scientific Discovery AAAI Symposium.
  27. Banerjee A. (1994) Initializing Neural Networks using Decision Trees. Proceedings of the International Workshop on Computational Learning and Natural Learning Systems (CLNL).

Others:

  1. Banerjee A. (2002) The Spike Activity of Neocortical Columns: A Dynamical Systems Analysis. Neural Information and Coding,(abstract).
  2. Banerjee, A. (2001) The Phase-Space Dynamics of Systems of Spiking Neurons. Ph.D Thesis, Department of Computer Science, Rutgers University.
Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s