Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

School of Artificial Intelligence and Data Science (AIDE)

Often, the real world variables are characterized with vagueness (represented by fuzzy set theory), associated hesitancy of the agent (represented by intuitionistic fuzzy set theory), and randomness (represented by probability) at the same time. Intuitionistic fuzzy set theory extends the fuzzy set theory to take account of hesitancy of the observer in addition to vagueness. We propose an integrated framework based on intuitionistic fuzzy set and probability theories to deal with the uncertainty posed by vagueness and randomness. The study is applied in an intelligent oil level controller. © 2018 IEEE.

World University root node

ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

Intelligent controllers for uncertain systems

In the literature of variational inequalities, there has been a lot of studies about the role of gap functions in the development of error bounds specially for the case where the variational inequality is described by a strongly monotone mapping. However the role of the dual gap function in devising error bounds, to the best of our knowledge, has not been thoroughly investigated. In this article we focus on the dual gap function for monotone variational inequalities. We highlight some properties of the dual gap function which are not shared by the other gap functions and also show how it can be used to develop error bounds for strongly monotone variational inequalities with convex and compact feasible sets. © 2018 Heldermann Verlag. All rights reserved.

Journal of Convex Analysis

The dual gap function and error bounds for strongly monotone variational inequalities

Visual cues from the speaker's face influence the perception of speech. An example of this influence is demonstrated by the McGurk-effect where illusory (cross-modal) sounds are perceived following presentation of incongruent audio-visual (AV) stimuli. Previous studies report the engagement of specific cortical modules that are spatially distributed during cross-modal perception. However, the limits of the underlying representational space and the cortical network mechanisms remain unclear. In this combined psychophysical and electroencephalography (EEG) study, the participants reported their perception while listening to a set of synchronous and asynchronous incongruent AV stimuli. We identified the neural representation of subjective cross-modal perception at different organizational levels-at specific locations in sensor space and at the level of the large-scale brain network estimated from between-sensor interactions. We identified an enhanced positivity in the event-related potential peak around 300 ms following stimulus onset associated with cross-modal perception. At the spectral level, cross-modal perception involved an overall decrease in power at the frontal and temporal regions at multiple frequency bands and at all AV lags, along with an increased power at the occipital scalp region for synchronous AV stimuli. At the level of large-scale neuronal networks, enhanced functional connectivity at the gamma band involving frontal regions serves as a marker of AV integration. Thus, we report in one single study that segregation of information processing at individual brain locations and integration of information over candidate brain networks underlie multisensory speech perception. © 2018 by Koninklijke Brill NV, Leiden, The Netherlands.

Multisensory Research

Segregation and Integration of Cortical Information Processing Underlying Cross-Modal Perception

Using state-level data on India's MidDay Meal program (school lunch program for children) we scrutinize if funds disbursed and food-grains supplied for the purpose can actually serve as good determinants of number of children covered (fed) by the scheme (our dependent variable). Our standard regression studies find that the effect of food-grain supplied has statistically significant effect on the dependent variable while the marginal effects of funds/money disbursed is not statistically significant. Using LASSO based Machine Learning techniques and after controlling for several correlated variables and state level factors we find that both policy variables-funds and food-grains however act as good out-of-sample predictors of number of children being covered. Evaluation of out-of-sample prediction performance of regression models and covariates is a very important but mostly an uncharted territory in development economics. Note that funds are used partly to provide fixed costs of the food service provided and therefore it is not surprising that the coefficient estimate of this covariate (i.e., its marginal effect on dependent variable) does not appear to be statistically significant; but it can still act as a good overall predictor for our dependent variable.

Applied Econometrics and International Development

India'S Mid-Day Meal Program And Schooling: An Evaluation Based On Machine Learning

Spatial cells in the hippocampal complex play a pivotal role in the navigation of an animal. Exact neural principles behind these spatial cell responses have not been completely unraveled yet. Here we present two models for spatial cells, namely the Velocity Driven Oscillatory Network (VDON) and Locomotor Driven Oscillatory Network. Both models have basically three stages in common such as direction encoding stage, path integration (PI) stage, and a stage of unsupervised learning of PI values. In the first model, the following three stages are implemented: head direction layer, frequency modulation by a layer of oscillatory neurons, and an unsupervised stage that extracts the principal components from the oscillator outputs. In the second model, a refined version of the first model, the stages are extraction of velocity representation from the locomotor input, frequency modulation by a layer of oscillators, and two cascaded unsupervised stages consisting of the lateral anti-hebbian network. The principal component stage of VDON exhibits grid cell-like spatially periodic responses including hexagonal firing fields. Locomotor Driven Oscillatory Network shows the emergence of spatially periodic grid cells and periodically active border-like cells in its lower layer; place cell responses are found in its higher layer. This model shows the inheritance of phase precession from grid cell to place cell in both one- and two-dimensional spaces. It also shows a novel result on the influence of locomotion rhythms on the grid cell activity. The study thus presents a comprehensive, unifying hierarchical model for hippocampal spatial cells. © 2018 Federation of European Neuroscience Societies and John Wiley & Sons Ltd

European Journal of Neuroscience

A unified hierarchical oscillatory network model of head direction cells, spatially periodic cells, and place cells

Oscillatory phenomena are ubiquitous in the brain. Although there are oscillator-based models of brain dynamics, their universal computational properties have not been explored much unlike in the case of rate-coded and spiking neuron network models. Use of oscillator-based models is often limited to special phenomena like locomotor rhythms and oscillatory attractor-based memories. If neuronal ensembles are taken to be the basic functional units of brain dynamics, it is desirable to develop oscillator-based models that can explain a wide variety of neural phenomena. Autoencoders are a special type of feed forward networks that have been used for construction of large-scale deep networks. Although autoencoders based on rate-coded and spiking neuron networks have been proposed, there are no autoencoders based on oscillators. We propose here an oscillatory neural network model that performs the function of an autoencoder. The model is a hybrid of rate-coded neurons and neural oscillators. Input signals modulate the frequency of the neural encoder oscillators. These signals are then multiplexed using a network of rate-code neurons that has afferent Hebbian and lateral anti-Hebbian connectivity, termed as Lateral Anti Hebbian Network (LAHN). Finally the LAHN output is de-multiplexed using an output neural layer which is a combination of adaptive Hopf and Kuramoto oscillators for the signal reconstruction. The Kuramoto-Hopf combination performing demodulation is a novel way of describing a neural phase-locked loop. The proposed model is tested using both synthetic signals and real world EEG signals. The proposed model arises out of the general motivation to construct biologically inspired, oscillatory versions of some of the standard neural network models, and presents itself as an autoencoder network based on oscillatory neurons applicable to time series signals. As a demonstration, the model is applied to compression of EEG signals. © 2018 Soman, Muralidharan and Chakravarthy.

Fulltext

Frontiers in Computational Neuroscience

An oscillatory neural autoencoder based on frequency modulation and multiplexing

Purpose: This paper aims to learn a decision-maker’s (DM’s) decision model that is characterized in terms of the attitudinal character and the attributes weight vector, both of which are specific to the DM. The authors take the learning information in the form of the exemplary preferences, given by a DM. The learning approach is formalized by bringing together the recent research in the choice models and machine learning. The study is validated on a set of 12 benchmark data sets. Design/methodology/approach: The study includes emerging preference learning algorithms. Findings: Learning of a DM’s attitudinal choice model. Originality/value: Preferences-based learning of a DM’s attitudinal decision model. © 2018, Emerald Publishing Limited.

Kybernetes

Learning attitudinal decision model through pair-wise preferences

In this chapter, we seek to study the interrelation between an equilibrium problem and the variational inequality problem. Under most natural assumption, the equilibrium problem is equivalent to an associated variational inequality. Hence, the existence results for equilibrium problems can be obtained from the existence results for variational inequality problems and vice versa. We study a problem of existence of Nash equilibrium in an oligopolistic market and show that it is equivalent to a variational inequality under the most natural economic assumption. We also study the relation between quasi-equilibrium problem and quasi-variational inequality. © 2018, Springer Nature Singapore Pte Ltd.

Indian Statistical Institute Series

About the Links Between Equilibrium Problems and Variational Inequalities

Brain connectivity analysis has provided crucial insights to pinpoint the differences between autistic and typically developing (TD) children during development. The aim of this study is to investigate the functional connectomics of autism spectrum disorder (ASD) versus TD and underpin the effects of development, disease, and their interactions on the observed atypical brain connectivity patterns. Resting-state functional magnetic resonance imaging (rs-fMRI) from the Autism Brain Imaging Data Exchange (ABIDE) data set, which is stratified into two cohorts: children (9-12 years) and adolescents (13-16 years), is used for the analysis. Differences in various graph theoretical network measures are calculated between ASD and TD in each group. Furthermore, two-factor analysis of variance test is used to study the effect of age, disease, and their interaction on the network measures and the network edges. Furthermore, the differences in connection strength between TD and ASD subjects are assessed using network-based statistics. The results showed that ASD exhibits increased functional integration at the expense of decreased functional segregation. In ASD adolescents, there is a significant decrease in modularity suggesting a less robust modular organization, and an increase in participation coefficient suggesting more random integration and widely distributed connection edges. Furthermore, there is significant hypoconnectivity observed in the adolescent group especially in the default mode network, while the children group shows both hyper- and hypoconnectivity. This study lends support to a model of global atypical connections and further identifies functional networks and areas that are independently affected by age, disease, and their interaction. © Copyright 2018, Mary Ann Liebert, Inc., publishers 2018.

Brain Connectivity

Age, Disease, and Their Interaction Effects on Intrinsic Connectivity of Children and Adolescents in Autism Spectrum Disorder Using Functional Connectomics

The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20–200 ms, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training. © Springer Nature Singapore Pte Ltd. 2018.