Department of Data Science

Indian Institute of Technology Palakkad&nbsp;(IIT Palakkad or IIT PKD) is a public autonomous&nbsp;engineering&nbsp;and&nbsp;research&nbsp;institute located in&nbsp;Palakkad,&nbsp;Kerala. It was&nbsp;one of the five new&nbsp;IITs&nbsp;proposed in the&nbsp;2014 Union budget of India. The campus was inaugurated on 3 August 2015. The institute has 94 faculty, 978 students, and 63 non-teaching staffs.

IT Palakkad currently offers four-year Bachelor of Technology (B.Tech) and two years MS programmes in 8 different engineering disciplines including&nbsp;Computer Science, Electrical, Mechanical, Civil among others.

&nbsp;

IIT Palakkad

We present SCCA-HSIC, a method for finding sparse non-linear multivariate relations in high-dimensional settings by maximizing the Hilbert-Schmidt Independence Criterion (HSIC). We propose efficient optimization algorithms using a projected stochastic gradient and Nyström approximation of HSIC. We demonstrate the favourable performance of SCCA-HSIC over competing methods in detecting multivariate non-linear relations both in simulation studies, with varying numbers of related variables, noise variables, and samples, as well as in real datasets. © 2018 IEEE.

World University root node

Proceedings - IEEE International Conference on Data Mining, ICDM

Sparse Non-linear CCA through Hilbert-Schmidt Independence Criterion

Motivation: In the analysis of metabolism, two distinct and complementary approaches are frequently used: Principal component analysis (PCA) and stoichiometric flux analysis. PCA is able to capture the main modes of variability in a set of experiments and does not make many prior assumptions about the data, but does not inherently take into account the flux mode structure of metabolism. Stoichiometric flux analysis methods, such as Flux Balance Analysis (FBA) and Elementary Mode Analysis, on the other hand, are able to capture the metabolic flux modes, however, they are primarily designed for the analysis of single samples at a time, and not best suited for exploratory analysis on a large sets of samples. Results: We propose a new methodology for the analysis of metabolism, called Principal Metabolic Flux Mode Analysis (PMFA), which marries the PCA and stoichiometric flux analysis approaches in an elegant regularized optimization framework. In short, the method incorporates a variance maximization objective form PCA coupled with a stoichiometric regularizer, which penalizes projections that are far from any flux modes of the network. For interpretability, we also introduce a sparse variant of PMFA that favours flux modes that contain a small number of reactions. Our experiments demonstrate the versatility and capabilities of our methodology. The proposed method can be applied to genome-scale metabolic network in efficient way as PMFA does not enumerate elementary modes. In addition, the method is more robust on out-of-steady steady-state experimental data than competing flux mode analysis approaches. Availability and implementation: Matlab software for PMFA and SPMFA and dataset used for experiments are available in https://github.com/aalto-ics-kepaco/PMFA. © The Author(s) 2018. Published by Oxford University Press on behalf of Nucleic Acids Research.

Fulltext

Bioinformatics

Principal metabolic flux mode analysis

Supervised transfer learning algorithms utilize labeled data from auxiliary domains for learning in another domain where labeled data is scarce or absent. Given sufficient cross-domain corresponding instances, one can learn a robust transformation that maps the features across the domains by using any multi-output regression task. However, this cross-domain corresponding data is not available for real-world transfer tasks across heterogeneous feature spaces such as, cross-domain activity recognition and cross-lingual text/sentiment classification. In this paper, we present a shared label space driven algorithm that transfers labeled knowledge between heterogeneous feature spaces. The proposed algorithm treats the similar label distributions across the domains as pivots to generate cross-domain corresponding data. The shared label distributions and the corresponding data is obtained from the random forest models of the source and target domain. The experimental results on synthetic and real-world benchmark datasets having dissimilar modalities validate the performance of the proposed algorithm against state-of-the-art heterogeneous transfer learning approaches. © 2018 Association for Computing Machinery.

Proceedings of the ACM India Joint International Conference on Data Science {\ldots}

Supervised heterogeneous transfer learning using random forests

Estimating economic and developmental parameters such as poverty levels of a region from satellite imagery is a challenging problem that has many applications. We propose a two step approach to predict poverty in a rural region from satellite imagery. First, we engineer a multi-task fully convolutional deep network for simultaneously predicting the material of roof, source of lighting and source of drinking water from satellite images. Second, we use the predicted developmental statistics to estimate poverty. Using full-size satellite imagery as input and without pre-trained weights, our models are able to learn meaningful features including roads, water bodies and farm lands and achieve a performance that is close to the optimum. In addition to speeding up the training process, the multi-task fully convolutional model is able to discern task specific and independent feature representations.

Proceedings of the 30th Innovative Applications of Artificial Intelligence Conference, IAAI 2018

Multi-task deep learning for predicting poverty from satellite images

This work proposes and evaluates a novel approach to determine interesting categorical attributes for lists of entities. Once identified, such categories are of immense value to allow constraining (filtering) a current view of a user to subsets of entities. We show how a classifier is trained that is able to tell whether or not a categorical attribute can act as a constraint, in the sense of human-perceived interestingness. The training data is harnessed from Web tables, treating the presence or absence of a table as an indication that the attribute used as a filter constraint is reasonable or not. For learning the classification model, we review four well-known statistical measures (features) for categorical attributes---entropy, unalikeability, peculiarity and coverage. We additionally propose three new statistical measures to capture the distribution of data, tailored to our main objective. The learned model is evaluated by relevance assessments obtained through a user study, reflecting the applicability of the approach as a whole and, further, demonstrates the superiority of the proposed diversity measures over existing statistical measures like information entropy.

arXiv preprint arXiv:1711.

Learning Interesting Categorical Attributes for Refined Data Exploration

In the approaching era of IoT, flexible and low power accelerators have become essential to meet aggressive energy efficiency targets. During the last few decades, Coarse Grain Reconfigurable Arrays (CGRA) have demonstrated high energy efficiency as accelerators, especially for high-performance streaming applications. While existing CGRAs mostly rely on partial and full predication techniques to support conditional branches, inefficient architecture and mapping support for handling control flow limits the use of CGRAs in accelerating either only inner loop bodies, or transformed loops specifically adapted to the target CGRA. This paper proposes a novel CGRA architecture with support for jump and conditional jump instructions and a lightweight global synchronization mechanism to enable complete Control Data Flow Graph (CDFG) mapping in an ultra-low-power environment. The architecture is coupled with a complete design flow that efficiently maps applications with heavy control flow starting from a generic C language description. The proposed mapping approach reduces the impact of wasteful instruction issues in the conventional approaches of predication providing an average energy improvement of 1.44x and 1.6x when compared to the state of the art partial and full predication techniques. Moreover, the proposed method achieves an average speed-up up to 21x and an energy improvement up to 50.42x while executing applications with heavy control flow with respect to sequential execution on a low-power embedded CPU, demonstrating its suitability for next generation IoT applications. © 2017 IEEE.

Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

Efficient mapping of CDFG onto coarse-grained reconfigurable array architectures

In this paper, we study the impact of locality on the decoding of binary cyclic codes under two approaches, namely ordered statistics decoding (OSD) and trellis decoding. Given a binary cyclic code having locality or availability, we suitably modify the OSD to obtain gains in terms of Signal-To-Noise ratio, for a given reliability and essentially the same level of decoder complexity. With regard to trellis decoding, we show that careful introduction of locality results in the creation of cyclic subcodes having lower maximum state complexity. We also present a simple upper-bounding technique on the state complexity profile, based on the zeros of the code. Finally, it is shown how the decoding speed can significantly be increased in the presence of locality, in the moderate-to-high SNR regime, by making use of a quick-look decoder that often returns the ML codeword. © 2017 IEEE.

IEEE International Symposium on Information Theory - Proceedings

A study on the impact of locality in the decoding of binary cyclic codes

Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)

Exploring databases via reverse engineering ranking queries with Paleo

Due to increasing demand of low power computing, and diminishing returns from technology scaling, industry and academia are turning with renewed interest toward energy-efficient programmable accelerators. This paper proposes an Integrated Programmable-Array accelerator (IPA) architecture based on an innovative execution model, targeted to accelerate both data and control-flow parts of deeply embedded vision applications typical of edge-nodes of the Internet of Things (IoT). In this paper we demonstrate the performance and energy efficiency of IPA implementing a smart visual trigger application. Experimental results show that the proposed accelerator delivers 507 MOPS and 142 MOPS/mW on the target application, surpassing a low-power processor optimized for DSP applications by 6x in performance and by 10x in energy efficiency. Moreover, it surpasses performance of state of the art CGRAs only capable of implementing data-flow portion of applications by 1.6x, demonstrating the effectiveness of the proposed architecture and computational model. © 2017 IEEE.

Proceedings - IEEE International Symposium on Circuits and Systems

A 142MOPS/mW integrated programmable array accelerator for smart visual processing

Recommending lifestyle articles is of immediate interest to theffecommerce industry and is beginning to attract research attention. Offen followed strategies, such as recommending popular items are inadequate for this vertical because of two reasons. Firstly, users have their own personal preference over items, referred to as personal styles, which lead to the long-tail phenomenon. Secondly, each user displays multiple personas, each persona has a preference over items which could be dictated by a particular occasion, e.g. dressing for a party would be different from dressing to go to o?ce. Recommendation in this vertical is crucially dependent on discovering styles for each of the multiple personas. There is no literature which addresses this problem. We posit a generative model which describes each user by a Simplex Over PERsona, SOPER, where a persona is described as the individuals preferences over prevailing styles modelled as topics over items. The choice of simplex and the long-tail nature necessitates the use of stick-breaking process. The main technical contribution is an efficient collapsed Gibbs sampling based algorithm for solving the attendant inference problem. Trained on large-scale interaction logs spanning more than halfa-million sessions collected from an e-commerce portal, SOPER outperforms previous baselines such as [9] by a large margin of 35% in identifying persona. Consequently it outperforms several competitive baselines comprehensively on the task of recommending from a catalogue of roughly 150 thousand lifestyle articles, by improving the recommendation quality as measured by AUC by a staggering 12:23%, in addition to aiding the interpretability of uncovered personal and fashionable styles thus advancing our precise understanding of the underlying phenomena. © 2017 ACM.